In robotics systems, vast amounts of visual data are easily captured at high resolution using low-cost, low-power hardware. Yet, limited bandwidth and on-device compute resources prevent full utilization when transmitted via conventional codecs like JPEG/MPEG. Newer codecs, like AV1/AVIF, improve the rate-distortion trade-off, but demand far more resources for encoding, impractical without custom ASICs. Recent asymmetric autoencoders deliver high quality under extreme power and bandwidth constraints, but add prohibitive decoding cost and use bespoke formats that ignore decades of infrastructure built around standards like JPEG. To address these limitations, we introduce a compression framework for cloud robotics based on a Sensor Embedded Autoencoder paired with a One-Time Transcode for Efficient Reconstruction (SEAOTTER). Because the sensor, cloud, and consumer stages face very different power and bandwidth budgets, SEAOTTER combines the compactness of a learned latent with the broad usability of a standard JPEG file. Since naive transcoding degrades performance, we propose a learnable JPEG color and quantization transform that enables increased accuracy for global, dense, and vision-language-based perception. Using SEAOTTER, we train both general-purpose and task-aware transcoding pipelines for a pre-trained, frozen encoder. At a compression ratio of 200:1 and compared to AVIF, we observe 7 times faster encoding, 3.5 times faster decoding, and +8% ImageNet top-1 accuracy, while retaining compatibility with JPEG infrastructure. Our code is available at https://github.com/UT-SysML/seaotter .

We introduce D^3S Consensus, a physics-based, closed-form algorithm that unifies depth-from-defocus (DfD) and stereo to achieve highly accurate depth estimation throughout an extended working range beyond the depth-of-field (DoF) of cameras. Given a pair of dual-defocus stereo images, the method estimates an overdetermined set of depth using a novel DfD theory, Dual Differential Defocus (D^3), and (S)tereo in a coupled fashion. It then picks the most confident depth prediction from the set by enforcing consensus between these physically independent cues to reject unreliable estimates. Analysis shows that D^3S achieves a comparable working range under the same error tolerance with 10x smaller baseline than previous triangulation-based depth estimation systems. This enables compact passive binocular rangefinders with substantially smaller form factors than conventional stereo and DfD designs. We demonstrate the first D^3S prototype with only 4 mm baseline and 12 mm EFL. It generates up to 900 x 1800-pixel depth maps with 1-cm mean absolute error over 0.3-1.64 m from a snapshot acquisition. This has surpassed the reported accuracy of certain commercially available stereo cameras with much larger form factors.

Despite the success of audio-visual large-language models (LLMs), they can produce plausible but ungrounded outputs, termed hallucination. Existing benchmarks focus on environmental sounds (e.g., dog barking) to indicate event occurrence. In contrast, human speech carries fundamentally different, rich semantics and temporal structures, yet it remains unexplored whether current models can accurately align speech content with corresponding visual signals. In this work, we show that speech content can induce hallucinations in audio-visual LLMs. To systematically study this, we introduce SVHalluc, the first comprehensive benchmark for evaluating speech-vision hallucination in audio-visual LLMs. Our benchmark diagnoses speech-vision hallucinations from two critical and complementary aspects: semantic and temporal. Experimental results demonstrate that state-of-the-art open-source audio-visual LLMs struggle with aligning speech content with corresponding visual signals, with a near-random accuracy on multiple tasks. In contrast, Gemini 2.5 Pro significantly outperforms the open-source models. Our analysis suggests that their failures stem from limited ability in cross-modality understanding, despite strong performance in single-modality perception. Our work uncovers a new and fundamental limitation of current audio-visual LLMs and highlights the need for speech-grounded video comprehension. Project page: https://chenshuang-zhang.github.io/projects/svhalluc/.

We identify and resolve a previously unreported failure mode in TensoRF when applied to X-ray attenuation fields: the default density shift of -10, originally introduced for RGB scene reconstruction, suppresses density gradients and prevents sparse-view medical reconstruction regardless of learning rate or regularization strategy. Setting the density shift to zero restores gradient flow and enables stable volumetric reconstruction of pulmonary nodules from only three orthogonal X-ray projections. Building on this, we propose AReT, an anatomy-regularized tensorial radiance field framework for lung nodule reconstruction using coronal, sagittal, and axial projections from the LIDC-IDRI dataset (19 patients, radiologist-annotated nodules). Unlike existing NeRF approaches requiring dense multi-view acquisition, AReT is designed for sparse-view thoracic imaging and incorporates chest-anatomy-aware regularization combining L1 sparsity and total variation smoothness. A systematic comparison across 11 reconstruction strategies shows anatomy-aware regularization consistently outperforms generative-prior-guided approaches. Evaluated against radiologist consensus segmentations, AReT achieves Pearson r=0.983 (p<0.0001) for clinically actionable nodules >=10 mm (n=14), median absolute volumetric error of 11.4%, near-zero systematic bias of -77.3 mm^3, and 8.4x improvement over spherical volume approximation.

This paper studies whether audio, images, and video can share a common wavelet token schema rather than relying on separate modality-specific latent grids. It introduces a preliminary continuous-token model built around a one-level Haar DWT/IDWT frontend, a shared coefficient-token layout, optional structural metadata, lightweight modality value adapters, and a shared token-wise encoder-decoder trunk. On Speech Commands, EuroSAT RGB, and DAVIS 2017 data, a dense shared model reaches 39.92 dB audio, 29.37 dB image, and 23.93 dB video PSNR. A matched-rate sweep under continuous latent scalar budgets indicates that the visual gains are not explained solely by latent capacity, while also showing that additive metadata embeddings are not a universal source of improvement. Finally, fixed-rate energy selection provides a strong non-parametric baseline: energy_global improves average PSNR over uniform selection by 16.73 dB for audio, 16.90 dB for images, and 15.86 dB for video under compressed keep ratios. Masked sparse training reaches 34.45 dB video PSNR with 50% of dense tokens. The results support a unified wavelet token schema and sparse token interface, while stopping short of establishing a universal discrete vocabulary.

Multi-view video recordings are increasingly used to capture the 3D movements of animals in experimental settings, yet extracting rich 3D representations from these recordings remains challenging. Supervised pose estimation requires extensive manual annotation, while general-purpose 3D reconstruction models trained on generic scene datasets fail on the specialized imagery and sparse-view setting of laboratory experiments. We address these limitations with BEAST3D, a self-supervised pretraining framework that learns 3D visual representations from unlabeled, calibrated multi-view video. BEAST3D uses a vision transformer to predict 3D Gaussian splats that reconstruct held-out views through differentiable rendering, while simultaneously segmenting the animal from the background. BEAST3D reconstructs 3D structure with as few as four views by conditioning directly on known camera parameters--unlike general-purpose models, which must estimate camera geometry from dense overlapping viewpoints that are seldom available in lab settings. Through comprehensive evaluation across four species, we demonstrate that BEAST3D produces rich, viewpoint-invariant features that transfer effectively to three downstream tasks: novel view synthesis, which validates the quality of the learned 3D representations; multi-view pose estimation, which provides the sparse keypoint trajectories widely used in behavioral analysis; and neural encoding, which relates 3D behavioral features to simultaneously recorded neural activity. BEAST3D thus establishes a versatile framework for behavioral analysis that leverages 3D structure in modern multi-view laboratory recordings.

Reconstructing interactive, simulation-ready 3D scenes from a single image is a critical bottleneck for robotic manipulation. While recent single-image lifters recover plausible per-object shapes, composing them yields scenes that collapse under physical simulation due to interpenetrating, hovering, or sinking objects. Existing physics-aware methods address this strictly as a post-hoc layout correction, leaving the underlying geometric errors unresolved. To address this, we introduce SimuScene, a compositional 3D reconstruction pipeline that puts physics in the loop of shape and layout estimation. Rather than using physics merely for layout cleanup, we utilize the physics engine as a diagnostic measurement tool during the generative process itself. By diagnostically simulating reconstructed objects under gravity, we convert penetration and support failures into quantitative correction signals that drive gravity-axis stretching and amodal shape resampling. This physics-informed feedback loop mitigates accumulated reconstruction errors and produces a stable, simulation-ready compositional 3D scene. Extensive experiments demonstrate state-of-the-art performance on physical stability and geometric alignment benchmarks. We further highlight SimuScene's utility by deploying reconstructed environments in humanoid control and robot-arm manipulation tasks.

This paper investigates "free lunch" strategies to boost the performance of lidar semantic scene completion (SSC) without requiring complex architectural redesigns. We first demonstrate that endowing input point clouds with semantic pseudo-labels from off-the-shelf segmentors significantly improves the performance of existing architectures. By evaluating these models against an oracle, we establish that high-quality semantic priors are a primary driver of mIoU gains. Furthermore, we equip the input lidar scan with visibility information that distinguishes between empty and unknown spaces, which provides a secondary performance boost across the tested architectures. Using these simple enhancements, we observe that older models remain competitive with state-of-the-art systems, and can even outperform them. Our code is available at https://github.com/astra-vision/SSC-Priors.

We investigate whether neuron populations within neural networks evolve predictably with scale, extending scaling laws beyond macroscopic observables such as loss. To probe this question, we study Rosetta Neurons, a previously characterized class of neurons whose activation patterns are similar across independently trained models (Dravid et al., 2023). In separate analyses of language models up to 30B parameters and vision models up to 5B parameters, we observe that the population of Rosetta Neurons follows a sublinear power law in model size, growing in absolute number but occupying a shrinking fraction of the total neuron count. We further observe a Neuron Polarization Effect: Rosetta Neurons become more selective and increasingly monosemantic with scale, separating from a growing non-Rosetta population that remains less selective. An analytical model balancing feature utility against limited neuron capacity explains the sublinear power-law scaling and this polarization effect. Finally, we find that Rosetta Neurons become more domain-specialized with scale and illustrate their selectivity through a targeted data-filtering case study for continued pretraining. Our results point to a scaling law for interpretable, shared neuron-level structure, linking model size to systematic changes in neuron universality, selectivity, and specialization.

Images composed of 2D pixel arrays are the standard input to computer vision algorithms, yet many underlying computations can be distributed across pixels. Transmitting raw, redundant, and noisy pixel data off the sensor remains inefficient, motivating a shift toward focal-plane sensor-processors that perform a significant part of the computation directly within each pixel. We envision pixels synthesizing higher-level signals locally, reducing downstream load, and providing richer inputs for higher-level vision tasks. We propose a fully parallelizable form of visual odometry and depth estimation across pixels, where sensor-processors exchange information through Gaussian Belief Propagation (GBP) to achieve consensus about camera motion and infer depth from per-pixel photometric observations and a surface normal prior. To maintain geometric stability during optimization, we introduce a keyframe-like anchoring mechanism that regulates the effective baseline between frames, enabling consistent motion and depth updates. Our method is evaluated on realistic datasets, demonstrating the feasibility of GBP-based pixel-level distributed odometry and depth estimation with keyframe anchoring on-sensor. Project Page: https://www.shinjeongkim.com/pixvod/

Previous work has evaluated physics reasoning in foundation models using synthetic or semi-synthetic scenes and visual question-answering tasks. However, these benchmarks emphasize high-level events and lack the visual fidelity required to assess true low-level Newtonian understanding. We introduce NewtPhys, a 4D physically annotated dataset built from multiview images of real-world scenes with physics-grounded simulations. The dataset provides dense, fine-grained annotations across timesteps -- including 3D forces and amodal per-pixel quantities covering physics, tracking, semantics and geometry -- bridging the gap between simplistic synthetic setups and realistic visual complexity. Using NewtPhys, we systematically evaluate 56 VLMs, including 54 open-weight models and 2 closed-source frontier models, and 10 VFMs and reveal limitations in low-level physics reasoning. Beyond benchmarking, our dataset enables future research in physics-grounded vision and the development of next-generation physics-aware evaluations. Code and datasets are available at https://astra-vision.github.io/NewtPhys.

We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale motion corpus for whole-body control. Unlike prior shallow MLP trackers constrained by scarce data and an agility-generalization trade-off, Humanoid-GPT is pre-trained on a 2B-frame retargeted corpus that unifies all major mocap datasets with large-scale in-house recordings. Scaling both data and model capacity yields a single generative Transformer that tracks highly dynamic behaviors while achieving unprecedented zero-shot generalization to unseen motions and control tasks. Extensive experiments and scaling analyses show that our model establishes a new performance frontier, demonstrating robust zero-shot generalization to unseen tasks while simultaneously tracking highly dynamic and complex motions.

Representations of the world, arguably, contain information about features (e.g. something is blue, something is a circle) but also information about which features are part of the same object (e.g. the circle is blue), which we call binding information. Any system with the ability to understand scenes with multiple objects must be able to solve the binding problem: it needs to know which features belong together. However, despite work showing that Vision Transformers (ViTs) know which patches belong together, it is not known whether current deep learning models learn to exhibit binding information, i.e., for features. We may believe that there is not much binding information, after all misattributing features to wrong objects is a common failure of ViT-based architectures, especially in scenes with objects sharing features. Here we formalize the binding problem with an information-theoretic approach, and introduce a probing method to measure binding information in model representations. We perform experiments on ViTs, measuring binding from different components of the architecture, such as the image summary token [CLS] or the spatial tokens. We use datasets with different binding challenges, such as feature sharing, occlusion, and natural features, while comparing the performance of several pre-trained ViTs. Overall, our research demonstrates binding as a key ingredient to strong visual recognition and reasoning.

Causal video generators must predict from the past, but they need not learn only from it. In streaming autoregressive video diffusion, each emitted segment becomes a commitment that future segments must preserve. Standard training, however, only asks each causal state to explain the present. This creates what we call a representation-level planning gap: states that fit the current segment may discard identity, layout, and motion information needed for a consistent future. We introduce Video-Mirai, a training-only method that closes this gap without changing causal inference: the generator rolls out causally, a frozen foresight encoder reads the completed rollout non-causally, and a lightweight predictor distills the resulting stopped-gradient targets into causal states. Future frames supervise representations, never generator inputs. At inference, the encoder and predictor are discarded, leaving the original architecture, per-step FLOPs, and KV-cache behavior unchanged. Video-Mirai improves a strong Causal-Forcing baseline on 5-second VBench from 83.8 to 84.6 in terms of Total Score. On 30-second rollouts beyond the training horizon, subject consistency improves from 84.9 to 88.5 and background consistency from 90.2 to 91.9. Ablations identify future-conditioned targets as the key ingredient, and probes show that future frames become more decodable from current features. Causality should constrain inference, not representation supervision. Our study highlights that visual autoregressive models need foresight. Project page: https://y0uroy.github.io/Video-Mirai.

As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount -- physical actions carry immediate and irreversible consequences that digital errors do not. We introduce the Vision-Language Embodied Safety Agent (VLESA), a framework that monitors human activities from egocentric video and triggers real-time safety interventions when dangerous actions are predicted. VLESA addresses intent-dependent safety where identical actions can be safe or dangerous depending on context. A dataset pairing egocentric frames with goal-conditioned safety annotations is introduced, enabling a goal-conditioned safety Q-filter trained via GRPO that evaluates actions with respect to inferred intent without retraining. On top of that, an intent-action prediction agent is proposed to jointly infer goals and predict future actions from video. On the ASIMOV-2.0 benchmark, VLESA achieves higher intervention accuracy at the exact ground-truth frame compared to baselines, while the GRPO-trained Q-filter improves action safety by over 41 percentage points through goal-conditioned constrained decoding. Code is available at https://github.com/HanjiangHu/VLESA.

Human experience in digital environments offers a vast, underexplored resource of authentic, untrimmed interactions that contain rich procedural knowledge. We introduce Demo2Tutorial, a framework that transforms this experience captured via screen recordings and interaction logs into structured, multimodal software tutorials for teaching both humans and agents. Demo2Tutorial first collects human experience via a dedicated recorder, then parses raw experience using a multimodal Action Parser to reconstruct perception, action, and intent. A Step Planner then abstracts these steps into hierarchical task graphs representing goals and steps. Finally, a Tutorial Composer transforms the parsed experience into structured, reusable image-text instructions. We evaluate the tutorial generation quality on a new benchmark derived from official software documentation. We further demonstrate that this distilled representation benefits (i) human learning, by automatically generating multimodal tutorials, and (ii) agent learning, by improving downstream GUI-agent planning and generalization. Experiments show Demo2Tutorial produces high-quality tutorials that surpass human-authored ones and significantly outperform baseline methods, while enabling both faster human task completion and improved GUI agent planning, demonstrating that structured tutorials distilled from human experience can serve as effective knowledge representations for advancing both human learning and agent capabilities. Code and data will be available at https://github.com/showlab/Demo2Tutorial.

Inverse adversarial training leverages high-confidence predictions to stabilize robust learning, yet we uncover a critical paradox: high confidence often stems from overfitting to non-causal background correlations rather than intrinsic object semantics. Our investigation reveals that visual context functions as a dual-natured signal, serving as either a necessary supportive prior or a spurious confounder. This insight renders existing blind suppression strategies flawed, as they inevitably lead to severe Feature Loss. To resolve this, we propose High-Confidence Causally Aligned Training (HICAT), a unified framework that establishes a Semantic Equilibrium. Operating on a ``Measure-Debias-Align'' pipeline, HICAT integrates a Learnable Background-Bias Estimator (LBBE) to adaptively diagnose context utility. Guided by this diagnosis, an Adaptive Debiasing mechanism performs surgical logit rectification, complemented by a geometrically grounded Foreground Logit Orthogonal Enhancement (FLOE) loss to enforce rigorous feature disentanglement. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K demonstrate that HICAT consistently improves over matched baselines across diverse architectures (CNNs and ViTs) while significantly reducing the robust generalization gap.

Converting multi-view RGB observations into simulation-ready 3D environments remains challenging because current reconstruction pipelines produce monolithic scene representations without explicit physical structure. They are typically defined up to an arbitrary global rotation and entangle rigid foreground objects with background geometry, which hinders stable physical interaction. Existing solutions often recover interactivity by replacing reconstructed objects with retrieved CAD assets, but this introduces a slow retrieval-and-replacement stage and weakens scene-specific geometric fidelity. We propose GARDEN, an RGB-only framework that reformulates reconstruction as physically-grounded scene factorization and outputs a structured hybrid scene representation. The key idea is to use gravity as a universal physical prior: we first align the reconstruction to a unified Gravity-View frame to resolve gauge ambiguity, then recover object-centric rigid meshes with accurate 6-DoF placement, and finally remove duplicate object geometry from the background through conditional 3D point classification. The resulting representation combines explicit rigid bodies with a decoupled background, enabling direct physics simulation while preserving visual realism. Experiments on both simulated and real multi-view scenes show that GARDEN improves object placement reliability, disentanglement quality, and rendering-simulation efficiency compared with retrieval-based baselines.

Understanding a video requires more than recognizing isolated moments, as humans continuously track entities, states, and events over time. This capacity for visual state tracking is fundamental to video understanding, yet remains underexplored in current evaluations of Multimodal Large Language Models (MLLMs). We introduce Visual STAte Tracking benchmark (VSTAT), a video-based benchmark designed to diagnose visual state tracking in MLLMs. VSTAT consists of 834 clips drawn from both synthetic and real-world videos, paired with 1,500 questions that cannot be answered from any single frame or short segment, requiring continuous perception and integration of events across the entire video stream. Despite their strong performance on existing video benchmarks, we find that state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines. To analyze this gap, we compare MLLMs' thinking traces with the underlying video stream to understand why and when MLLMs fail on VSTAT. We find that MLLMs reason and track correctly in text, but fail at visually perceiving the events they need to track. Finally, our preliminary evaluation suggests that recent agentic approaches, including MLLM-based video agents and coding agents, do not readily resolve these failures, still falling short on VSTAT.

We propose PatchScene, a novel diffusion-based framework for large-scale LiDAR scene completion. Unlike existing methods that rely on global latent representations or dense voxel grids, PatchScene adopts a patch-based voxel diffusion paradigm that explicitly generates fine-grained geometry within localized 3D regions. To ensure coherent reconstruction at both spatial and temporal scales, we introduce a confidence-guided spatio-temporal fusion mechanism that integrates overlapping patches and adjacent frames in a unified generative process. Furthermore, we design an Annular-Flow diffusion strategy that leverages the radial density pattern of LiDAR scans to progressively propagate high-fidelity information from near-range to far-range regions, enabling spatially unbounded scene completion. Extensive experiments on the SemanticKITTI benchmark demonstrate that PatchScene achieves state-of-the-art performance across all standard metrics, surpassing previous approaches in both geometric accuracy and temporal consistency. Remarkably, the model trained on 20 m LiDAR ranges generalizes effectively to 50 m scenes without retraining, highlighting its strong scalability and generalization capability for real-world autonomous driving applications.

Modern generative models possess a deep understanding of visual content, yet training them for image editing typically requires massive datasets of paired examples. This limits scalability, especially for video editing where collecting paired data is prohibitively expensive. We propose Bootstrap Your Generator (ByG), a general framework for unpaired training of flow matching editing models. It leverages the base model's knowledge without any external signal. Our approach pairs instruction-following cues extracted from the frozen model with cycle-consistency for structure preservation. To make this tractable, we propose to route gradients from downstream losses over clean predictions to noisy training states. We demonstrate state-of-the-art results on challenging data-scarce image and video editing scenarios. Extensive evaluations and user studies show that our method effectively generalizes to unseen domains and outperforms supervised baselines trained on millions of samples. Analysis reveals that our gradient routing bridges the train-inference gap, and extracting semantic cues from a base model provides a robust training signal that obviates the need for external reward models.

While 3D Gaussian Splatting has shown promising results in street scene reconstruction, existing methods require massive numbers of Gaussian primitives to capture fine details, leading to prohibitive storage costs and slow rendering speeds. We observe that dynamic objects (e.g., vehicles and pedestrians) demand high-fidelity representations to maintain temporal consistency, while static background regions often contain substantial redundancy. Motivated by this, we propose SparseStreet, a general compression framework specifically designed for street scenes. First, we introduce a node-based learnable pruning strategy that systematically removes low-contributing Gaussian primitives while preserving visually critical regions. Second, after the scene representation stabilizes, we apply background compression, further reducing redundancy in static regions. Our method effectively preserves the geometry and appearance of dynamic objects while significantly reducing the total number of Gaussian primitives. Extensive experiments on the Waymo and nuScenes demonstrate that SparseStreet achieves up to 80% compression ratio with minimal quality degradation, enabling resource-efficient, high-fidelity dynamic scene reconstruction. Project website: https://sparsestreet.github.io/.

Multi-objective optimization (MOO) underlies many machine learning problems, yet MOO solvers across the loss-balancing, gradient-balancing, and Pareto-based families almost universally hand their reconciled directions to Adam~\cite{kingma2015adam}. We show this coupling introduces two systematic gaps between the solver's intent and the optimizer's execution. The first is a \emph{weighting mismatch}: Adam's second-moment denominator entangles the time-varying preference vector with gradient statistics, marginalizing the preference into a history average and collapsing distinct Pareto trade-offs toward a near-uniform mixture. The second is a \emph{geometric mismatch}: Adam's adaptive metric distorts the Euclidean geometry MOO solvers assume, turning aligned objectives into apparent conflicts. To resolve both jointly, we introduce \textbf{MAdam} (Metric-Aware Multi-Objective Adam), a drop-in wrapper that leaves both solver and optimizer unchanged. MAdam preconditions the reconciled direction by the preference-conditioned curvature of the scalarized objective; on this whitened input, Adam's second moment collapses to identity, so the realized update is governed by the preference-conditioned metric. Across multi-task learning, Pareto-front recovery, physics-informed neural networks, and medical imaging, MAdam consistently improves over Adam for every solver family.

Diffusion-weighted imaging (DWI) is used for whole-body cancer screening, but it typically requires a long acquisition time. When the scan time is reduced, the image quality often suffers, leading to increased noise in the scans. Magnitude reconstruction in DWI introduces signal-dependent Rician noise, which makes denoising more challenging for conventional convolution-based methods. To address this limitation, we propose a noise-aware attention-driven denoising framework that integrates hierarchical Swin Transformer window attention with transformer-based multi-dimensional gated refinement for DWI restoration. The model incorporates explicit noise-level conditioning and residual reconstruction to enable adaptive suppression of heteroscedastic noise across a wide range of corruption levels. Experimental evaluation on corrupted DWI scans demonstrates strong restoration performance. Our model achieves a mean PSNR of 33.69~dB and SSIM of 0.8539 across noise levels from 1\% to 15\%, while maintaining stable behavior under severe noise conditions. These results indicate that attention-guided contextual modeling combined with channel-adaptive refinement provides a robust and generalizable solution for DWI denoising.

Accurate execution of preoperative plans in corrective femoral osteotomies remains challenging. Current techniques are limited by variable accuracy, invasiveness, and radiation exposure, with free-hand methods and patient-specific instrumentation (PSI) often requiring >30 and >6 fluoroscopic images, respectively. We present an integrated, electromagnetic tracking (EMT)-based navigation system for femoral osteotomies that minimizes dissection and intraoperative fluoroscopy. The system couples CT-based preoperative planning with one-time intraoperative C-arm calibration and accurate X-ray-to-CT registration from two fluoroscopic images acquired at initialization. This enables real-time, fluoroscopy-free EMT navigation of the saw blade and bone fragments relative to the preoperative plan, and is compatible with uniplanar and biplanar osteotomies. In a feasibility study using 18 synthetic femora, EMT guidance significantly outperformed free-hand execution in total angular error ($(3.05 \pm 0.75)^\circ$ vs.\ $(6.32 \pm 2.36)^\circ$, $p=0.031$), assuming the same minimal surgical exposure for both. No EMT-guided trials exceeded the >5° clinical threshold, whereas free-hand produced 4 outliers of 6 trials. The system achieved statistical equivalence ($\pm 2^\circ$, $\pm 2,\text{mm}$) to PSI for total angular ($p \le 0.02$) and total translational ($p=0.048$) errors, with no significant differences in user questionnaire scores. By transferring preoperative plans using only two fluoroscopic images while matching PSI accuracy without additional surgical exposure, the proposed system motivates subsequent cadaveric and clinical validation.

Multimodal agents in robotics, AR, and autonomous driving must reason about places and layouts from continuous egocentric streams, often using evidence outside the current view. Existing benchmarks either evaluate offline over full videos or target events rather than spatial structure. We introduce OVO-S-Bench, a fully human-annotated benchmark for streaming spatial intelligence, comprising 1,680 questions over 348 source videos. Annotation involves 12 trained annotators, each also serving as a blind cross-reviewer, across roughly 804 person-hours of multi-round quality assurance. Each question carries a query timestamp and an evidence interval, and at evaluation, the model sees only the prefix preceding the query. Questions span four levels of increasing abstraction: instantaneous egocentric perception, spatiotemporal context tracking, spatial simulation and reasoning, and allocentric mapping. Across 38 proprietary and open-source MLLMs, Gemini-3.1-Pro trails human experts by 27 points, 59.2 vs. 86.6, with allocentric mapping as the dominant bottleneck. Notably, streaming and spatially fine-tuned MLLMs underperform their own backbones. We further find that chain-of-thought reasoning amplifies spatial errors when ungrounded in the stream. By exposing these limitations, OVO-S-Bench establishes a demanding testbed for next-generation streaming spatial MLLMs.

Self-supervised learning has enabled large-scale pre-training on 2D natural images, producing general-purpose visual representations that transfer effectively across tasks. However, many medical imaging modalities, such as CT scans, are inherently three-dimensional and differ fundamentally from natural images in both structure and semantics. Volumetric modalities capture spatial continuity, organ anatomy, and intensity-based tissue properties (e.g., Hounsfield Units), which are not adequately modeled by 2D pre-training. To bridge this gap, we introduce CoralBay, a self-distillation framework that extends DINO by using a hierarchical 3D Swin backbone and applying self-distillation to concatenated multi-scale features, enabling data-efficient self-supervised learning of rich spatial representations that encode both global semantics and fine-grained local structure. As a result, CoralBay transfers effectively to a wide range of downstream radiological tasks, demonstrating strong and consistent performance across diverse anatomical targets. In addition, we contribute to the open-source \eva framework by introducing a public, reproducible 3D radiology leaderboard that unifies multiple datasets and establishes a standardized benchmark for evaluating volumetric representation learning methods.

As foundation models scale toward fusing more heterogeneous visual streams, understanding how diverse encoders interact under joint training becomes a prerequisite for principled design. Yet large vision-language models (LVLMs) currently lack the tools to do so, and parameter-efficient encoder configurations remain hard to identify before training. To re-examine encoder roles under joint training, on the 16-benchmark Cambrian-1 suite we retrain and evaluate all 31 non-empty subsets of five common vision encoders under a unified pipeline (~20k GPU-hours total), and report three findings. First, retraining each subset from scratch reveals encoder rankings that differ from those obtained by masking encoders on a fixed checkpoint, including which encoder ranks first overall. Second, we decompose each encoder's contribution into two axes, Capacity, the score an encoder reaches on its own, and Necessity, the drop when it is removed from the full pool. The two axes are not interchangeable. Pairing the two highest-Capacity encoders is suboptimal, while pairing a high-Capacity anchor with an adaptive complement matches the full five-encoder model. Adding further encoders beyond this pair yields only marginal gains. Third, at fixed parameter count, per-encoder pre-projector effective rank explains the residual score variation. The strongest pairs combine an anchor whose rank survives joint training with a complement whose rank expands under it, suggesting that higher-rank, less-collapsed projector inputs correspond to a more favorable optimization regime at the encoder-projector interface. Together, the Capacity-Necessity decomposition and the pre-projector rank analysis, along with comprehensive evaluation through retraining, expose a methodological gap in multi-encoder LVLM design, and offer concrete primitives for closing it.

3D representations are fundamental to scene rendering, understanding, and interaction. Recent approaches, such as 3D Gaussian Splatting and Neural Radiance Fields, achieve impressive photorealistic novel-view synthesis, but lack the ability to easily decompose scene elements into a few primitives, requiring additional segmentation or grouping for object-level manipulation. We present MLP-Splatting, a method that enables scene decomposition via a few expressive light-field primitives while providing photorealistic novel-view synthesis. MLP-Splatting models each primitive as an independent compact MLP with localized spatial support that predicts radiance and opacity. In contrast to low-level Gaussian primitives or a single global radiance field, our neural primitives provide greater expressive capacity while remaining spatially localized. Rendering is performed through efficient sparse volumetric compositing over ray-primitive interactions. Our primitives are supervised using RGB supervision alone, which yields primitives that represent local scene regions often corresponding to objects or object parts, enabling interactive object-level editing without segmentation masks by selecting a handful of primitives. Our method, augmented with optional semantic feature distillation, enables open-vocabulary scene interaction and open-set instant segmentation. Compared to state-of-the-art methods, we achieve substantially lower memory usage (1/15$\times$) and faster rendering (3$\times$), as we show in our experiments compared to semantic 3DGS methods. Project Page: https://shinjeongkim.com/mlp-splatting

Autonomous systems require robust Multi-Object Tracking and Segmentation (MOTS) to operate reliably in dynamic environments, ensuring consistent object identities and precise mask-level delineation. Foundation models such as SAM2 have shown strong zero-shot generalization for segmentation, but their direct application to MOTS is limited by unreliable track association and false-positive propagation. This work introduces Seg2Track++, a framework that integrates instance segmentation with SAM2 and a novel track management module to perform zero-shot MOTS with enhanced temporal consistency. Tracks are associated using Mask Centroid Distance (MCD) and Confidence-Aware Cost Modulation (CCM), while Probabilistic Track Validation (PTV) employs a Bernoulli filter to validate track existence and suppress ghost tracks. Experimental results on KITTI MOTS demonstrate improved identity preservation, reduced false-positive propagation, and robust track management without fine-tuning.

We present DyaPlex, a streaming, full-duplex speech-and-motion model designed for dyadic interaction. To capture the continuous and reciprocal nature of human communication, this full-duplex capability empowers the agent to simultaneously perceive and generate both speech and physical motion in a streaming fashion. At its core, our method leverages the strong priors of a foundational full-duplex speech model and integrates a novel motion pathway, thereby achieving fully synchronized multi-modal interaction. Specifically, we design a dual-tower Transformer architecture that preserves the zero-shot conversational reasoning of a frozen base speech model while constructing a deeply coupled, streaming motion pathway. By introducing a unified dyadic token interleaving mechanism and guiding cross-attention via a time-aligned speech-motion RoPE, our model effectively aligns autoregressive motions with rich latent speech features. Trained on the 4,000-hour Seamless Interaction dataset, our model effectively captures cross-speaker dependencies and establishes new state-of-the-art performance across both monadic and dyadic human interaction benchmarks.

Visual instruction tuning effectively adapts a pre-trained Large Language Model (LLM) to process image information alongside text. Yet, it remains unclear how visual features are embedded into the layer-wise hierarchy of abstractions of the LLM backbone. Across a diverse set of vision-language architectures, we show that instruction tuning primarily serves as a bridge, embedding visual features directly into the intermediate semantic layers of the LLM, bypassing the early layers devoted to unimodal processing. With probing analyses and causal interventions, we show that these intermediate layers are the semantic core of vision-language processing and play a critical role in the performance on a broad set of multimodal benchmarks. In addition, by comparing the geometry of semantically equivalent visual and textual representations, we find that fine-tuning extends and strengthens the existing abstraction phase, aligning visual features with pre-existing textual ones. Finally, we confirm the functional role of this localized alignment by restricting fine-tuning to intermediate layers alone: this strategy preserves the performance of full fine-tuning on vision-centric benchmarks while reducing training time. Our results suggest that multimodal integration is a localized phenomenon driven by the repurposing of the internal abstraction engine of the LLM.

Recent world action models leverage video foundation models by aligning broad visual-dynamics priors with executable robot actions. We revisit this alignment from a distributional perspective. Existing formulations typically narrow the aligned prior into an observation-conditioned policy distribution over future actions. In contrast, we keep the distribution broader by modeling the joint space of interaction videos and executable hand trajectories under multiple conditioning regimes. We propose Donk, a unified video-action denoising model for dexterous hands. With language, an initial image, and the initial hand state, Donk samples future videos and bimanual MANO trajectories as an action policy. Without the image condition, the same denoising architecture samples paired video-action rollouts from a text-conditioned distribution, turning the aligned video prior into a data engine. Across action, video, and text-only generation evaluations, Donk improves dexterous trajectory accuracy, preserves strong video fidelity, and produces smooth text-conditioned action rollouts under the same unified training recipe.

Parameter-efficient fine-tuning (PEFT) and probing enable adaptation of foundation models using only a small number of trainable parameters, making it attractive for video understanding where annotation and computation are expensive. However, video PEFT has focused on adapting image-pretrained models, while standard PEFT methods can also be applied to video representations. These settings are rarely compared and both confine temporal reasoning to a single component of the model, leaving open how temporal context should be distributed across backbone, PEFT and probe. In this work we provide a systematic study of model adaptation strategies for video understanding. We evaluate methods across appearance-focused, motion-focused and spatially dense settings, with a particular focus on scenarios with limited data where parameter-efficiency is most beneficial. Our results provide new insights into PEFT and probing across settings and demonstrate the importance of temporal context allocation for effective video adaptation

Temperature-emissivity-texture (TeX) decomposition seeks to recover object heat state, material spectral response, and visible-like geometric texture from long-wave infrared hyperspectral imaging (LWIR HSI). Existing TeX pipelines are mainly scene-specific inverse solvers, and the lack of paired LWIR HSI-TeX supervision has limited learning-based decomposition. To address this gap, we introduce TeX-1500, a large-scale paired LWIR HSI-TeX dataset and benchmark for supervised HSI-to-TeX decomposition. TeX-1500 contains 1,522 calibrated real-scene pairs from DARPA Invisible Headlights (DARPA IH) pushbroom imagery and our FTIR acquisitions, covering five locations, four seasons, diverse acquisition times, heterogeneous wavelength layouts, and two sensor families. Each sample stores a calibrated valid-band radiance cube, calibrated wavelength positions, and aligned temperature, emissivity, and texture supervision constructed through a consistent restoration and TeX-construction protocol. We further provide TeX-UNet, a simple wavelength-aware baseline that maps calibrated HSI bands and wavelength positions to TeX fields. Experiments on the held-out DARPA IH pushbroom scenes and zero-/few-shot transfer to FTIR scenes show that TeX-1500 provides usable paired supervision and a measurable benchmark for data-driven physical-property-centered thermal perception.

Objective: Consumer face camera remote photoplethysmography (rPPG) enables passive cardiovascular monitoring, but whether single-cycle waveform morphology encoding arterial stiffness biomarkers is recoverable from this measurement has not been characterised. Methods: We evaluated 16 architectures spanning six families on 153 subjects across three datasets, introducing cross-subject Pearson r to distinguish subject-specific recovery from template collapse. Results: No architecture recovered subject-specific morphology (cross-subject r range 0.773--0.9999; ground-truth ceiling 0.601). Supervised Contrastive (SupCon) converged to log N = 4.844, constituting the strongest available empirical evidence that no discriminative morphological structure is extractable from single-cycle rPPG by the encoder families tested. The VAE decoder restores population-level harmonic content absent from the rPPG input (H2/H1: 0.310 output vs. 0.275 input), generalising zero-shot to UBFC (r = +0.708); a directional hallucination gap (p = 0.150) suggests partial signal reading. Anti-collapse objectives fail when input carries no discriminative structure. Significance: Consumer cameras cannot encode individual arterial morphology; cross-subject r is a necessary collapse diagnostic for waveform reconstruction benchmarks.

Vision-language models map visual features into a shared embedding space through learned projection layers, yet it remains unclear how these transformations alter the structure of visual information. This study examines changes in representation through spatial-frequency accessibility, measured by the linear recoverability of band-limited Fourier energy from model representations. To isolate effects beyond dimensionality reduction, we introduce Residual Spectral Loss (RSL), which evaluates changes relative to a dimension-matched random projection baseline. To reduce confounding effects from optimization, the analysis uses pretrained models with all parameters frozen. The experimental results show consistent frequency-dependent changes in accessibility across CLIP and DINOv2 on ImageNet and MS-COCO datasets. Spectral accessibility follows a non-monotonic trajectory across depth, peaking at intermediate layers before decreasing toward the output representation. The final transformation differs across architectures: CLIP's learned projection is spectrally neutral, with changes explained by compression, whereas DINOv2's [CLS] pooling induces a structured loss across the spectrum. These findings identify intermediate layers and pooling mechanisms as primary drivers of spectral transformation in modern vision encoders.

Multimodal Large Language Models integrate visual perception into language reasoning, introducing a continuous attack surface susceptible to adversarial attacks. Prior work on MLLM robustness has focused largely on English-centric tasks, leaving multilingual behaviour unexplored. We address this gap through a systematic study of adversarial robustness and multimodal safety across 12 diverse languages, evaluating open-source MLLMs that acquire multilingual capability through instruction tuning. Gradient-based attacks reveal a transferable multilingual vulnerability: adversarial images optimized in one language continue to induce failure in others, demonstrating strong cross-lingual transferability. Multilingual safety further varies with how effectively a model retrieves or interprets harmful instructions. When harmful intent is issued through text, languages with stronger linguistic grounding more often elicit misuse-enabling responses, while weaker languages produce fewer unsafe outputs. When embedded in the image as typographic content, English scripts are reliably recognised and followed, whereas non-English scripts are rarely parsed by the vision encoder. Lower-resource languages may therefore appear safer, but this is an artefact of comprehension and visual-grounding failures rather than genuine alignment, a phenomenon we term safety-by-failure. In contrast, MLLMs that build multilingual capability throughout their training stages rather than only at instruction tuning, such as Qwen3-VL, exhibit genuine cross-lingual safety, maintaining active refusal across languages rather than masking comprehension failure. Shallow multilingual adaptation, such as fine-tuning on translated instruction data, may produce surface-level understanding that creates illusory safety in low-resource languages; deeper integration across training stages leads to genuine multilingual safety alignment.

Low-Rank Adaptation (LoRA) successfully enables personalization in text-to-image generation by adapting pre-trained diffusion models to specific visual concepts and styles. However, extending such models to multi-concept customization remains challenging. Naively combining multiple LoRA weights or their outputs often leads to interference among concepts, resulting in degraded visual quality and reduced fidelity to the reference images of individual concepts. This paper proposes a simple yet effective approach for multi-concept customization by optimally combining the outputs of multiple LoRA modules. We leverage the relative importance of each concept during generation, as inferred from its corresponding prompt tokens and introduce two methods, W-Switch and W-Composite, that employ a prompt-aware importance weighting strategy in which each LoRA is weighted according to the semantic influence of its trigger words in the target prompt. In addition, we extend existing quantitative evaluation metrics by proposing a new image-based similarity evaluation framework that assesses image fidelity and identity preservation through comparisons between real-world reference images and automatically segmented concept regions from generated images. We evaluate our approach on the ComposLoRA testbed and demonstrate consistent improvements over existing state-of-the-art methods in terms of visual quality, identity preservation and compositionality. Qualitative evaluations, including a Large Language Model (LLM) based assessment and a user study, further validate the effectiveness of the proposed methods and align with the newly introduced quantitative image-based metrics. Our code is available at https://github.com/GeorgeTsoumplekas/Prompt-Aware-Multi-LoRA-Composition.

Eye tracking is essential for smart glasses, as it provides insight into user attention for ambient intelligence applications. However, most existing eye-tracking systems rely on active infrared (IR) illumination, creating practical barriers to all-day outdoor use due to power consumption. In this paper, we investigate whether passive IR cameras alone, without any active IR light source, can enable reliable pupil detection in unconstrained outdoor environments, where ambient sunlight serves as the sole illumination source. To support this investigation, we introduce AmbientEye, a large-scale dataset of 2,606,225 eye images collected from 35 participants from 19 countries. It is captured outdoors under natural sunlight with two off-axis camera configurations and two sun-orientation conditions. We provide high-quality pupil annotation through SAM2 automatic segmentation, followed by refinement by human annotators. We benchmark a state-of-the-art pupil segmentation algorithm on our dataset and compare its performance with that on existing datasets under controlled IR illumination. Results reveal a substantial drop in pupil segmentation performance from 0.928 on controlled IR datasets to 0.767 on AmbientEye. This performance gap highlights the challenge of the ambient-light setting. This positions AmbientEye as a first benchmark for an unexplored and highly practical eye-tracking scenario.

Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware. The YOLO family has become widely deployed for this reason, yet most YOLO detectors still rely on non-maximum suppression at inference, carry heavy detection heads due to Distribution Focal Loss, require long training schedules, and can leave the smallest objects without positive label assignments. We present Ultralytics YOLO26, a unified real-time vision model family that addresses these limitations through coordinated architecture and training advances. YOLO26 uses a dual-head design for native NMS-free end-to-end inference and removes DFL entirely, yielding a lighter head with unconstrained regression range. Its training pipeline combines MuSGD, a hybrid Muon-SGD optimizer adapted from large language model training; Progressive Loss, which shifts supervision toward the inference-time head; and STAL, a label assignment strategy that guarantees positive coverage for small objects. Beyond detection, YOLO26 introduces task-specific head and loss designs for instance segmentation, pose estimation, and oriented detection, producing consistent gains across tasks and scales. The family spans five scales (n/s/m/l/x) and supports detection, instance segmentation, pose estimation, classification, and oriented detection in a single pipeline, with an open-vocabulary extension, YOLOE-26, for text-, visual-, and prompt-free inference. Across all scales, YOLO26 achieves 40.9-57.5 mAP on COCO at 1.7-11.8 ms T4 TensorRT latency, advancing the accuracy-latency Pareto front over prior real-time detectors, while YOLOE-26x reaches 40.6 AP on LVIS minival under text prompting. Code and models are available at https://github.com/ultralytics/ultralytics.

Text-to-image models rely on text prompts as their primary interface to human intent. Prompts are encoded by a text encoder into embeddings that condition the image generation process. Beyond individual token meanings, text embeddings encode contextual information across the full prompt, such as compositionality and attribute binding. However, whether image models actually exploit this richer information remains underexplored. Here, we address the question: Which aspects of text representation are essential for image generation? We show that text-to-image diffusion transformer-based models commonly rely only on two relatively straightforward aspects of text representations: (i) the merging of adjacent tokens into a word representation, for words spanning multiple tokens, and (ii) word order, which is imprinted by the positional embedding of the text-encoder. To show this, we construct a new text embedding that encodes only individual word meanings and order but lacks any contextual information about the full prompt. We find that this bag of position-tagged words representation is sufficient to successfully guide image generation, achieving visual quality and text fidelity that are on par with full text embedding-guided generation. This demonstrates that, contrary to common belief, text-to-image models often do not use the rich information encoded in the text embedding beyond individual word meanings and word order. Instead, the decoding of complex linguistic structures is performed by the image model itself. Project webpage: https://nsping13.github.io/contextless-TTI/

Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e.g., CLIP) substantially expands the attack surface, making these models vulnerable to visual adversarial perturbations. Prior defenses typically preserve compatibility with pretrained MLLMs by enforcing strict alignment to CLIP's original embedding space during adversarial fine-tuning; while practical, this constraint fundamentally limits achievable robustness. We present a systematic investigation of adversarial robustness in MLLMs. We first introduce a diagnostic CLIP-alignment protocol that predicts, prior to full MLLM training, which robust vision encoders will transfer effectively to the multimodal setting, revealing that large-scale multimodal adversarial pretraining, rather than unimodal scale alone, is the critical factor for strong robustness transfer. Integrating such encoders into MLLMs via end-to-end multimodal training yields average gains of 28 CIDEr points on captioning and 11.7% VQA accuracy under strong adversarial attacks compared to constrained plug-and-play baselines. We further show that adversarial training applied directly to a standard non-robust MLLM degrades both clean and adversarial performance, establishing robust visual representations as a strict prerequisite, while end-to-end adversarial training from a robust backbone delivers additional gains of 1.9 CIDEr points and 4.3% VQA accuracy. Beyond training-time defenses, lightweight test-time visual stochastic transformations serve as an effective black-box defense for non-robust MLLMs, elevating adversarial performance from near-zero to levels comparable with robust models. Finally, we show that our robust models substantially reduce toxic generation under white-box visual jailbreak attacks. Code and pretrained weights will be released publicly.

To enable meaningful human-robot interaction (HRI), a robot must continuously assess engagement by consistently tracking users over time. State-of-the-art computer vision models, however, are heavily optimized for surveillance or autonomous driving. A social robot faces distinct egocentric challenges, such as humans bouncing, obstructing each other, or leaving the frame. Frequent identity switches (IDSW) cause the robot to lose its footing mid-conversation. To address this, we introduce a novel, custom-annotated egocentric dataset collected via the Furhat robot to capture complex social dynamics. We present a systematic evaluation isolating detection errors from tracking logic, comparing face versus body tracking, and assessing the impact of extended spatial memory and appearance re-identification (ReID). Results indicate that increasing spatial memory mitigates prolonged occlusions but fails on complex dynamic events. Integrating ReID resolves complex switches but exhibits opposing effects: it substantially improves body tracking stability, yet causes facial IDSW to spike due to profile angle sensitivity. Ultimately, our optimized pipeline reduces IDSW by 49\%, mitigating interaction breakdowns. Because standard benchmarks lack dense, close-quarter occlusions, this work highlights the critical need for natively captured social dynamics to truly validate HRI perception models.

Medical Vision-Language Models (VLMs) are typically evaluated on English radiology visual question answering benchmarks, leaving their robustness under non-English clinical language largely unexplored. We introduce IndoRad-VQA, an Indonesian adaptation of VQA-RAD, to assess whether medical VLMs retain radiology reasoning ability when questions are asked in Bahasa Indonesia. Radiology question-answer pairs are translated into Indonesian with self-evaluation-based quality control to preserve clinical meaning, terminology consistency, and answer equivalence. We evaluate general-purpose, Southeast Asian multilingual, and medical-specific VLMs under English and Indonesian prompting settings. Beyond accuracy, we quantify the language robustness gap between English and Indonesian inputs. We also conduct an error analysis to identify failure modes of question answering, such as yes/no flips, laterality errors, and output-language mismatches. Our findings show that strong performance on English medical VQA benchmarks does not necessarily translate to robust behavior in Indonesian clinical contexts. We observe a performance gap of 8 to 25 percent between the English and Indonesian settings, depending on the evaluation metric. These results highlight the need for more inclusive multilingual evaluation of medical multimodal foundation models. The dataset is available at https://huggingface.co/datasets/Lab-IS/IndoRad-VQA.

Methane is a potent greenhouse gas, and detecting leaks early via hyperspectral satellite imagery can help climate change mitigation efforts. Meanwhile, many existing hyperspectral missions only capture areas manually targeted by operators, thus missing potential events of interest. To overcome slow downlink rates cost-effectively, onboard detection is a viable solution. However, traditional methane detection methods are too computationally demanding for resource-limited onboard hardware. This work accelerates methane detection by focusing on efficient, low-power algorithms. In particular, we test fast target detection ACE and CEM methods that have not been previously used for methane detection and propose Mag1c-SAS -- a significantly faster variant of the current state-of-the-art Mag1c algorithm. To explore their detection potential, we integrate them with a machine learning model based on U-Net and LinkNet. We evaluate our methods on the STARCOP dataset and a novel EMIT-MSeg dataset, which we introduce and open-source alongside a high-quality annotation strategy. The proposed Mag1c-SAS approach proves highly effective by operating ~80x faster than the original Mag1c approach, providing a visually similar, but noisier result. When additionally paired with the lightweight LinkNet approach, it effectively reduces noise, achieving AUPRC score improvements of over 30 pp on EMIT-MSeg compared to the baseline Mag1c approach, and an F1 score on STARCOP ~4 pp higher. We evaluate two novel band selection strategies and confirm the system's onboard viability through hardware profiling, demonstrating marginal power consumption and efficient CPU/RAM utilization. We release the final system in a user-friendly and lightweight PyPI library at: https://pypi.org/project/onboard-methane-detection/, alongside all experimental code, models, and data at: https://github.com/zaitra/methane-filters-benchmark.

Recent deep unfolding networks (DUNs) have advanced Compressive Sensing (CS) by effectively integrating iterative optimization with deep learning architectures. However, most CS approaches predominantly confine their inference to a single solution space, neglecting the inherent ill-posedness of CS problems that intrinsically permits multiple plausible candidate hypotheses. In this paper, a novel Multi-Hypothesis Collaborative Deep Unfolding CS Network (MHC-DUN) is proposed, which explicitly models and leverages multiple hypotheses by jointly optimizing across diverse solution spaces. Specifically, following the Proximal Gradient Descent algorithm, MHC-DUN jointly performs gradient descent and proximal mapping within this multi-hypothesis paradigm. i) For gradient descent, a well-designed AlphaNet is introduced to dynamically predict spatially varying step sizes for all hypotheses, enabling collaborative gradient updates across multiple solutions. ii) For proximal operator, a sophisticated multi-hypothesis collaborative proximal mapping module is designed, which leverages both intra-hypothesis and inter-hypothesis correlation priors to jointly refine multiple solutions. To enable end-to-end training, a novel composite loss function is designed, which balances measurement fidelity, hypothesis diversity, and reconstruction accuracy, encouraging exploration of complementary solutions while maintaining reconstruction fidelity. Experimental results reveal that the proposed CS method outperforms existing CS networks.

This paper constructs the first benchmark on semi-supervised multi-modal crowd counting. To lay the foundation for this unexplored task, we first formulate the semi-supervised multi-modal setting and a standardized protocol that specifies the labeled-unlabeled data partition across different labeled ratios. Next, to establish solid reference points, we carefully tailor a diverse set of representative baselines, including existing fully supervised multi-modal methods and semi-supervised single-modal methods. Then, we carefully evaluate their performance under our proposed benchmark. Codes and the data partition will be released on https://github.com/HenryCilence/Semi-supervised-Multimodal-Crowd-Counting.

Understanding short online videos involves more than identifying visible objects and actions; video makers often include an underlying message or purpose in the clip. We introduce VidMsg, a benchmark for evaluating implicit message understanding in short, internet-native video clips. VidMsg contains 400 YouTube-derived clips across 9 practical topic areas and 52 fine-grained target messages, covering domains such as career and finance, education, health and well-being, culture, safety, sustainability, and lifestyle. VidMsg is constructed through a message-first pipeline: an LLM first translates target messages into indirect search scenarios, which are used to retrieve candidate clips. Human annotators then retain clips that convey the intended message without being overly explicit. VidMsg is designed primarily for bidirectional message-clip retrieval for scalable applications such as video search and recommendation, where systems must capture holistic video understanding. In addition to retrieval, VidMsg includes a diagnostic multiple-choice QA benchmark, where models select the intended message of a clip from semantically related alternatives. Experiments with contemporary video-language and retrieval models show that strong models often fail on VidMsg, because the task requires pragmatic inference, integration of contextual cues, and discrimination among semantically close messages. We also introduce VidVec-Msg, a baseline method that improves message-oriented retrieval while leaving substantial headroom for future work.

Vision-language models (VLMs) have been explored for visual programming, where they generate code to solve visual tasks. However, most prior work focuses on visual programming for productivity; it remains unclear how well current VLMs perform on education-oriented visual programming and what factors limit their performance. To bridge this gap, we introduce TurtleAI, a benchmark containing 823 tasks curated based on real-world visual programming tasks in the Turtle Graphics domain. Solving these tasks requires models to perceive geometric patterns, reason about spatial relationships, and synthesize Python code that faithfully reproduces geometric patterns. We evaluate 20+ VLMs, including GPT-5, GPT-4o, and Qwen2-VL-72B, and find that they struggle significantly, with most achieving success rates below 30%. To address these limitations, we propose a data generation technique that requires only a small set of seed samples. Fine-tuning Qwen2-VL-72B on the resulting synthetic data yields an improvement of about 20% on real-world tasks. Our failure analysis reveals that GPT-4o struggles with spatial reasoning and precise visual replication, whereas fine-tuning primarily improves the alignment between visual reasoning and code implementation.

Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, where only a single labeled exemplar is available for each novel action. A key challenge is learning representations that capture the hierarchical and compositional structure of human motion while aligning effectively with high-level action semantics under extreme data scarcity. Existing approaches, largely based on Euclidean embeddings and low-level motion cues, struggle to model the tree-like organization of skeleton data, limiting cross-modal alignment and generalization to unseen action categories. We propose SkelHCC, a unified skeleton hyperbolic CLIP-driven cache adaptation framework for one-shot skeleton-based action recognition. SkelHCC introduces an Explicitly Hierarchical Hyperbolic CLIP (EH-HCLIP) module that embeds skeleton sequences and action language into a shared hyperbolic space. By leveraging the negative curvature and exponential volume growth of hyperbolic geometry, EH-HCLIP naturally encodes the joint-part-body hierarchy of human anatomy and yields structurally consistent cross-modal representations. To support efficient one-shot adaptation, SkelHCC further integrates a training-free LLM-guided Multi-granularity Voting Cache (LMV-Cache) for context-aware inference. Experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD demonstrate that SkelHCC consistently outperforms state-of-the-art methods.

World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models can generate concrete visual rollouts of possible futures, while MLLMs can reason abstractly over questions, goals, and rules. However, generated rollouts are stochastic and may be visually plausible but task-incorrect, making it necessary to determine when visual simulation is useful, whether a rollout is credible, and how it should influence the final answer. We formulate this problem as controlled concrete reasoning, where a model learns to invoke, verify, and integrate visual future simulation alongside abstract reasoning. To study this setting, we construct two human-verified benchmarks, VRQABench for controllable spatial lookahead and OpenWorldQA for open-domain physical prediction, and propose Privileged-Future On-Policy Self-Distillation (PF-OPSD). During training, PF-OPSD uses ground-truth future videos and answers only as teacher-side privileged context to evaluate on-policy concrete-reasoning trajectories, while the deployable student never observes true futures at test time. Experimental results show that PF-OPSD outperforms baseline by 10.6% and 10.9% on VRQABench and OpenWorldQA, respectively, while increasing robustness to noisy or conflicting rollouts. Our code and dataset are available at https://github.com/yczhou001/PF-OPSD.

Unstructured scenes present unique challenges for autonomous driving, as irregular obstacles and sparse scene layouts undermine the effectiveness of traditional perception methods such as 3D object detection. 3D semantic occupancy prediction has emerged as a prominent focus due to its ability to provide dense spatial representations by assigning semantic labels to individual voxels in 3D space. However, directly applying 3D semantic occupancy prediction to unstructured scenes remains challenging because scene sparsity hinders effective cross-modal fusion and the more severe long-tail distribution in these scenarios further degrades prediction performance. To validate the effectiveness of our approach, we construct a dedicated dataset of unstructured scenes collected from open-pit mines. Based on this, we propose UnsOcc, a multi-modal 3D semantic occupancy prediction framework that improves robustness in unstructured environments. At its core, we introduce a rendering-based fusion module, RenderFusion, which enhances cross-modal feature alignment through bidirectional rendering supervision. Furthermore, we propose GSRefinement, a detail-aware auxiliary supervision method based on Gaussian Splatting that projects sparse 3D occupancy predictions into dense 2D semantic segmentation maps, enabling effective supervision for long-tail categories. Extensive experiments on both the open-pit mine dataset and the nuScenes dataset demonstrate that our method significantly outperforms existing state-of-the-art approaches.

Latent diffusion models leverage visual tokenizers to compress images into latent spaces for efficient generative modeling. However, better reconstruction quality of a tokenizer does not necessarily translate into better generation quality, suggesting that latent representations should be evaluated not only by fidelity but also by their diffusability. Recent studies have proposed diverse explanations for diffusion-friendly latent spaces, including semantic separability, affine equivariance, distribution uniformity, spatial structure, spectral smoothness, and manifold continuity. Yet these properties are often validated on a limited set of tokenizers, leaving it unclear which factors are most predictive of downstream generation quality and whether such conclusions hold beyond the specific settings in which they are introduced. In this work, we conduct a systematic study of latent diffusability by training a large collection of tokenizers with diverse regularization strategies, architectures, and latent configurations, and evaluating them with multiple downstream diffusion backbones. Our analysis identifies several latent properties that consistently correlate with generation quality and exhibit strong generalization across experimental settings. Beyond existing metrics, we introduce Velocity Irreducible Variance (VIV), a measure of velocity ambiguity induced by trajectory crossings. Extensive experiments show that VIV is one of the most stable predictors of generation quality.

Wide-baseline matching (WBM) requires integrating geometric understanding, viewpoint changes, fine-grained perception, and occlusion reasoning, making it a challenging testbed for spatial reasoning in multimodal large language models (MLLMs) deployed in physical environments. However, current MLLMs lack systematic evaluation and training frameworks for these capabilities. We introduce ReasonMatch-Bench, a benchmark stratified by viewpoint displacement and matching granularity across indoor, outdoor, and object-centric scenarios, and show that current MLLMs still struggle with fine-grained wide-baseline correspondence: on a difficult 90-sample subset, human annotators achieve 84.0 F1, while the best existing baseline reaches 37.2. To bridge this gap, we build a scalable data-generation pipeline that automatically extracts wide-baseline view pairs from large-scale video-3D corpora, including RGB-D videos and SfM reconstructions, yielding diverse and verifiable supervision. We further propose Dynamic Correspondence Reinforcement Learning (DCRL), which combines Image-Level Viewpoint Progression and Point-Level Correspondence Curriculum to improve WBM training through verifiable rewards without explicit CoT supervision. Extensive experiments show that DCRL substantially improves ReasonMatch-Bench and transfers to related spatial benchmarks, while maintaining general visual understanding performance with modest gains on several benchmarks.

Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference. While visual token pruning offers a promising solution, existing methods predominantly rely on initial attention scores. This single-metric paradigm presents a critical flaw: high attention scores inherently collapse onto semantically similar regions, thereby severely reducing feature diversity and discarding vital contextual details. To address this, we introduce Structure-to-Semantics (STS), a novel two-stage visual token pruning framework that explicitly decouples the pruning process. The first stage employs a repulsion-based sampling mechanism to maximize spatial and structural diversity. The second stage leverages instruction-aware cross-attention to precisely filter out prompt-irrelevant tokens. This two-stage synergy constitutes the core of STS, first ensuring geometric coverage and then refining the retained tokens according to semantic relevance. Extensive evaluations demonstrate that STS mitigates the redundancy caused by attention-based selection, improving both structural diversity and fine-grained task alignment of the preserved visual tokens.

Post-processing is a critical stage in LiDAR-based 3D object detection, where dense and overlapping proposals must be filtered for compact and reliable perception. This work introduces two learned filtering modules that replace heuristic non-maximum suppression (NMS) by leveraging relations among detections. D2D-Rescore employs transformer-based detection-to-detection (D2D) attention, while GossipNet3D adapts the 2D GossipNet concept to 3D through localized message passing in bird's-eye view. A metric-aware matching strategy aligned with the nuScenes evaluation protocol ensures consistent training and validation behavior, improving overall detection performance. Both approaches improve mean average precision (mAP), nuScenes detection score (NDS), and true positive quality compared to CircleNMS, particularly for small and infrequent classes, while adding minimal computational overhead. These results demonstrate that learned, detection-level filtering can enhance 3D detector reliability without modifying the base network, offering a principled alternative to heuristic suppression. Code is available at https://github.com/rst-tu-dortmund/learned-3d-nms .

Background: The lateral ventricle choroid plexus (LVCP) is gaining recognition as a key imaging biomarker for multiple sclerosis (MS) related to physical disability and neuroinflammation. Yet, manual segmentation of the LVCP is highly tedious, restricting its use in broad clinical trials and longitudinal assessments. This research aims to develop a SwinUNETR-driven pipeline that leverages targeted intra- and peri-ventricular small patch sampling to automatically segment the LVCP in MS from both standalone and multi-modal MRI inputs. Methods: We retrospectively assessed 3T MRI scans across three sets of data stemming from two separate MS-dominant cohorts (Dataset 1: n=177; Dataset 2: n=177; expanded test set: n=388). Our method employed a SwinUNETR architecture trained on 32x32x32 voxel patches, benchmarking it against the 3D UXNET model. The primary metric for evaluation was the Dice Similarity Coefficient (DSC), supplemented by computational demand (GFLOPs) and the 95th percentile Hausdorff Distance (HD95). Results: On the extended test set, the SwinUNETR model secured a mean DSC of 0.868 (95% CI: 0.863-0.872) with MPRAGE and FLAIR combined, showing a statistically significant gain over UXNET (DSC: 0.858 [95% CI: 0.853-0.862], p<0.0001). When restricted to standalone FLAIR inputs, the transformer-based approach sustained a high DSC of 0.863, while the spatial localization of UXNET worsened considerably (HD95: 1.86 vs. 3.00 mm). Importantly, the proposed framework lowered computational load by 99% (91.8 vs. 22,080 GFLOPs). By integrating localized patch sampling with a SwinUNETR architecture, this methodology offers an accurate, robust, and statistically superior alternative to current leading models for LVCP segmentation. Its vast reduction in computational cost makes it ideal for widespread implementation in clinical and research environments.

Existing human attention (saliency) modeling methods persist as highly fragmented across modalities, scenes, and task formulations. Consequently, even with increasing model capacity and data scale, current models predominantly remain scene-dependent and task-specific, failing to practically generalize in real-world applications. To address the fundamental limitations, we present the Attend to Anything Model (AAM), a multi-modal foundation model that unifies attention modeling across various image, video, and audio-visual tasks and scenes. AAM reformulates attention as a cognitive entailment relationship organized in a general-to-specific hierarchy, implemented through language prompts with hierarchical embeddings in hyperbolic space. Furthermore, to unify static image and dynamic video attention, we adopt a fluid-dynamics perspective, formulating video-frame attention as a diffusive temporal evolution governed by the Fokker--Planck equation. Extensive experiments on 16 benchmarks demonstrate that AAM consistently outperforms state-of-the-art methods by an average of 6\% across various scenarios, while achieving approximately a 4$\times$ speedup in video inference. Overall, these results demonstrate that AAM provides a principled foundation for future research on attention and saliency-related tasks. The dataset and code will be available at https://github.com/wz-zhao/Attend-to-Anything.

Spatio-Temporal Video Grounding aims to localize object tubes based on textual queries. While recent methods have achieved remarkable success, they mainly focus on high-quality(HQ) inputs, neglecting the widespread presence of low-quality(LQ) videos in real-world scenarios. Although tuning methods like LoRA can adapt to degraded inputs, they inevitably disrupt pre-trained knowledge. To address this, we propose Null-Space Tuning (NST). This framework exploits the geometric property that adding vectors within the null-space of frozen weights to the layer input does not affect the output. Leveraging this, NST injects learnable residuals into input features that can be selectively invisible to the pre-trained backbone. Specifically, NST combines the Quality-Adaptive Unit and Dual-Space Reparameterization to synthesize these residuals by confining components for HQ inputs to the null-space, while directing restoration components for LQ inputs to the non-null space. As the frozen weights eliminate null-space components, we effectively rectify degraded inputs while preserving pre-trained knowledge for HQ inputs. Extensive experiments show that NST outperforms state-of-the-art methods on our Mixed-Quality benchmark.

Building memory is essential for long-horizon planning in zero-shot embodied navigation. Detector-centric scene graphs often compress observations into sparse nodes, discarding fine-grained visual evidence and accumulating noise, while 3D reconstruction-based methods remain computationally prohibitive. We present EvoMemNav, an efficient, self-evolving, fine-grained memory framework for zero-shot embodied navigation. EvoMemNav constructs a Visual-Semantic Memory Graph (VSMGraph) that keeps raw views as first-class memory and organizes them with lightweight semantic cues and topological relations into a room-view-object hierarchy, preserving fine-grained details for disambiguation and Stop verification. To scale to growing memory, we introduce a budgeted coarse-to-fine policy: a coarse stage compresses the search space into promising regions, and a fine stage invokes a VLM only for targeted verification and decision. Beyond static memories, EvoMemNav performs reflection-driven write-back after each subtask, updating graph-attached priors that encode accumulated environmental knowledge to refine future decisions without retraining. Experiments on GOAT-Bench and HM3D across object, text-description, and image-goal modalities show consistent gains in SR/SPL, with better multi-instance disambiguation, fewer premature stops, and stronger zero-shot generalization.

Printed circuit board (PCB) defect detection is an essential part of automated optical inspection (AOI); yet it remains challenging in practice because many defects are tiny, low-contrast, and embedded in dense circuit backgrounds. To address these issues, this paper presents a two-phase PCB defect detection framework that combines structure-guided mixed masked pretraining with spatial continuity regularization. In the pretraining stage, we design a sparse convolutional masked pretraining scheme to exploit unlabeled PCB images, where structure-guided mixed masking is used to construct informative masked inputs. The sparse convolutional reconstruction pipeline suppresses invalid responses from masked regions and enables the detector backbone to infer missing PCB structures from visible conductive patterns, thereby learning PCB structural priors. In the fine-tuning stage, the pretrained backbone is transferred to the downstream defect detection task. For the task, a spatial continuity regularization term is introduced during fine-tuning. This term constrains dispersed positive predictions assigned to the same defect instance and promotes more compact localization on elongated defect regions. Experiments on the DsPCBSD+ dataset show that the proposed method achieves 85.5% mAP0.5 and 52.3% mAP0.5:0.95, outperforming several strong baseline detectors. Ablation studies and qualitative results further confirm the effectiveness of the proposed framework for robust PCB defect detection in industrial AOI scenarios.

Existing 3D avatar outfit transfer methods face distinct challenges: approaches that lift 2D edits to 3D often suffer from outfit or identity quality degradation, while those that separately model body and clothing layers are prone to intersection artifacts. We introduce AvatarMix, a compositional paradigm that bypasses these issues by directly composing the head and body from two high-fidelity Gaussian avatars. While this paradigm inherently preserves outfit quality and avoids intersections, it introduces challenges in creating a seamless join and maintaining appearance fidelity after body reshaping. To this end, we propose a two-tier refinement strategy: SeamFix, a localized diffusion module that refines hair and neck to ensure an artifact-free join, and an optional full-body refinement, FullbodyFix, that restores garment appearance when retargeting degrades the clothed body. Both operate on renders from an already 3D-consistent Gaussian avatar, which limits multi-view artifacts compared to 2D-to-3D lifting. To preserve the user's body identity, our mesh-based Gaussian representation enables the adaptation of a robust mesh retargeting technique, precisely reshaping the clothed body to the user's physique and robustly handling diverse body shapes. Extensive experiments demonstrate that our method achieves state-of-the-art results in outfit fidelity and identity preservation, providing a new perspective for realistic 3D outfit personalization. Project page: https://larsph.github.io/avatarmix/

3D Gaussian Splatting (3DGS) has rapidly emerged as a leading representation for real-time novel view synthesis, but recent work shows it is vulnerable to diverse poisoning attacks, including illusory object injection, computation cost amplification, and post hoc model watermarking. Despite this expanding threat surface, existing studies focus mainly on attack success, while defense and detection remain underexplored. From a detection perspective, a key challenge and opportunity arise from the multi-stage nature of the 3DGS reconstruction pipeline, which produces heterogeneous intermediate representations. Forensic signals for detecting poisoning are inherently stage dependent: an attack introduced at one stage may produce signals that emerge only at later stages. This motivates a stage-wise view of detectability that goes beyond single-stage evaluation. We introduce Poison-3DGS, a benchmark for stage-wise characterization of poisoning detection in 3DGS. It exposes stage-specific artifacts, including multi-view images, geometry, training dynamics, and Gaussian parameters, across a diverse set of scenes and attacks. Using it, we conduct a systematic study of detectability across pipeline stages. Our analysis reveals several insights. First, detectability varies significantly across stages, and no single stage consistently dominates across attack types. Second, different attacks exhibit distinct stage-specific forensic signals, so detection effectiveness depends critically on where signals are observed. Third, later-stage signals such as training dynamics and Gaussian parameter statistics provide strong cues not observable at earlier stages. Overall, our work provides a principled benchmark and the first systematic characterization of stage-dependent detectability in 3DGS, offering a foundation for future research on robust and reliable 3DGS systems.

Neural networks suffer from shortcut learning, where learned features generalize well to the training set but not to in-distribution (ID) or out-of-distribution (OOD) test sets. Existing studies are all based on a few standard benchmarks, which are shape-driven. Numerous application domains, however, are texture-driven. In this work, we present shortcut learning analysis for texture-driven domains, and compare it with that of a standard benchmark. We show that texture-driven domains suffer from low-frequency shortcuts. They make the majority of their decisions based on a few low-frequency components (LFCs) with a skewed spectral behavior, despite that their classification information is in higher-frequency, fine-grained details. Pruning LFCs from training and test sets eliminates the shortcut and provides a more balanced spectral behavior, improving the ID accuracy by up to 8%. We show that low-frequency shortcuts make the models highly vulnerable to OOD corruptions, leading up to 70% accuracy drop compared to the ID accuracy. Pruning LFCs significantly improves robustness to low-frequency corruptions, by up to 40%, and introduces a trade-off for high-frequency corruptions; the balanced spectral behavior provides a better generalization performance, whereas the increased dependence on high-frequency features reduces it. OOD accuracy depends on the interaction between these two factors.

Modern action recognition models operate on memory- and compute-intensive dense RGB video volumes and frequently exploit appearance and background shortcuts, for example, predicting actions from objects or scenes instead of characteristic motion. We investigate an efficient alternative input modality that is largely free of such biases by construction: sparse point trajectories. To this end, we develop a simple transformer architecture for 2.5D trajectory-based recognition together with a masked-trajectory pretraining, which we show to substantially improve downstream action recognition accuracy. Despite using only a fraction of the dense RGB input, our method reaches 45% top-1 on Something-Something V2 and 54% on EPIC-Kitchens-100, and surpasses V-JEPA on time-reversal sensitivity. More importantly, we find trajectory features to be complementary to state-of-the-art appearance-based features. Fusing our pretrained model with DINOv2 and V-JEPA 2 improves top-1 accuracy on Something-Something V2 by 8.7 and 1.6 points, respectively. Code: https://github.com/ecker-lab/TrAction

Dynamic 3D Gaussian Splatting (3DGS) methods reconstruct time-varying scenes from synchronized multi-camera video using photometric supervision. When a moving object becomes fully occluded from all training cameras, this supervision vanishes: the Gaussians representing it receive no gradient signal and degrade. Existing approaches to incomplete observations in neural reconstruction rely on learned generative priors that prioritize visual plausibility over physical correctness. We propose $\textbf{PersistGS}$, a method that restores object permanence during occlusion by coupling differentiable rigid body simulation with 3D Gaussian Splatting. Our approach decomposes the scene into per-object Gaussians and collision meshes, estimates friction and velocity from the observed pre-occlusion trajectory via differentiable simulation, and uses the resulting SE(3) trajectory to position object Gaussians throughout the occlusion period. Because the predicted trajectory satisfies the governing equations of rigid body dynamics, it faithfully captures contact events (bounces, friction-based deceleration, direction changes) that kinematic extrapolation cannot model. We introduce a centroid silhouette loss that isolates positional gradients from appearance noise, yielding 40% lower trajectory error than photometric supervision. We evaluate using cameras withheld from training that observe the object during its occlusion. Experiments on synthetic scenes show that PersistGS outperforms constant velocity extrapolation by +2.46dB PSNR and comes within 0.19dB of a ground-truth trajectory upper bound.

We introduce Dual Face-Hair Retrieval (DFHR), a new mixed-modality dual-reference task in image retrieval where a query consists of a face image specifying identity and a hairstyle reference expressed as either an image or text. Unlike prior retrieval settings, DFHR requires cross-component reasoning between two semantically independent attributes -- identity and hairstyle -- originating from heterogeneous modalities. This formulation demands localized feature disentanglement, cross-modal semantic alignment, and mixed-modality composition within a unified embedding space. We construct DFHR-Bench, the first benchmark for mixed-modality face-hair retrieval, comprising over 180K annotated triplets across dual-image and image-text settings, built via a multi-stage annotation protocol ensuring semantic and identity integrity. We further propose MFHC (Multimodal Face-Hair Combiner), a unified framework that fuses disentangled identity and hairstyle embeddings through token injection and multi-view supervision. DFHR and DFHR-Bench together establish a new paradigm for identity-aware, attribute-controllable visual retrieval across modalities.

Underground coal mining requires personnel and heavy equipment to operate within shared, confined, and poorly illuminated spaces where hazards such as equipment proximity violations, structural instabilities, and occluded blind spots are difficult to anticipate. Conventional monitoring systems, including fixed cameras and rule-based proximity alerts, can detect predefined events but lack the 3D scene understanding and contextual memory needed to identify complex or evolving hazards. This paper presents a continuous monitoring framework that converts colourised 3D point clouds into structured and traceable safety reasoning outputs. The framework combines 3D semantic perception, uncertainty-based anomaly detection, rule-based hazard checks, on-device LLM reasoning, and GraphRAG -based memory analysis to identify immediate hazards and interpret longer-term safety patterns. Scene and temporal graphs serve as the explicit knowledge structure, linking perception outputs across reasoning stages. To overcome the scarcity of labeled underground data, real roadway scans, controlled object placement, and high-fidelity longwall simulation were combined to generate diverse hazard scenarios, while self-supervised pretraining improved segmentation from limited annotations. The perception model achieved 92.7% accuracy at 30 FPS with low memory usage. Across 115 hazard scenarios, rule-based checks achieved 57% coverage, increasing to 76% with contextual LLM reasoning and 93% with memory-based reasoning using historical records. Qualitative results show uncertainty-derived anomaly signals support the interpretation of out-of-distribution hazards beyond predefined classes. Overall, graph-based knowledge representation combined with 3D perception and layered safety reasoning provides a practical foundation for intelligent decision support in underground mine monitoring.

Unifying the complementary strengths of diverse Vision Foundation Models (VFMs) into a single efficient model is highly desirable but challenged by the negative transfer inherent in monolithic distillation. To address these feature conflicts, we introduce \textbf{PRISM}, a novel dual-stream Mixture-of-Experts (MoE) framework that synergizes VFMs via modular specialization. We propose a two-stage paradigm: (1) expertise deconstruction, where a teacher-conditional router guides experts to specialize in distinct representational subspaces to mitigate interference, followed by (2) dynamic recomposition, where the router learns to assemble these experts into tailored computational pathways for downstream tasks. Experiments on PASCAL-Context and NYUD-v2 show that \textbf{PRISM} establishes a new state of the art, validating that sparse, emergent specialization is a scalable approach for integrating diverse visual knowledge.

We present PHAF-Personalized Hand Avatars in a Flash, a personalized photo-realistic hand avatar which provides high quality multi-view renders from just two images (dorsal and palmar views).Unlike slow optimization-based techniques, PHAF generates fast personalized textures for real-time deployment on edge devices. Our approach combines semantic guided mesh alignment and densified texture extraction to transfer high-frequency details efficiently. A view-based inpainting network refines textures ensuring smooth, continuous appearance. PHAF generalizes to novel viewpoints and leverages a parametric hand model for accurate articulations, making it compatible with standard graphics engines. Experiments show it is comparable to existing methods in visual fidelity while drastically reducing texture generation time by 30 times, enabling practical AR/VR applications.

Multimodal fake news detection aims to identify the authenticity of news. Existing multimodal fake news detection methods mainly focus on cross-modal consistency, but often fail to explicitly model the semantic incongruity that characterizes deceptive multimodal content. However, misinformation often contains semantic information incongruity with the facts. To address these challenges, we propose Incongruity-aware Distribution Optimization (IDO) to improve the performance of fake news detection from the perspectives of factual incongruity and modality incongruity. For factual incongruity, we introduce a channel-wise reweighting strategy to obtain semantically discriminative embeddings and utilize gaussian distribution to model the uncertain correlation caused by factual incongruity. For modality incongruity, we utilize incongruity contrastive learning to learn cross-modal semantic information. Experiments demonstrate that IDO achieves state-of-the-art performance.

While multimodal deep learning has advanced medical imaging analysis, existing black-box systems \textcolor{black}{may remain confined to isolated tasks, often overlooking} the trust-sensitive nature of clinical diagnosis as a multi-task process. We propose IMT-CXR (Interpretable Multi-task Transformer for Chest X-ray Analysis), a framework that emulates radiologists' diagnostic workflow through three evidence-driven stages: 1) Disease recognition; 2) Attribute characterization (e.g., size, location, severity quantification); 3) Evidence-integrated report generation with traceable decision pathways. The framework employs a unified transformer architecture optimized via medical-domain instruction tuning, sequentially executing four clinical tasks: multi-label disease classification, lesion localization, anatomical segmentation, and radiology report generation. Experimental validation demonstrates competitive performance on ten CXR benchmarks under direct inference and fine-tuning settings. In a blinded evaluation of 160 historical reports from four medical centers, three radiologists rated 66\% of AI-generated reports as comparable to or surpassing original clinical reports in diagnostic clarity, highlighting the framework's translational potential. By establishing traceable diagnostic pathways from anatomical findings to conclusions, this work bridges the gap between AI technical metrics and clinical utility, advancing trustworthy AI systems in medical imaging.

Engineering diagrams pose a distinct challenge for vision-language models: unlike natural images or general documents, they encode information through dense spatial layouts, domain-specific symbols, and cross-references between visual callouts and structured parts tables. Despite their centrality to service, repair, and design workflows, there is no public benchmark for measuring VLM capabilities in this domain; existing datasets primarily focus on flowcharts, scientific figures, or business documents. To address this gap, we introduce Enginuity, the first open dataset and benchmark for evaluating VLMs on complex engineering diagrams. We define two tasks over a corpus of U.S. military service and repair manuals: structured parts-table extraction (Task 1) and free-form visual diagram question answering (VQA)(Task 2) for benchmarking. We evaluate four frontier VLMs (GPT-5.2 Chat, Claude Opus 4.7, Gemma 4, Qwen3-VL-32B-Instruct) under zero-shot and chain-of-thought prompting. On Task 1, models reach Recall@all of 0.61-0.87 but Token F1pen of only 0.03-0.18, exposing a systematic gap between part identification and description fidelity. Task 2 reveals a consistent factual-reasoning gap across all models. A supporting analysis shows that token-overlap metrics under-report model capability on technical descriptions by 2-6x relative to semantic similarity, motivating LLM-as-judge calibration for domain-specific evaluation. We release the dataset, annotations, evaluation harness, and per-sample model outputs to support a reproducible study of VLM capability on engineering content.

Reliable correspondence estimation is a fundamental problem in image processing, underpinning applications such as Structure from Motion, visual localization, and image registration. Existing learning-based methods have significantly improved local feature representations, yet most still operate at the pixel or patch level and lack explicit modeling of regions that are jointly visible across views. We propose SAMatcher, a feature matching framework that formulates correspondence estimation through co-visibility modeling. Instead of directly matching local features, SAMatcher first predicts co-visible region masks and bounding boxes as structured priors for correspondence estimation. Built upon the Segment Anything Model (SAM), it introduces a symmetric cross-view interaction mechanism that enables bidirectional feature exchange and cross-view semantic alignment. We further develop a unified supervision scheme that jointly optimizes mask prediction and box localization through mask learning, box regression, and mask-box consistency constraints. Extensive experiments on challenging benchmarks demonstrate substantial improvements over existing matching pipelines, particularly under large viewpoint and scale variations. Our results show that foundation models originally designed for monocular segmentation can be effectively extended to multi-view correspondence reasoning through explicit co-visibility modeling, offering a new perspective on structured representation learning for image matching. Code and project page: https://xupan.top/Projects/samatcher

Scientific images function as critical evidence in research communication, yet their integrity faces unprecedented threats from AI-generated content that introduces subtle but consequential errors. Existing evaluation paradigms prove inadequate: perceptual quality metrics poorly correlate with scientific validity, while language models lack domain-specific verification capabilities. To address this gap, we propose the \textbf{S}cientific \textbf{I}mage \textbf{U}tility and \textbf{U}pgradability \textbf{A}ssessment (\textbf{SIU$^2$A}) framework, which introduces two complementary dimensions for scientific image evaluation. \textbf{Utility} encompasses \textit{error detection} (identifying scientific inaccuracies) and \textit{correction feasibility} (assessing whether errors can be reliably repaired). \textbf{Upgradability} measures the quality of correction. We categorize scientific image corruption into four fundamental types: Detail Distortion, Incompleteness, False Content, and Entity Confusion. Based on this taxonomy, we construct SIU$^2$A-Benchmark, a dataset with expert annotations for error identification and repair. The framework implements a two-stage evaluation protocol: the \textit{Utility} stage evaluates error detection capability and repair instruction generation, while the \textit{Upgradability} stage assesses whether corrections faithfully restore scientific validity without compromising existing accurate information. Experiments reveal that current multimodal systems exhibit significant limitations in both scientific error assessment and faithful correction, exposing a fundamental gap between visual perception and scientific usability.

Recent generative models can now produce visual artifacts with realistic embedded text and layouts, creating a new misinformation threat: synthetic credibility. We introduce SYNCRED-Bench, a benchmark of 600 AI-generated misinformation images balanced across six credible-form categories and seven fine-grained circulation styles, together with FP450, a real-image negative set for measuring false positives. Extensive evaluation shows that existing systems remain unreliable: under a 5% false-positive-rate constraint, 15 MLLMs achieve only 10.5% true positive rate (TPR), open-source AIGC detectors achieve less than 5%, and commercial APIs reach 57.6%. Human annotators also struggled to identify synthetic credibility, reaching only 63% TPR. These findings establish synthetic credibility as a severe and underexplored visual misinformation challenge, and provide a benchmark for developing detectors that reason beyond superficial credibility cues.

We present P-Topics (Perception Topics) modeling, a novel problem for understanding how images are perceived affectively and across cultures. The goal is to (1) discover and model the different perception experiences in a dataset of images and captions, where each experience is defined by an objective factual and a subjective affective aspect, and (2) associate images to their relevant perception experiences. We introduce **PercepT** (**Percep**tion topic **T**ransformer), a two-stage architecture that tackles P-Topics modeling. In the formation stage, percepT discovers *P-Topics* as visual-textual clusters using an unsupervised training objective, and dynamically selects the number of clusters to match the perceptual richness of the dataset. In the mapping stage, it learns *P-Topic mapping functions* via attention pooling to associate images to their respective clusters. On ArtELingo, PercepT achieves a silhouette score of **0.97** compared to **0.37** from the closest baseline reflecting better perceptual clusters. PercepT also achieves an AUC score of **0.94** compared to **0.77** showing better mapping to perceptual clusters. Human evaluation confirms that PercepT captures semantically meaningful perception experiences and significantly outperforms existing methods. Our implementation will be made public.

In multi-modal image registration, the primary challenge lies in shared structural information extraction. Compared to Transformers, Structured State Space Duality (SSD) offers greater global structural feature extraction with higher efficiency during training and inference. Inspired by these advantages, we propose a novel algorithm for multi-modal image registration, named RegNetMamba-2. Our algorithm incorporates SSD into coarse-to-fine matching process to extract local and global structural features effectively. Firstly, SSD is applied in three different scales for multi-modal feature extraction in our network. To strengthen local representation, we pay more attention on foreground edge and structural information by feature scaling function of SSD. Secondly, for shared feature extraction of input images and multi-modal feature fusion in all scales, we propose cross-modality feature fusion model based on SSD, consisting of Cross-Modality feature Interaction (CMI) module and Multi-Scale feature Fusion (MSF) module. CMI module is designed for cross-modality feature extraction of each scale by SSD in cross form. MSF module is designed to employ a progressive upward fusion in feature-level to obtain fine features, consisting of multi-modal features in all scales. Following coarse-to-fine, the features in 1/8 scale from CMI and 1/2 scale from MSF are collected to calculate matching probability scores. Then we respectively establish matching process by correspondences of pixel-wise. Extensive experiments demonstrate that comparing with state-of-the-art deep-learning based algorithms, RegNetMamba-2 has achieved good effects in both performance and efficiency for multi-modal image registration on the following datasets: VIS-SAR (OSDataset), VIS-IR (LGHD/RoadSence) and VIS-NIR (RGB-NIR sense).

Self-supervised learning (SSL) has emerged as a powerful paradigm for learning meaningful representations from unlabeled data. However, the standard protocol for evaluating these representations, linear probing, is computationally expensive, sensitive to hyperparameters, and provides limited insight into the geometric structure of the representation space. In this work, motivated by connections between neural network generalization and intrinsic dimension (ID) we propose IdEst, a method for estimating the ID of SSL representations via the Minimum Spanning Tree dimension estimator ($\mathrm{dim}_\mathrm{MST}$). Across diverse datasets, architectures, and SSL pretraining objectives, we show that IdEst strongly correlates with downstream linear probe performances. Furthermore, we demonstrate that IdEst enables efficient hyperparameter selection, significantly reducing the computational cost compared to supervised alternatives. Our results highlight intrinsic dimensionality as a principled geometric proxy for assessing SSL representations, complementing standard supervised probing protocols.

High-fidelity semantic 3D scene representations are crucial for numerous applications, including robotics, autonomous driving, and simulation. Beyond this, the ability to edit such representations enables developers to adapt these applications more easily to specific target scenarios. Current approaches provide limited support for controllable editing. We introduce TASE, a method that projects pretrained 2D semantic features into a truncation-aware embedding space to enable flexible 3D scene editing. Our method explicitly optimizes a feature space in which progressively reducing feature channels yields increasingly abstract semantic representations, while retaining more channels preserves fine-grained detail. Additionally, we improve multi-view consistency of the features using a scale- and translation-equivariance loss. The resulting truncation-aware embedding space enables text-driven edits to 3D scenes, providing explicit control over how strongly edits adhere to the original scene content and allowing more substantial modifications than prior methods. Moreover, we propose a finetuning stage for the editing diffusion model to mitigate artifacts caused by geometric changes. Experimental results demonstrate competitive performance in 3D scene editing, substantially outperforming prior methods on edits involving large geometric modifications.

We introduce SagaQA, a long-form video benchmark for multi-hop reasoning over full-length TV series. Existing video reasoning benchmarks often emphasize local understanding of adjacent frames or clips. SagaQA addresses this gap by requiring high-level comprehension of extended multimodal narratives in entire TV shows. A distinguishing feature of SagaQA is the granularity of its reasoning steps. Our dataset necessitates long-range reasoning hops to connect information across completely different episodes. This requires models to reason over entire events and actions, demanding a deep understanding of the show's narration and progression at a multimodal level. Motivated by recent progress in agentic methods, we further study how different planning strategies handle such complex reasoning. We categorize these approaches into three classes-Parallel, Sequential, and Hybrid planners-and evaluate their ability to generate coherent and complete reasoning plans. Our results on SagaQA suggest that hybrid planners consistently produce higher-quality plans and exhibit stronger capabilities for complex, high-level narrative understanding in TV shows.

Feed-forward models for 3D reconstruction have achieved strong performance using deep cross-view attention to exchange information across images. However, these approaches often depend on heavy decoder stacks and lack a structured mechanism for geometry refinement, resulting in poor multi-view consistency. We address this by drawing inspiration from classical bundle adjustment (BA), which can be viewed as an iterative information propagation process between poses and local geometry. Inspired by BA, we propose BA-T, an iterative Transformer that implements BA-style structured updates as a repeatable layer in implicit token space. Instead of relying on deep attention stacks, BA-T refines predictions based on latent residual by a single lightweight layer. Experiments demonstrate that BA-T progressively improves pose and reconstruction accuracy across iterations, achieves stronger cross-view consistency than conventional decoders, and matches or surpasses substantially larger models while using only 16% of their decoder parameters. BA-T provides a compact, efficient, and structural alternative to depth-heavy attention, enabling accurate 3D reconstruction within a lightweight architecture. The code will be made publicly at https://github.com/zhangganlin/BA-T.

Visual DeepSearch requires multimodal large reasoning model (MLRM) agents to answer complex visual queries by repeatedly inspecting image regions, grounding intermediate reasoning in visual evidence, and connecting fine-grained clues across long reasoning chains. However, existing benchmarks mainly focus on single-step visual understanding or static image-question answering, offering limited evaluation of iterative image inspection, visual-anchor grounding, and multi-hop evidence integration. In this work, we introduce VistaHop, a benchmark for evaluating vision-centric search and multi-hop visual reasoning in Visual DeepSearch. VistaHop contains 300 high-resolution images, 25 visual search scenarios, and 350 multi-hop QA tasks that require models to follow evidence chains from visual anchors or fuse information across multiple image-grounded reasoning paths. We further develop VistaArena, a unified evaluation environment that supports tool-augmented reasoning with text search, image search, image cropping, and evidence-based answer validation. Experiments on seven representative MLRMs show that current models remain far from solving VistaHop: the best model, SenseNova-MARS-32B, achieves only 24.31% Pass@1. These results reveal persistent limitations in visual grounding, evidence revisiting, long-chain reasoning, and multi-anchor information fusion, highlighting the need for stronger benchmarks and training methods for Visual DeepSearch.

We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.9B baseline, its remaining errors concentrate in under-optimized regions where model behavior is unstable, data coverage is sparse, or supervision is unreliable. Rather than expanding the training corpus indiscriminately, PaddleOCR-VL-1.6 introduces a region-aware data optimization framework that identifies weak regions from the previous model, applies targeted enhancement to these regions, and improves the reliability of supervision signals. It further adopts a progressive post-training recipe based on curated data selection and reinforcement learning, pushing model performance to a higher level through staged optimization. PaddleOCR-VL-1.6 achieves a new state-of-the-art score of 96.33% on OmniDocBench v1.6, demonstrates strong competitiveness against top-tier VLMs, and provides a practical post-training recipe for the PaddleOCR-VL series.

Feed-forward 3D Gaussian Splatting (3DGS) allows efficient and high-fidelity novel view synthesis (NVS) from an offline recorded image sequence. However, achieving online NVS from streaming and unposed image inputs remains challenging. Although online feed-forward geometric estimation methods have been proposed for streaming depth and point cloud recovery, they cannot be adapted to NVS due to severe rendering artifacts. This is because NVS demands stricter multi-view consistency in Gaussian scales and pose-geometry alignment; even minor deviations would accumulate over time and visibly degrade rendering quality. To this end, we propose FreeStreamGS, a robust online feed-forward framework for efficient and high-quality NVS. We introduce two key mechanisms: a Decoupled Intrinsic Recovery Head that removes cumulative camera intrinsic bias and prevents scene scale jitter during long-term streaming, and a Dynamic Point Refinement Offset strategy that relaxes rigid unprojection to correct coupled pose-depth drift. Extensive experiments show that FreeStreamGS achieves rendering quality competitive with state-of-the-art offline feed-forward 3DGS methods, despite operating without access to future frames.

In nature, events that affect some individuals or groups but not others constitute an implicit intervention and are known as natural experiments. For example, the COVID-19 pandemic was an intervention by the coronavirus on the sub-population infected with COVID. We ask, do natural experiments occur in existing real-world datasets? If yes, how should we treat them? To detect natural experiments in data, we use causal discovery to recover the underlying causal graph and perform feature selection based on causal links. If downstream performance improves by treating the data as interventional rather than observational, we argue that this suggests the dataset contains natural experiments. We first validate this hypothesis by simulating datasets with and without natural experiments using synthetic graphs. We then perform a systematic empirical evaluation on a large suite of real-world datasets. Our results indicate that real-world datasets do contain natural experiments and we can take advantage of those natural experiments to improve model performance using causal inference. Our work represents the initial foray into this area, offering a preliminary exploration within a limited scope.

The development on robust perception systems for Maritime Autonomous Surface Ships (MASS) is heavily constrained by the scarcity of diverse training data, particularly for adverse weather and low-light conditions. Because collecting paired images in dynamic maritime environments is physically impossible, synthetic data generation via unpaired image-to-image translation offers a critical solution. However, existing generative models suffer from failing to preserve the fine structural details of small navigational objects due to latent compression bottlenecks. In this paper, we introduce a framework for generating synthetic maritime data using CycleGAN-turbo, a one-step unpaired translation architecture. By incorporating zero-convolution skip connections to bypass the Variational Autoencoder (VAE) bottleneck, our approach explicitly preserves small object details (e.g., distant vessels and sea marks) during translation. We compiled a dataset of 7,000 maritime images to train and evaluate models for Day-to-Foggy, Day-to-Sunset, and Day-to-Night domain translations. Qualitative evaluations and variable-strength inference studies demonstrate that our method effectively synthesizes realistic atmospheric conditions while maintaining the underlying semantic structure of the scene. The Day-to-Foggy and Day-to-Sunset models exhibit great structural retention, whereas the Day-to-Night model highlights the challenge of semantic hallucination, such as generating artificial coastal lights, induced by unbalanced training distributions. Ultimately, this work establishes an efficient, structure-aware data synthesis pipeline that directly addresses the data scarcity bottleneck in autonomous maritime navigation.

Modern text-to-image models have achieved strong visual synthesis, yet remain unreliable when prompts require implicit visual constraints, relational reasoning, or external knowledge. Existing retrieval-augmented and agentic generation methods mitigate this issue by acquiring external knowledge, references, or refined prompts for the current request, yet they typically treat each generation as an isolated episode and do not systematically preserve past successes or failures for future use. In this work, we ask whether a text-to-image system can continually improve from its own generation experience without updating the underlying generator. We propose MemoGen, a training-free framework that augments existing image generators with an agentic evolution layer. For each task, MemoGen explicitly infers visual requirements, retrieves external evidence and references when necessary, translates them into executable generation constraints, evaluates the generated result, and stores task understanding, reference choices, visual feedback, successful strategies, and failure lessons as reusable experience memory. Across evolution rounds, the agent retrieves relevant experience to improve similar future generations, selectively repairing previously failed cases while preserving successful ones, thereby enabling test-time self-evolution without parameter updates. Extensive experiments on knowledge-intensive and reasoning-oriented benchmarks demonstrate the effectiveness of this paradigm: after only two evolution rounds, MemoGen built upon the open-source Qwen-Image backbone surpasses strong proprietary systems such as Nano Banana Pro and GPT-Image-1 on WISE and Mind-Bench, showing that explicit experience memory can serve as a powerful continual learning signal for reliable text-to-image generation.

We study preference alignment for image inpainting. Rather than proposing yet another method, we revisit the problem from first principles and reassess its core challenges. We adopt the widely used direct preference optimization framework and construct preference training data with publicly available reward models. Our empirical study spans nine reward models, two benchmarks, and two baseline inpainting models that differ in architecture and generative mechanism. Our main findings are: (1) Most reward models provide valid signals for preference data construction, although some are unreliable as evaluators. (2) Across models and benchmarks, preference data exhibits consistent trends under both candidate and sample scaling. (3) Reward models display pronounced biases--particularly in brightness, composition, and color scheme--that make them prone to inducing reward hacking. (4) A simple ensemble of reward models mitigates such biases and yields robust, generalizable performance. {\color{rebuttal_blue}(5) Preference alignment is transferable to the object removal task, where the goal shifts from open-ended creative generation to coherent background completion. (6) Further analysis reveals that a calibrated ensemble method further mitigates hacking and improves robustness.} Without modifying model architectures or introducing additional datasets, our models substantially outperform prior state-of-the-art models on standard metrics, large vision-language model evaluations, and human assessments. Our code is available at: https://github.com/shenytzzz/Follow-Your-Preference.

In this study, we evaluate the performance of skin lesion classification using ResNet-based convolutional models, focusing on the impact of demographic bias in training data, particularly variations in patient sex and age. We use linear programming to generate datasets with controlled demographic characteristics, allowing systematic investigation of bias effects. Three learning strategies are evaluated: a single-task model, a reinforcing multi-task model, and an adversarial learning scheme. Our sex-based analysis indicates that sex-specific training datasets optimise model performance. Notably, including male patients in the training data improved performance for the male subgroup, even in female-majority cases. Reinforcing and adversarial learning schemes narrowed or eliminated bias gaps in balanced and female-majority datasets. However, these strategies proved less effective in male-majority settings, where models continued to perform better for males than females. The two learning schemes showed marginal bias reduction compared to the baseline model in predominantly male patient populations. Age-based analysis demonstrates comparable baseline performance across the three model approaches, with performance declining across age categories. Younger groups consistently achieve the highest performance, regardless of training data distribution. Although balanced training yields optimal results for the youngest age category, performance decreases in older categories. We find that sex biases arise mainly from data imbalances, while age biases consistently favour younger groups regardless of distribution. These distinct mechanisms require targeted mitigation strategies. Additionally, cross-dataset validation on two external datasets revealed that domain shifts notably affect performance and patterns of demographic bias.

Joint audio-video generation aims to synthesize realistic audio-video pairs that are both semantically aligned with text prompts and precisely synchronized. While existing joint audio-video generation models often require substantial training resources to improve fidelity, Inference-Time Scaling (ITS) has recently emerged as a promising training-free alternative in single-modality domains. However, extending ITS from a single modality to multimodal domains is non-trivial, as it requires balancing multiple heterogeneous objectives. In this paper, we present the first comprehensive study of ITS for joint audio-video generation. We first demonstrate that a multi-verifier framework is essential to address the limitations of single-objective guidance, including asymmetric performance trade-offs and verifier hacking. Through systematic analysis, we then identify an optimal multi-verifier combination that yields balanced improvements across all quality dimensions. Finally, to effectively aggregate diverse reward signals, we propose Adaptive Reward Weighting (ARW), a novel test-time optimization algorithm. ARW treats reward aggregation as an online optimization problem, utilizing learnable parameters to calibrate reward variances without requiring prior knowledge of reward distributions, thereby ensuring robust multi-objective selection. Experimental results on VGGSound and JavisBench-mini benchmarks demonstrate that our framework significantly enhances semantic alignment, perceptual quality, and audio-visual synchronization of generated outputs. Synthesized samples and code are available on the project page: https://jung-jaemin.github.io/ITS-AVGen-Proj.

Vision-language models (VLMs) for radiology have emerged as a scalable paradigm by leveraging image-report pairs naturally produced in clinical workflows. However, this pairing reveals a mismatch in scale: each finding occupies only a small region of the image, yet supervision is provided only at the global image-report level. This poses a central challenge: prior approaches spread weight densely across all patches rather than concentrating on the sparse subset relevant to a given query. To address this, we present GLINT (Gated Language-Image alignmeNT), a framework that explicitly models this sparse correspondence. On the alignment side, we introduce Sparsely Gated Alignment, a novel architecture in which a sigmoid gate over a separate gate embedding space activates only the patches relevant to each textual query, enforcing explicit sparsity. On the representation side, we add Dense Feature Regularization, which anchors the trainable encoder's intermediate features to a frozen self-supervised learning (SSL) teacher, preserving the fine-grained patch features that the gate relies on. The same recipe applies to both 2D chest X-ray (CXR) and 3D chest computed tomography (CT), built with DINOv3 and V-JEPA 2.1, respectively. GLINT enables zero-shot classification, grounding, and segmentation from free-text queries, and to our knowledge is the first to demonstrate zero-shot segmentation on 3D CT volumes without mask supervision. Notably, the most pronounced gains arise on zero-shot grounding and segmentation, where sparse, query-specific localization is required, consistent with our design intent. In downstream evaluation, GLINT outperforms both SSL encoders and medical VLMs on classification, report generation, and segmentation.

While instruction-based video editing has seen significant progress, joint audio-visual editing remains constrained by the absence of dedicated datasets and benchmarks. To bridge this gap, we present JAVEdit-100k, the first large-scale, high-quality dataset tailored for instruction-guided joint audio-visual editing. Focusing on human-centric videos, JAVEdit-100k comprises approximately 100K editing triplets spanning five distinct categories, including subject editing and speech editing. This dataset is rigorously constructed via four meticulously designed generation pipelines, seamlessly paired with an agent-in-the-loop quality control mechanism. Furthermore, to address the lack of standardized evaluation within the field, we introduce JAVEditBench, a comprehensive benchmark featuring curated source videos and human-aligned instructions across all editing categories. Finally, we propose JAVEdit, a pioneering baseline model for instruction-guided joint audio-visual editing. Experiments show that \model\ outperforms all baselines on five of six evaluation metrics.

Recognizing human actions from point cloud sequences is critical for 3D perception driven applications such as autonomous driving and human-computer interaction. However, the irregular structure and temporal inconsistency of point clouds pose unique challenges for spatio-temporal representation learning, especially in capturing both global motion context and fine-grained temporal dynamics. We propose SRENet, a spectral-aware framework designed to explicitly learn both global context and fine-grained temporal dynamics of motion from a frequency perspective for action recognition. SRENet introduces a Spectral Decomposition Block (SDeBlock) that performs wavelet-based analysis along temporal and spatial axes, disentangling features into low- and high-frequency components with frequency-specific attention. To recover residual dynamics and re-align temporal frequency structures distorted during semantic fusion, a Spectral Re-entry Block (SReBlock) performs secondary temporal decomposition. Furthermore, a spectral-aware learning strategy is devised to enhance discriminability in both frequency subspaces via contrastive loss and a curriculum schedule that gradually shifts focus from low- to high-frequency spaces in line with coarse to detailed motion patterns. Extensive experiments on MSR-Action3D, NTU-RGBD and NTU-RGBD120 demonstrate that SRENet achieves state-of-the-art performance, validating the effectiveness of frequency modeling in point cloud-based action understanding.

As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations. While recent reconstruction-based neural simulators offer photorealism, they are fundamentally constrained by their initial captured data and struggle to generalize to highly dynamic or novel scenes. To overcome these limitations, we introduce OmniDreams, a foundation generative world model mid- and post-trained from the Cosmos diffusion model to autoregressively generate action-conditioned videos in real time. By leveraging the rich visual priors of Cosmos and mid- and post-training on 21k hours of driving scenarios, OmniDreams synthesizes complex, unobserved phenomena that are hard for traditional simulators to capture, such as extreme weather and unpredictable dynamic agent behaviors. Crucially, it autoregressively conditions its photorealistic sensor generation on past frames, the current simulator state, and immediate driving actions. Deployed in a closed-loop system with the Alpamayo 1 policy model and AlpaSim orchestrator, OmniDreams acts as a highly responsive, reactive environment, providing a scalable and comprehensive solution for training and evaluating next-generation autonomous driving policies. We additionally show preliminary results indicating that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters. These results highlight the potential for a real-time world model like OmniDreams to also serve as a backbone for policy architectures.

Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we find that the attention maps of smaller self-supervised ViTs localize foreground objects better than those of larger ViTs. However, we still need large ViTs, because they extract richer representations from each patch. To get the best of both worlds, good localization and rich representations, we propose $A^2$, a simple method that leverages this inverse scaling finding by decoupling where to look (a small attention model) from what to extract (a large embedding model): we crop around the attention peaks of a small model and embed the crops with a larger model. $A^2$ uses entirely pretrained features, requires no group labels, and does not require per-dataset attention or backbone training. Across 5 benchmarks, $A^2$ is competitive with backbone-matched loss-level methods like DFR, and outperforms end-to-end attention training under stronger distribution shifts.

Large Vision-Language Models (LVLMs) show strong visualization interpretation, yet it is unclear whether their responses reflect genuine reasoning over visual evidence or factual priors learned during training. Current evaluations mix these two sources, obscuring when correct visual interpretation is overridden by memorized facts. We present a framework that isolates visual correctness from factual correctness, revealing validity limitations in existing visualization literacy assessments. Across three experiments with 15 state-of-the-art LVLMs: (1) several models reach human-level performance on standard tests (VLAT), but this may reflect factual recall rather than visual understanding, while randomized-data tests (reVLAT) underestimate literacy when correct visual interpretation is superseded by factual priors. (2) Using our Counterfactual Visualization Literacy Assessment Test (CVLAT) with capability-normalized arbitration metrics, we classify models by the sign of their visual-factual reliance index (VFRI), revealing a visualization-oriented majority and a factual knowledge-oriented minority, though several near-zero cases warrant caution. A human baseline (N=30) on the same counterfactual items confirms that people overwhelmingly follow the chart under conflict, providing a human reference point. (3) Prompt-based intervention can shift prioritization, but its effectiveness is highly model-dependent and direction-asymmetric, and high chart-reading capability does not predict prompt-controllability. Overall, high visualization accuracy is not sufficient evidence of faithful visual reasoning: reliable integration into visual analytics requires evaluating not only visualization literacy but also how models arbitrate between visual evidence and factual priors when the two diverge. Benchmark and code: https://github.com/JaeyoungKim-HCIL/CVLAT

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis by representing scenes as collections of anisotropic Gaussians optimized via differentiable rasterization. However, standard pixel-space losses (L1, SSIM) constrain only aggregate reconstruction error, permitting the optimization to redistribute error across frequency scales. This leads to oversmoothing and structural artifacts, particularly in sparse-view settings where supervision is limited. We propose KC-3DGS, which augments 3DGS training with wavelet-domain supervision based on natural image statistics. Our method combines three components: (1) a multi-scale wavelet coefficient alignment loss that explicitly penalizes missing high-frequency detail, (2) a supervised kurtosis concentration loss that encourages rendered images to match the heavy-tailed frequency statistics of ground-truth images, and (3) a cross-band covariance penalty that promotes frequency specialization. We provide theoretical analysis showing that pixel-space losses admit a family of indistinguishable perturbations under wavelet redistribution, and that our joint objective excludes degenerate solutions. Experiments across MipNeRF360, Tanks&Temples, MVImgNet, DeepBlending, and WRIVA-ULTRRA demonstrate consistent improvements in perceptual quality. On the challenging WRIVA-ULTRRA outdoor dataset, KC-3DGS achieves a 9.48% improvement in DreamSim while also improving PSNR, SSIM, and LPIPS. In sparse-view settings with only 12 training images, our method improves PSNR by up to 0.5 dB on MipNeRF360 while maintaining perceptual quality. The approach integrates seamlessly into existing 3DGS pipelines as a plug-and-play regularization strategy.

Guidance methods, such as classifier-free guidance (CFG) and auto-guidance (AG), have advanced noise-to-data generation in diffusion models. Recently, bridge models have introduced a data-to-data generative process that can exploit an instructive clean prior. In this work, inspired by previous methods creating quality difference between denoising results as guidance, we propose a training-free bridge guidance method, termed Prior Guidance (PG). Specifically, we introduce a weak prior, which is unseen during bridge pre-training, hindering prior exploitation and thereby degrading denoising result. Then, we contrast it with the seen prior to highlight and enhance prior exploitation via a scaling factor. Moreover, we analyze the underlying mechanism of prior exploitation in the bridge process and design frequency-modulated prior guidance (FMPG), which tailors the guidance scale to low- and high-frequency bands coherent with bridge generative dynamics. To address prior exploitation in image in-painting, we develop a cascaded framework, CFG-FMPG, which first generates a noisy hidden representation via CFG and then exploits it as a generative prior with FMPG, fulfilling their complementary strengths without compromising inference efficiency. Experiments demonstrate that our PG methods consistently improve pre-trained bridge models across diverse image translation tasks.

Objective: Diseases such as age-related macular degeneration and retinitis pigmentosa cause the degradation of the photoreceptor layer. One approach to restore vision is to electrically stimulate the surviving retinal ganglion cells with a microelectrode array such as epiretinal implants. Epiretinal implants are known to generate visible anisotropic shapes elongated along the axon fascicles of neighboring retinal ganglion cells. Recent work has demonstrated that to obtain isotropic pixel-like shapes, it is possible to map axon fascicles and avoid stimulating them by inactivating electrodes or lowering stimulation current levels. Avoiding axon fascicle stimulation aims to remove brushstroke-like shapes in favor of a more reduced set of pixel-like shapes. Approach: In this study, we propose the use of isotropic and anisotropic shapes to render intelligible images on the retina of a virtual patient in a reinforcement learning environment named rlretina. The environment formalizes the task as using brushstrokes in a stroke-based rendering task. Main Results: We train a deep reinforcement learning agent that learns to assemble isotropic and anisotropic shapes to form an image. We investigate which error-based or perception-based metrics is adequate to reward the agent. The agent is trained in a model-based data generation fashion using the psychophysically validated axon map model to render images as perceived by different virtual patients. We show that the agent can generate more intelligible images compared to the naive method in different virtual patients. Significance: This work shares a new way to address epiretinal stimulation that constitutes a first step towards improving visual acuity in artificially-restored vision using anisotropic phosphenes.

Remote sensing change detection for real-world monitoring often relies on imperfect heterogeneous observations, where pre- and post-event images may be asynchronous, cross-sensor, or affected by illumination, seasonal, and modality shifts. This setting is especially challenging for EO-SAR disaster mapping, where nuisance variation can resemble structural damage. We propose FAF-CD, a frequency-aware hybrid framework with a DINOv3-pretrained ConvNeXt encoder and a linear-complexity VMamba-based decoder. Its rectification-aware tri-branch fusion module combines deformable spatial alignment with Fourier and Haar-wavelet comparisons, using adaptive gating to aggregate complementary cues across scales. On BRIGHT validation, a matched heterogeneous EO-SAR adaptation improves clean and perturbed tc-mIoU/tc-mAP over NeXt2Former-CD. FAF-CD also generalizes to binary optical CD, achieving 0.924 cF1 on LEVIR-CD and 0.955 cF1 on WHU-CD, and obtains the best average perturbed cIoU/cF1 on both binary datasets among M-CD and NeXt2Former-CD under pseudo-change-aligned stress tests. It further reduces cost by approximately 24 GFLOPs relative to NeXt2Former-CD while maintaining or improving accuracy.

This paper studies the problem of inverting the DDIM image generation process to recover latent variables, particularly the initial noise map, from a generated image. Existing methods often struggle with accuracy in this task. We propose a novel hybrid approach that combines direct inversion via gradient descent for the first step, followed by a fixed-point method for subsequent steps. Empirical evaluations across three datasets demonstrate that our method significantly improves the prediction of initial latent variables while achieving superior reconstruction accuracy. Additionally, we introduce a new evaluation, called the self-interpolation test, which assesses the quality of images generated from interpolated points between the true and predicted latent maps, offering deeper insights into performance. Our results reveal that while existing methods perform reasonably well in reconstruction, they consistently fail to accurately predict the initial latent variables, resulting in poor performance on the self-interpolation test. In contrast, our method outperforms all others across all metrics, providing valuable insights into diffusion models and enhancing their applications in image generation and editing.

The deployment of data-driven computer vision models for structural health monitoring (SHM) is heavily constrained by the data silo dilemma due to stringent privacy and security regulations. While federated learning (FL) offers a privacy-preserving collaborative alternative, its application to nationwide infrastructure networks is severely hindered by the challenge of ``double heterogeneity'': macro-level physical divergence across disparate structural types and micro-level statistical imbalances within local datasets. To overcome this challenge, this paper proposes a novel hierarchical federated learning framework. The framework orchestrates a synergistic two-tier optimization strategy. At the macro-level, a dynamic gradient-based clustering mechanism autonomously aggregates distributed clients into specialized expert groups based on their structural degradation trajectories, circumventing the need for prior geographical metadata. Concurrently, at the micro-level, an intra-cluster Dynamic Region-Adaptive Proximal Regularization (DRAPR) module computes a real-time statistical Non-IID Intensity Score for each client. By adaptively modulating a proximal penalty based on local label skewness and gradient divergence, DRAPR effectively calibrates local updates, mitigates client drift, and prevents the catastrophic forgetting of minority damage classes. Comprehensive evaluations on a large-scale, real-world structural inspection dataset demonstrate that the hierarchical integration of macro-clustering and micro-regularization successfully neutralizes dual-level heterogeneity, yielding highly robust and specialized diagnostic models for complex infrastructure inspection.

Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate inference, resulting in memory consumption that scales linearly with context length. This issue is particularly pronounced in VLMs due to substantial redundancy in the visual modality. Although KV cache eviction approaches can effectively reduce inference memory, they often incur significant performance degradation in VLMs, as most are designed for language models and overlook the inherent gap between text and vision. By systematically analyzing the modality gap in VLMs in this work, we argue that the importance of visual information should be grounded in textual guidance and accordingly propose a Text-Grounded KV Eviction method for VLMs (TGV-KV). TGV-KV comprises three submodules: (1) Text-Vision Budgeting (TVB) assigns budget to each layer based on the mutual information interaction. (2) Text-Weighted Ranking (TWR) assesses the priority of text and ranks vision importance based on weighted text-image attention. (3) Text-Prioritised Retention (TPR) policy strategically preserves text KV to avoid acute information loss. We evaluate TGV-KV across five models with different sizes and architectures, showing that TGV-KV preserves 99.2% full-KV accuracy on the VizWiz-VQA task with LLaVA-NeXT and boosts end-to-end throughput by 52.6% with an extreme retention budget of 5%. Code is available at https://github.com/Danielement321/TGV-KV.

Generalized segmentation of medical images prevents performance degradation when different imaging devices and clinical protocols are used across multiple domains. The Whitening Transform-based Probabilistic Shape Regularization Extractor (WT-PSE), published in IEEE Transactions on Medical Imaging in 2024, addresses this challenge by employing feature decorrelation and Wasserstein distance-based knowledge distillation to achieve robust cross-domain segmentation. This study systematically examines improvements to the WT-PSE learning framework. Four limitations in the original implementation are identified: limited training augmentations that fail to simulate real scanner variations, reliance on per-pixel binary cross-entropy loss that is sensitive to edge noise, the absence of a scheduled loss weighting strategy that may destabilize early training, and the lack of ablation switches for controlled scientific comparison. To address these issues, we propose four enhancements: (1) domain-adaptive augmentation including random erasing, gamma correction, and salt-and-pepper noise; (2) a hybrid BCE and Dice loss function for improved edge-aware segmentation under noisy conditions; (3) a curriculum-based Dice weight scheduling strategy; and (4) command-line control flags for systematic ablation studies. Experiments on the fundus optic disc segmentation benchmark demonstrate that the improved pipeline achieves a final epoch optic-disc Dice score of 0.956 and an ASD score of 13.31, outperforming the baseline epoch-5 Dice score of 0.939. These results indicate that training-level improvements can provide consistent performance gains without modifying the underlying WT-PSE architecture.

Remote photoplethysmography (rPPG) enables non-contact extraction of blood volume pulse (BVP) signals using consumer-grade cameras. Recent unsupervised rPPG methods learn BVP representations without requiring ground-truth physiological annotations, yet their optimization is often hindered by noisy and unstable gradients, resulting in slow convergence and limited cross-domain generalization. In this paper, we propose FCUS-rPPG, a fast-converging unsupervised rPPG framework with strong generalization capability. Motivated by the observation that BVP representations exhibit both multi-spectral covariation and low-dimensional manifold structure, we design a spectrally shared backbone that facilitates BVP feature disentanglement while improving optimization efficiency. To jointly enhance convergence stability and generalization performance, we further develop a unified optimization framework operating at the gradient, loss-landscape, and feature-representation levels. Specifically, a post-verification masking mechanism filters out misleading gradients according to the weak-amplitude physiological prior of BVP signals; a perturbation-based loss landscape smoothing strategy steers optimization toward more generalizable flat minima; and a noise-aware null-space regularization constrains feature updates to the orthogonal complement of the noise subspace, thereby mitigating noise-induced representation drift. Extensive experiments on five datasets demonstrate that FCUS-rPPG requires only one training epoch, whereas existing methods typically require tens to hundreds of epochs. Notably, FCUS-rPPG consistently achieves state-of-the-art (SOTA) performance in cross-dataset evaluations. This study provides an efficient and robust solution to the real-world deployment of unsupervised rPPG. The source code will be publicly available at https://github.com/JiaJieLee/FCUS-rPPG.

Despite rapid progress, multimodal large language models (MLLMs) still fail on tasks that humans solve effortlessly, such as navigating a grid maze from a screenshot or selecting the correct puzzle piece. Rather than retraining the model, we ask a complementary question: how much capability can be elicited from a frozen MLLM purely by improving the execution scaffold around it? We introduce MUSE, a multimodal unified structured execution harness that wraps any off-the-shelf MLLM with composable modules for task representation, visual processing, perception tool use, structured parsing, deterministic verification, and verifier-guided repair, without any model retraining. We evaluate MUSE across diverse benchmarks spanning visual spatial planning, visual perception, multimodal reasoning, and fine-grained visual discrimination, using multiple state-of-the-art MLLMs. MUSE delivers consistent gains over the bare model in all settings, with the largest jumps on challenging instances. Further analysis reveals that many MLLM failures arise from harness-level shortcomings rather than fundamental model deficits, and can be addressed through verifier-guided repair without touching the model. These findings highlight the agentic multimodal harness as a critical yet underexplored design dimension, offering an orthogonal avenue for improving MLLMs beyond model-centric optimization.

Inertial odometry (IO) using only Inertial Measurement Units (IMUs) provides a lightweight solution for human motion tracking in augmented reality (AR) and wearable devices. Recent learning-based IO methods have improved the generalizability of inertial localization through large-scale pretraining on human motion datasets. However, these approaches remain prone to drift and noise because they do not explicitly capture human motion dynamics, especially on daily activity datasets such as Nymeria. In this work, we propose to ground inertial odometry in human kinematics through a learned IMU-inferred pose prior, which promotes physically consistent motion constraints. We integrate this pose prior into existing IO architectures and reduce positional drift by up to 36% on the challenging Nymeria dataset, which is 5x larger than datasets used in prior work. We further improve long-term performance with a sensor-fusion framework that incorporates auxiliary signals from lightweight sensors already available on commercial AR glasses, including magnetometers, barometers, and secondary IMUs. With this fusion strategy, positional drift is reduced by up to 42%, improving robustness and generalization across diverse motion conditions. Together, our results introduce a new paradigm for inertial and lightweight odometry by unifying human motion kinematics with multimodal sensing, setting a new benchmark for accurate and robust camera-less human tracking. Our website is available at https://spice-lab.org/projects/MARIO/.

We present a novel compact deep multi-task learning model to handle various autonomous driving perception tasks in one forward pass. The model performs multiple views of semantic segmentation, depth estimation, light detection and ranging (LiDAR) segmentation, and bird's eye view projection simultaneously without being supported by other models. We also provide an adaptive loss weighting algorithm to tackle the imbalanced learning issue that occurred due to plenty of given tasks. Through data pre-processing and intermediate sensor fusion techniques, the model can process and combine multiple input modalities retrieved from RGB cameras, dynamic vision sensors (DVS), and LiDAR placed at several positions on the ego vehicle. Therefore, a better understanding of a dynamically changing environment can be achieved. Based on the ablation study, the model variant trained with our proposed method achieves a better performance. Furthermore, a comparative study is also conducted to clarify its performance and effectiveness against the combination of some recent models. As a result, our model maintains better performance even with much fewer parameters. Hence, the model can inference faster with less GPU memory utilization. Moreover, the result tends to be consistent in 3 different CARLA simulation datasets and 1 real-world nuScenes-lidarseg dataset. To support future research, we share codes and other files publicly at https://github.com/oskarnatan/compact-perception.

Egocentric Natural Language Query (NLQ) grounding asks a model to localize, in a long first-person video, the temporal interval that answers a free-form text query. Existing methods fuse video appearance with the query but ignore hand motion, despite the fact that roughly 41% of Ego4D NLQ queries are answered at a moment of hand--object manipulation or their immediate outcomes.We propose a hand-trajectory encoder for converting a sequence of hand skeletons into highly-semantic hand kinematic features, which are then aligned and combined with pretrained video--text features through a cross-attention fusion strategy with adaptive gating. On the Ego4D NLQ v2 validation split, the clearest gains appear for Hand-Object Interaction queries (+2.54 R1@IoU=0.3) and Quantity/State queries (+4.32 R1@IoU=0.3), indicating that hand trajectory provides grounding cues beyond appearance alone.

Existing autonomous driving datasets have enabled major progress, but fall short in sensor fidelity, map completeness, or geographic diversity. We present KITScenes Multimodal, a European dataset built around high-fidelity sensors and maps. Our fully synchronized sensor suite combines high-resolution global-shutter cameras, long-range lidar beyond 400m, 4D imaging radar, and redundant GNSS/INS localization. Our HD maps are, to our knowledge, the most complete of any sensor dataset, validated through autonomous driving trials on open-source software. For the first time in a public dataset, all driving-relevant traffic elements, such as traffic lights, are mapped in 3D to a reprojection-accurate level with full topological connectivity. Recorded in cities with irregular street layouts and mixed traffic modes, our dataset complements existing datasets by broadening the available geographic diversity. We also introduce four benchmarks, each advancing spatial learning for embodied AI: online HD map construction, long-range depth estimation, novel view synthesis, and end-to-end driving. Project page: https://kitscenes.com/

Deploying language-driven agents in robotics requires evaluations that reflect real-world task demands: natural-language instructions with reproducible outcomes. Such agents must connect language models to callable perception and control tools, and be assessed using deployment-critical metrics including latency, accuracy, and error modes. We present SCOPE (Simulation and Camera Operations for Perception and Evaluation), a modular agent for natural-language, open-vocabulary pan-tilt-zoom (PTZ) camera control and visual scene understanding, designed explicitly for edge deployment. SCOPE operates both in a Blender-based simulation environment and on a physical PTZ camera, executing all perception, planning, and control locally at the deployment site using edge-accessible compute. We release a 536-task benchmark spanning QA, single- and multi-step commands, counting, spatial reasoning, descriptions, and optical character recognition in a Blender-based simulation environment that exposes realistic PTZ control affordances. Execution traces are combined with an LM-as-Judge to evaluate latency, accuracy, and error modes. We evaluate 19 planner-perception model combinations pairing Qwen3 small language models (SLMs) with Moondream and Qwen vision-language models (VLMs). Stronger SLMs substantially reduce hallucinations and improve tool routing, leading to more reliable closed-loop behavior. Once a sufficiently capable SLM is used, perception becomes the dominant performance bottleneck. Mixture-of-Experts models on both the planning and perception side consistently match or exceed dense alternatives at latencies and memory footprints comparable to much smaller networks. Quantization provides additional efficiency gains with minimal accuracy degradation, identifying a practical, sim-to-real validated design point for real-time, edge-feasible language-driven PTZ control.

Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks. Recent work has shown that this paradigm is highly vulnerable to backdoor attacks, and that existing defenses are ineffective in open-ended generation settings. In response, we propose BYORn, a backdoor-robust fine-tuning framework motivated by the observation that poisoned target responses are often semantically implausible given the corresponding image-text inputs and a pretrained model. BYORn identifies such misaligned responses and dynamically replaces them with alternative responses generated by the model, thereby breaking the correlation between triggers and target outputs. The resulting objective gradient corresponds to the gradient of the empirical estimate of the population risk upper bound over the clean data distribution. Empirically, BYORn consistently improves robustness to backdoor attacks while preserving clean-task performance, establishing a new trade-off frontier between generalization and attack success rate. Finally, we demonstrate that BYORn remains effective against adaptive attacks specifically designed to circumvent the proposed defense.

Accurate registration of CAD models to CT scans is essential for establishing ground truth geometry in volumetric imaging. Obtaining reliable object masks is of growing importance in machine learning settings; as recent architectures grow more capable, huge datasets are required to fully utilise their capabilities. Traditional intensity-based methods fail when CT grayscale values lack calibration references, while point-based algorithms (e.g., ICP, RANSAC) require feature correspondence unavailable between idealized CAD geometry and noisy volumetric CT data. We propose a two-stage geometric registration method for cylindrical objects (ionization chambers) that takes advantage of the distinctive geometric features of the objects. First, we estimate the 3D rotation axis by detecting elliptical cross-sections across CT slices, fitting ellipses to edge-detected contours, and performing PCA on the fitted ellipse centers after RANSAC outlier removal. Second, we voxelize the CAD model, orient it along the detected axis, and maximize volumetric overlap with the CT scan through translational adjustment. This approach achieves robust registration with tilt and orientation errors below $0.1^\circ$ without intensity calibration or feature matching. Once registered, the aligned CAD model provides ground truth geometry for applications including machine learning-based object localization and automated analysis in industrial CT workflows.

Normalization layers such as BatchNorm and LayerNorm have long been considered essential for stable training in deep networks. This work demonstrates that they can be fully replaced by a single learnable activation mechanism. We identify a plasticity suppression effect induced by standard normalization: learnable activation parameters rapidly lose adaptability when paired with normalization layers. Motivated by this observation, we introduce SALU (Saturated Adaptive Linear Unit), \[ \operatorname{SALU}(x;a,b) = \frac{a x}{\sqrt{1 + a b x^2}},\quad a>0,\; b>0 \] a bounded, learnable activation that provides intrinsic signal stabilization without relying on batch statistics or external affine parameters. Building on SALU, we propose SaluNet, a paradigm grounded in total plasticity: SALU replaces normalization layers, while SWALU and GALU replace standard activations. With ResNet-18, SaluNet-C-18 achieves 97.35\% on CIFAR-10 and 83.25\% on CIFAR-100 without normalization, maintaining 93.44\% and 76.23\% at batch size 1 where normalized architectures fail. For transformers, SaluNet-T improves over LayerNorm-GELU from 90.92\% to 91.01\% on CIFAR-10 and from 66.54\% to 68.10\% on CIFAR-100. SaluNet-C-50 reaches 78.67\% Top-1 on ImageNet-1K at $224\times224$, and $79.23\%$ at $288\times288$. These results suggest normalization layers suppress total plasticity, a property biological neurons inherently possess, enabling deep networks to learn effectively.

Autonomous driving perception is typically evaluated on clean benchmark data, yet real-world deployment requires robustness to rare, structured, and potentially adversarial sensor anomalies. This gap is especially critical for LiDAR, where external actors can physically manipulate the sensing process to induce black-box perception failures without accessing the model. Existing LiDAR benchmarks provide little visibility into this failure mode. Prior adversarial LiDAR studies have largely centered on attack hardware, geometric and algorithmic defenses, and early-generation detectors, leaving the robustness of modern perception systems unexplored. To address this evaluation gap, we introduce ATLAS (Adversarial Temporal LiDAR Attack Suite), the first large-scale, physically grounded evaluation benchmark for LiDAR perception models under black-box sensor attacks, simulating the two primary attack modes -- point injection and point removal -- across real driving sequences. Evaluating a broad cross-section of current state-of-the-art LiDAR perception models, ATLAS reveals a surprising robustness asymmetry: models with stronger performance on standard benchmarks tend to better withstand removal attacks, yet are actually more vulnerable to injection attacks than weaker models. We trace this vulnerability to standard object database sampling augmentations, revealing how current training practices can induce architecture-agnostic robustness failures, and study initial directions for mitigating both attack modes. We release the ATLAS generation code to support extensible, reproducible evaluations as attack capabilities evolve, helping make black-box sensor robustness an explicit consideration in future LiDAR perception development.

Visual posters are a compact medium for communicating dense information, yet progress on automatic poster generation remains difficult to measure because existing evaluations are often restricted to paper-only inputs, narrow domains, or surface-level visual similarity. We introduce Any2Poster Bench, a benchmark for any-source poster generation that evaluates systems across eight input modalities--PDFs, URLs, PPTX, DOCX, Markdown, LaTeX, notebooks, and videos--and five content domains. Any2Poster Bench pairs each source with quiz-based probes of verbatim factual retention and interpretive understanding, together with VLM-based judgments of visual quality, layout, readability, content completeness, and logical flow, enabling reproducible assessment of both information fidelity and visual communication. To instantiate and validate this benchmark, we further present Any2Poster Agent, an end-to-end reference agent that parses heterogeneous sources, organizes salient content, plans poster layouts, renders posters, and iteratively refines them using visual feedback. On Any2Poster Bench, Any2Poster Agent achieves 87.25% average accuracy across input modalities and 87.28% across content domains. On PaperQuiz-style evaluation, where prior paper-to-poster agents are directly comparable, Any2Poster Agent improves over PosterAgent-4o from 51.06-51.33% to 72.58% overall accuracy and from 116-121 to 145.16 in density-augmented score. Together, Any2Poster Bench and Any2Poster Agent provide a reusable evaluation resource and a competitive baseline for studying multimodal, domain-general poster generation.

Single-image reflection separation is fundamentally challenged by the entanglement of transmission and reflection layers under complex image formation processes. Existing approaches largely rely on simplified assumptions or independent modeling, limiting their ability to handle real-world scenarios. In this work, we revisit the problem from a unified perspective and identify a key issue of existing approaches, i.e., the widely adopted linear composition model in the sRGB domain fails to capture the nonlinear coupling introduced by real-world image signal processing pipelines. To address this, we introduce a learnable nonlinear superposition model that more faithfully characterizes layer interactions and improves decomposition fidelity. Building upon this formulation, we propose a generalized dual-stream interactive framework that explicitly models bidirectional dependencies between transmission and reflection through feature exchange. This framework unifies activation-, gating-, and attention-based interaction mechanisms, and is compatible with both CNN and Transformer backbones. Extensive experiments on diverse real-world benchmarks demonstrate that the proposed approach achieves superior performance with strong generalization capability. More importantly, our study reveals that reflection separation is not about undoing a linear mixture, but about learning nonlinear formation and interaction}, offering new insights into the design of principled image decomposition models. Code and models are publicly available at https://mingcv.github.io/DIRS-Page.

Evaluating vision-language models (VLMs) on medical images requires benchmarks that are clinically grounded, scalable, and controlled for evaluation confounds. Existing public benchmarks are limited in scale, manually annotated, or potentially leaked into VLM pretraining corpora. We present an automated agent-driven pipeline that generates multiple-choice VQA datasets directly from paired private radiology reports and 3D oncology imaging, producing two complementary question types: RADS-style questions deterministically derived from clinician-defined reporting schemas, and radiology report-derived questions generated by an LLM from radiologist findings and verified against the source report. Applied to four in-house cancer cohorts, the pipeline yields an instance-contamination-controlled benchmark without per-question human annotation. Zero-shot evaluation of six VLMs reveals no dominant model and substantial headroom across all cells. A blind ablation reveals that visual reliance is highly dataset-specific: liver Report-derived questions genuinely require the image, while Lung CT is essentially solvable without it - the leading closed model exceeds its sighted accuracy on Lung CT when blinded - indicating that even private clinical data does not guarantee a contamination-controlled read of visual capability. The pipeline is released as an open agent skill for in-house redeployment.

Human-object interaction (HOI) recognition is critical for automatically analyzing student behavior in complex educational environments. Although state-of-the-art (SOTA) HOI detectors perform well on benchmark datasets, their performance often degrades when deployed in real-world training environments due to domain-specific objects, occlusions, and complex visual conditions. In this paper, we introduce a diagnosis-driven framework that integrates a triplet-level HOI error taxonomy with error-factor attribution analysis for real-world educational video data. We study this problem in the context of Critical Care Air Transport Team (CCATT) mixed-reality medical training. Based on an analysis of HOI failure modes and their causes, we develop a diagnosis-informed refinement strategy for adapting pretrained HOI models to the target domain. Experiments on the CCATT dataset show that this approach improves the macro-F1 score of a pretrained CDN model from 48.6 to 90.2 through targeted refinement guided by diagnosed error factors. These results highlight the value of detailed diagnostic analysis for informing targeted adaptation of HOI models in real-world educational environments.

Vision-language models (VLMs) for autonomous driving have shown promising performance, but their ability to handle region-specific traffic rules remains underexplored, raising uncertainties about their deployment across diverse global settings. We therefore introduce GeoDrive-Bench, a novel benchmark that enables the systematic investigation of VLMs' geo-culturally grounded driving reasoning. We curated 5,053 human-validated multiple-choice QA pairs across six countries covering diverse driving cultures. Specifically, we emphasize four driving tasks: perception, prediction, planning, and region reasoning. Each question requires models to infer the correct driving behavior from visual evidence and local traffic conventions without explicit country labels. Beyond evaluation, we further design a distillation algorithm that injects region-specific traffic-rule knowledge into the internal representations of VLMs, enabling models to better align visual scene understanding with local driving policies. Experiments on nine state-of-the-art VLMs show substantial performance variations across geo-driving cultures for each task, while our proposed baseline models exhibit improved geo-cultural reasoning across regions. These results suggest that current VLMs still lack robust region-aware driving intelligence and highlight GeoDrive-Bench as a diagnostic and training-oriented testbed for deployable autonomous driving foundation models.

Satellite-derived bathymetry (SDB) from multispectral imagery is cost-effective but scales poorly across regions, especially in optically complex coastal environments. We evaluate machine learning and deep learning for transferable SDB over the 0-20 m depth range using Sentinel-2 imagery. A Random Forest baseline and four CNNs (ResNet-50, ResNet-101, EfficientNet-B4, ConvNeXt-Large) are trained on Pratas Island and selected Great Barrier Reef regions, then evaluated on spatially independent intra- and cross-regional test areas. Preserving spatial continuity during training, by keeping contiguous reef blocks rather than random patches, is the single most impactful design choice; we further introduce a Smooth Weight Function (SWF)-weighted RMSE loss that emphasizes near-surface depths. With these choices, intra-regional RMSE ranges from 1.15 to 1.92 m over 0-20 m and is as low as 0.26 m for depths <= 3 m. Random Forest degrades sharply under cross-regional transfer (RMSE 1.53 m -> 2.99-3.78 m), while the deep models stay more robust (2.46-2.98 m). On the public MagicBathyNet aerial-RGB benchmark (0-16 m) the proposed networks reach 0.19-0.22 m RMSE, outperforming a U-Net baseline and a task-specific transformer architecture with substantially fewer parameters. We further exploit multi-temporal repeat imagery: training on it broadens diversity, and median-aggregating predictions across passes at inference reduces noise from changing sun angles, atmospheric conditions, water properties, and tides. We release optimized architectures and pretrained weights to enable scalable transfer to new sites.

Video world models are a foundational generative technology for embodied AI and the Metaverse, yet existing approaches are inherently limited to a single agent observing from a single perspective. Extending these models to multi-agent settings introduces two critical challenges: data scarcity (coordinated multi-view recordings are prohibitively expensive to collect for general open-domain scenarios) and world state alignment (independently generated video streams cannot ensure that shared physical environments and events evolve consistently across views). To address these challenges, we propose MetaWorld, a novel framework that scales multi-agent video world models to open-domain environments directly from single-view videos. First, we introduce Monocular World-State Unrolling (MWSU) to explicitly decompose monocular footage into the camera operator's ego-motion and the visible subject's spatial trajectory. This camera-trajectory decomposition naturally extracts synchronized multi-agent motion data within a shared 3D space, completely bypassing the need for multi-camera setups. Second, for precise visual control, we develop the Subject-Aware World Generator to enable appearance-driven simulation conditioned on per-agent identity images. Finally, to ensure both views are grounded in the identical physical reality, we propose World-State Alignment, a per-frame inter-branch cross-attention mechanism inserted at every transformer layer of the video DiT. By jointly synchronizing the denoising process, WSA enforces both static geometric consistency and dynamic motion consistency, encouraging that the shared 3D environment and physical events remain well-aligned across both egocentric views. Extensive experiments demonstrate that MetaWorld achieves superior cross-view consistency and identity fidelity, establishing a highly scalable, physics-driven paradigm for multi-agent video world modeling.

Planning records define restrictions over geographic areas, but their source documents often provide only indirect spatial evidence rather than machine-readable boundaries. We introduce Plan2Map, a 208-case multimodal benchmark for document-grounded geospatial boundary reconstruction from UK planning records. Given only a source planning document, systems must reconstruct a valid geospatial boundary from notice text, schedules, map plates, map labels, and boundary annotations; the reference GeoJSON is held out for scoring. We propose GeoPlanAgent, a document-grounded, geospatial-tool-in-the-loop system that decomposes the task into evidence extraction, localisation, map registration, boundary segmentation, projection, and verification. On Plan2Map, GeoPlanAgent achieves 0.736 mean IoU and 0.904 median IoU, with 67.8\% of predictions at or above 0.8 IoU, substantially outperforming direct VLM-to-GeoJSON baselines. Diagnostic analysis shows that direct VLM prediction remains unreliable, while remaining errors are concentrated in localisation and map registration, and supervised boundary segmentation substantially improves pixel-level mask quality. Plan2Map provides a concrete testbed for multimodal geospatial reconstruction from public planning records. Project page: https://odeb1.github.io/Plan2Map_Project_Page/.

Spatial reasoning is fundamental to robotics, autonomy, and embodied AI, yet modern vision-language models (VLMs) remain unreliable on metric distance queries. A common assumption is that consistent predictions across viewpoints reflect geometric grounding. We test this assumption and find the opposite: leading VLMs often produce view-invariant and consistent answers even when those answers are incorrect, indicating weak coupling between predictions and viewpoint-specific visual evidence. We introduce \textbf{ViewDiag}, a controlled multi-view evaluation protocol built from Hypersim, ScanNet, and KITTI360, comprising 176 object-pair tracks across 80 scenes with 2--10 views per track. The protocol evaluates models along three axes: metric accuracy, distributional concentration, and a latent feature probe for internal collapse that distinguishes decision collapse from representation collapse. Across diverse models, we observe a consistent pattern of high prediction stability paired with substantial error, clustering in a regime characterized by strong consistency but low accuracy. \noindent These results challenge the common use of cross-view consistency as a proxy for geometric understanding. Instead, we show that stable predictions may reflect prior-driven collapse rather than evidence-sensitive reasoning. ViewDiag provides a controlled benchmark and diagnostic framework for evaluating spatial VLMs beyond accuracy alone. The code and data can be found \href{https://github.com/SDivakarBhat/Consistent_Yet_Wrong.git}{here}

Audio-visual speaker tracking aims to localize and track active speakers by leveraging auditory and visual cues, enabling fine-grained, human-centric scene understanding. This capability is essential for real-world applications such as intelligent video editing, surveillance, and human-computer interaction. However, existing datasets are largely limited to simple or homogeneous audio-visual scenes with coarse annotations. Such oversimplified settings bias evaluation toward static audio-visual co-occurrence, rather than rigorously assessing robust spatiotemporal modeling and cross-modal reasoning in complex, dynamic scenes. To address these limitations, we introduce AVTrack, a human-centric audio-visual instance segmentation (AVIS) dataset designed for dynamic real-world scenarios. AVTrack features diverse and challenging conditions, including camera motion, visual occlusions, and position changes. Evaluations of representative AVIS methods on AVTrack reveal substantial performance degradation, establishing AVTrack as a challenging benchmark for robust human-centric audio-visual scene understanding in complex environments. We further provide a simple yet effective baseline to facilitate future research. Project website: https://FudanCVL.github.io/AVTrack/

Camouflaged object detection has improved substantially, but most standard benchmarks evaluate models only on clean images. This is not realistic because real cameras often capture blur, sensor noise, weather effects, and compression artifacts. We present COD10K-C, a corruption robustness benchmark based on COD10K. It includes 8 corruption types and 5 severity levels, giving 40 conditions and 81,040 evaluation pairs in total. We evaluate three popular camouflaged object detection models, SINet-v2, PFNet, and ZoomNet, as well as a lightweight model called RobustCODLite. All models show clear performance drops on corrupted images. Motion blur and Gaussian blur cause the largest drops, with SINet-v2 losing 18.5 Dice points under motion blur. Brightness and fog are less harmful. RobustCODLite uses corruption augmentation, a frequency-prior branch, and an uncertainty-consistency loss. It retains 92.3% of its clean Dice score under corruption, compared with 87.7% for SINet-v2, 84.8% for ZoomNet, and 84.1% for PFNet. On the hardest corruptions, RobustCODLite matches or outperforms models that perform better on clean data. We will release the COD10K-C GitHub repository to support future research in robust camouflaged object detection.

In computational pathology, Whole Slide Images (WSIs) survival analysis is crucial for patient prognosis assessment, but it faces multiple technical challenges. Although the Transformer captures long-range dependencies through its self-attention mechanism, its $O(N^2)$ time complexity causes a severe computational bottleneck in large-scale WSIs graph structures. The Mamba model breaks through the Transformer's computational bottleneck with linear complexity. But, owing to Mamba's high sensitivity to the order of input data, traditional node sorting methods in Graph Mamba, such as those based on node degree or subgraph size, fail to adequately account for the topological connectivity of graph data. This inadequacy consequently restricts the performance of Mamba's sequential modeling. Moreover, its unidirectional architecture cannot leverage the bidirectional spatial structure of images. To address these challenges, this paper proposes a novel Graph Mamba survival analysis framework based on topology-aware ordering (TopoMamSurv) to adapt to the sequential sensitivity of Mamba. Our visualization experiments further confirmed that the nodes extracted through the topology-aware ordering (TAO) strategy indeed exhibit higher similarity. Furthermore, we designed a bidirectional Mamba module and integrated a Graph Convolutional Network (GCN) to achieve bidirectional spatial context modeling of images, forming a hierarchical feature learning architecture for "local aggregation - global capture." This framework effectively reconciles the contradiction between long-range dependency modeling, computational efficiency, and spatial structure utilization in WSIs analysis through its systematic design of TAO, bidirectional semantic modeling, and hierarchical feature fusion. This framework has been validated for its comprehensive performance advantage on five TCGA datasets.

While video streaming understanding has made significant strides, real-world applications, such as live sports broadcasting, autonomous driving, and multi-screen collaboration, inherently demand continuous, multi-stream interactions. However, existing benchmarks are confined to single-stream paradigms, leaving a critical gap in evaluating online, cross-stream reasoning. To bridge this, we introduce X-Stream, the first benchmark dedicated to multi-stream streaming understanding. Comprising 4,220 rigorously curated QA pairs across 932 videos, X-Stream evaluates 11 subtasks across multi-window, multi-view, and multi-device scenarios. Crucially, our dataset is constructed using a novel dual-verification pipeline that prevents over-reliance on a single stream. Furthermore, we pioneer the conceptualization of multi-modal large language models (MLLMs) as naive multiplexers, systematically evaluating their performance through the lens of Signal Multiplexing Theory. Our extensive online inference experiments reveal a stark reality: state-of-the-art MLLMs struggle significantly with concurrent streams, achieving only about 50% score and exhibiting poor proactive ability. Ultimately, X-Stream exposes the trade-off of current multiplexing schemes, providing both a practical evaluation protocol and empirical guidance for next-generation multi-stream agents.

Diffusion transformer (DiT) has been widely adopted in the generative diffusion field, advancing the denoising of query tokens through attention and Feed-Forward (\text{FFN}) layers. FFN actually acts as the key-value vocabulary for decoding visual contents where the value embeds the visual semantical knowledge. We present that focusing on critical query tokens corresponding to more complex details and encouraging the model to improve these tokens is essential for fine-grained visual generation. To this end, we propose FocusDiT, which applies a Masking scheme to focus on critical query tokens that are exclusively fed into FFN. The masked queries can retrieve visual tokens from the FFN vocabularies, and use them to decode their visual details. Extensive text-to-image experiments validate the effectiveness of token masking in enhancing generative performance.

Metal surface defect detection is critical for maintaining product quality in industrial manufacturing. However, it faces significant challenges, including limited annotated data, difficulty in identifying subtle multi-scale defects, and poor generalization across diverse scenarios. To address these issues, this paper proposes a novel Contrastive Augmented Transformer (CAT) framework for robust defect detection. CAT employs a hierarchical Swin Transformer backbone and redesigns the feature pyramid network to effectively fuse low-level textures with high-level semantics, enabling precise modeling of subtle and multi-scale defect patterns. To enhance robustness under real-world noise conditions, we propose a domain-specific droplet augmentation algorithm. Furthermore, we incorporate a hard negative mining strategy into the contrastive loss to strengthen the model's discrimination ability in ambiguous defect regions. Experimental results on the KolektorSDD2 dataset demonstrate that CAT achieves a pixel-level AUROC of 99.54%, outperforming existing methods. In addition, CAT exhibits superior generalization and robustness on three unseen datasets, including KSDD1, MTD for tile defects, and MSDD for rail surface defects, demonstrating its potential for wide-scale industrial deployment.

Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs), yet verification remains sparse: many slices are missing, making empirical failure rates unreliable. We propose SliceScorer, a deterministic scoring rule for missing-slice recommendation that combines (i) an exposure-based coverage prior to prioritize rare, under-tested regions, and (ii) a neighbor-failure prior that propagates risk from similar tested conditions. SliceScorer is deliberately simple - interpretable, auditable, and conservative - properties essential for safety-critical validation. For stress testing beyond the declared ODD, we embed SliceScorer within SliceNav, an LLM-orchestrated verification pipeline where the model interprets developer queries to select relevant operators (triage, scoring, acquisition, evaluation) and vocabulary extensions, composing verification workflows while keeping all scoring deterministic and auditable. Experiments on three driving VLMs (WiseAD, DriveMM, Cosmos-Reason2-2B) show that SliceNav surfaces high-risk coverage gaps more effectively than prior slice-discovery methods while maintaining diverse recommendations across the condition space. Ablations confirm both scoring components contribute, and qualitative analysis demonstrates end-to-end workflows from developer query to targeted evaluation.

Charts are a primary medium for conveying quantitative and relational information, yet systematically evaluating chart parsing models remains difficult. Existing benchmarks focus on narrow chart types and leave diagrammatic structures such as flowcharts and mind maps largely unaddressed, while models produce outputs in incompatible formats, and datasets rarely include the printed or hand-drawn images encountered in practice. To address these issues, we introduce ChartArena, a comprehensive bilingual benchmark covering eight chart families spanning both numeric charts and diagrammatic structures, each evaluated across three visual scenarios: digital renderings, printed photos, and hand-drawn photos. The dataset is built via a human-agent collaborative annotation pipeline with multi-stage human verification to ensure annotation reliability. To enable fair cross-model comparison, we further design a format-agnostic evaluation protocol that maps heterogeneous outputs into two canonical semantic spaces, a normalized triple view and a directed graph view, and scores them with structure-aware metrics. Through extensive evaluation of 26 leading MLLMs, we observe three consistent findings: (i) frontier proprietary models such as Gemini 3.1 Pro lead overall, yet the strongest open-source systems are rapidly closing the gap; (ii) document parsing models handle numeric charts reasonably but fall sharply behind on diagrammatic structures; and (iii) expert chart parsers remain limited to narrow chart families. Across all models, radar charts and hand-drawn scenarios stay especially challenging. These findings show that ChartArena exposes clear capability gaps and provides a unified foundation for future progress. ChartArena is publicly available at https://github.com/pspdada/ChartArena.

Placenta Accreta Spectrum (PAS) is a rare but highly dangerous obstetric disease. Early and accurate PAS diagnosis is critical for maternal health. Traditional PAS diagnosis relies on experienced doctors by analyzing the cesarean history and Magnetic Resonance Imaging (MRI) data. However, district-level hospitals often lack the expertise and resources for accurate PAS diagnosis. To address these challenges, we establish the first MRI-based PAS dataset, which includes both fine-grained segmentation and classification annotations. Meanwhile, diagnosing PAS can be significantly enhanced by segmenting lesion areas from MRI images of the uterus. To achieve automatic PAS diagnosis, we propose 3DSAMba, a novel feature learning framework for effective lesion segmentation. More specifically, we first design a 3D Segment Anything Model (SAM) and incorporate medical domain information into the model through an efficient adapter mechanism. In addition, we introduce a Multi-Level Aggregation Mamba (MLAM) to aggregate feature maps across different levels and a Fusion State Space Model (FSSM) to fuse multi-scale features from both the encoder and decoder. Finally, we apply segmentation masks to the original MRI images through element-wise multiplication, effectively isolating lesion areas for more accurate PAS diagnosis. Extensive experiments validate that our framework significantly improves the PAS diagnostic performance. To facilitate further research in PAS diagnosis, we have released the dataset and source code at https://github.com/Drchip61/PASD.

Personalized visual understanding has advanced significantly, yet existing approaches struggle to localize and extract specific concepts when input images contain multiple objects. Many prior methods rely heavily on segmentation-based supervision or exhibit poor compositional generalization, limiting their ability to accurately disentangle and manipulate individual concepts. In this work, we propose UniVerse, a Unified Modulation Framework for segmentation-free, disentangled multi-concept personalization in diffusion transformers. Our method allows for composable and decomposable concept extraction, enabling fine-grained localization and representation of target objects without explicit segmentation masks. UniVerse learns to decompose complex scenes into concept-specific representations and then compose them in a unified manner, enabling robust personalization across diverse visual contexts. Through extensive experiments on multiple benchmarks, we demonstrate that UniVerse significantly outperforms state-of-the-art baselines in both localization accuracy and visual fidelity. Qualitative and quantitative results show that our approach can precisely extract target concepts in cluttered scenes, paving the way for more flexible, interpretable, and personalized visual generation and understanding.

In fulfillment centers, diverse objects move continuously from inbound to outbound operations and can become jammed due to excessive conveyor friction, incorrect orientation, or mechanical failures. Traditional jam detection approaches rely on object detection models to identify objects, followed by tracking algorithms (such as IoU overlap and Kalman filtering) to monitor motion over time. This pipeline requires thousands of manual annotations, consuming approximately two weeks of effort, and is limited to annotated object classes. We present a training-free, object-agnostic jam detection method that eliminates the need for labeled data. Our approach uniformly samples reference points within the monitoring region when no objects are present. As objects occlude these points, we detect motion. When a sufficient fraction remains occluded beyond a temporal threshold, we classify the event as a jam. Unlike conventional point tracking--which treats occlusion as a failure case--our approach repurposes occlusion as a detection signal, monitoring whether reference points remain persistently occluded rather than tracking where they move. Our experimental evaluation on 1,069 videos demonstrates that AllTracker achieves 100.00% precision and 93.33% F1 score, significantly outperforming classical sparse tracking methods while maintaining training-free deployment. This approach offers three key advantages: (1) no training data or manual annotations, (2) object-agnostic generalization to arbitrary object types, and (3) significantly reduced development time.

While current multimodal models are proficient at open-ended visual editing, executing precise single-answer edits remains an important obstacle. To probe this challenge, we introduce PaintBench, a dynamically scalable benchmark targeting 20 fundamental precise visual editing operations across four categories: geometric transformation, structural manipulation, color change, and symbolic reasoning. Procedural generation with configurable complexity enables an effectively infinite, contamination-resistant evaluation suite, and deterministic pixel-level evaluation eliminates reliance on bias-prone judge models. Across 11 image editing models, we find overall low performance, with the current highest-performing industry leader scoring only 17.1% (mIoU). Task decomposition reveals especially challenging operation types (geometric transformation, most structural manipulation, formula-based color change) and model-specific specializations. Fine-grained benchmark diagnostics further show performance degradations induced by scene variations in object count, background complexity, color scheme, and edit-region size. To test generalization of PaintBench scores to applied task performance, we create a procedural, deterministic evaluation for data visualization editing (TinyGrafixBench) and find strong linear correlation with PaintBench scores ($R^2 = 0.91$, $p < 0.001$). Altogether, PaintBench provides a rigorous foundation for measuring and driving progress in precise multimodal visual editing.

Visual agents employ external visual tools within visual chains of thought to incorporate fine-grained evidence. While prior work has mainly studied these tools in visual search tasks, their role in more complex visual reasoning remains underexplored. In this paper, we move beyond simple visual search tasks to investigate more challenging tasks, including 3D spatial reasoning and medical visual question answering, where agents must integrate tool-acquired local evidence with the global context. We identify a {tool-use collapse phenomenon: models progressively stop using tools while still achieving higher task accuracy. Moreover, we observe a clear asymmetry: (i) completely eliminating tool use degrades performance, whereas (ii) incentivizing tool use yields only marginal gains despite substantially increasing usage. We find that vanilla training and tool-use encouragement both reduce rollout diversity, explaining why higher tool use does not yield stronger reasoning performance. Motivated by these findings, we add an entropy regularization term to encourage diverse rollout exploration, achieving the best performance despite gradually declining tool usage. Overall, our findings suggest a training-time view of tools as scaffolding, where broader exploration over language generation and visual tool invocation improves reasoning despite tool-use collapse. Project page: https://scaffolded-exploration.github.io

Real-world images rarely suffer from a single degradation, and the order in which degradations are removed substantially affects the final restoration quality, motivating agent-based image restoration (IR), where a vision-language model schedules a pool of pre-built restoration-experts. However, existing training-based agents require $\mathcal{O}((N^{\mathbf{D}})^{2})$ restoration-expert calls per image to construct the Optimal Restoration-action Trajectory Dataset (ORTD), where $N^{\mathbf{D}}$ denotes the number of degradation types in the universe $\mathbf{D}$, and couple agent training to a fixed restoration-expert pool, preventing extension to newly introduced restoration-experts without full retraining. To overcome these efficiency and extensibility bottlenecks, we propose \textbf{DiTTo}, a novel order-aware image restoration agent framework consisting of the DiTTo Simulator and the DiTTo Agent. The DiTTo Simulator combines $\cup$S-IR for single-step restoration-action simulation and AiO-IQA for per-action quality prediction, reducing ORTD construction to $\mathcal{O}(N^{\mathbf{D}})$ simulator calls per image; the DiTTo Agent is trained by SFT on the simulator-generated ORTD, followed by \textbf{Order-aware Restoration Alignment (ORA)} that aligns degradation identification, restoration-action-ordering, and output format along independent axes. This enables \textbf{plug-and-play scalable extensibility}: adding a new restoration-expert requires updating only the lightweight ORA stage. On the MiO-100 evaluation set with up to five concurrent degradations, our DiTTo Agent achieves state-of-the-art multi-degradation restoration quality among previous agent-based IR methods.

Colo-segment recognition in colonoscopy videos is a key requirement for many downstream tasks, but existing automatic recognition methods only use colonoscopy images without fully exploiting the use of temporal information, leading to poor performance. Additionally, relevant public video-based datasets are in scarcity. To tackle this problem, we curate and release a labeled dataset specifically for the task of colo-segment recognition. In addition, we propose a two-stage deep learning-based framework, Colo-Segment Recognition via SpatioTemporal Network (ST-ColoNet), for the task of colo-segment recognition from colonoscopy videos which includes the Colorlaus module that uses metric learning to optimize edge-mediated spatial feature extraction, as well as the Full-Temp module which combines three self-attention patterns to better approximate full self-attention on long colonoscopy sequences and optimize temporal feature aggregation. Through extensive ablation experiments, we show that our framework is capable of achieving state-of-the-art performance on the task of colo-segment recognition, achieving an accuracy of 81.0% and F1-score of 70.7%, which is a tremendous improvement over state-of-the-art methods.

X-ray computed tomography (XCT) is widely used for non-destructive testing of Nomex honeycomb structures in aerospace manufacturing, but industrial inspection still relies heavily on manual interpretation and supervised models trained on limited labeled data. This work introduces NL-MambaXCT, a Mamba-based framework that combines self-supervised masked image modelling with a Nested Learning (NL) formulation for automated, label-efficient defect classification from production XCT slices. The backbone is a four-stage 2D encoder with RegNet convolutional blocks in the early stages and Mamba-based sequence mixing with attention in the deeper stages. It is pretrained by masked image modelling on 19,961 unlabeled industrial XCT slices and fine-tuned on 2,000 relabeled Nomex XCT slices split by production order. NL is instantiated through two-timescale parameter dynamics: selected projections maintain slow exponential-moving-average traces alongside fast weights, while a deep-momentum optimizer introduces an additional slow parameter-update trajectory. On the held-out test set, the MIM-pretrained NL-MambaXCT model achieves 96.91% accuracy and 96.8% macro F1, outperforming CNN, attention, and single-timescale Mamba baselines by 3.11--10.31 percentage points in accuracy. The results suggest that combining masked self-supervision with NL-style fast/ slow learning dynamics is a promising strategy for robust defect classification in Nomex honeycomb XCT inspection.

We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete point clouds directly from a single RGB image, with no need for 3D inputs. Additionally, we introduce a transformer-based Point-to-Point (P2P) refinement module that uses self- and cross-attention between point tokens and image features to iteratively refine the coarse I2P output. The I2P module enables the image encoder to learn rich geometric representations, while the P2P module progressively recovers fine-grained details. Unlike existing multimodal methods that rely on auxiliary losses or fusion modules, our explicit I2P task provides a strong, geometry-aware prior based on images alone. Extensive experiments on ShapeNet-ViPC demonstrate state-of-the-art completion performance with a 12.3% relative Chamfer Distance improvement over prior methods. Code is available at: https://github.com/AzharSindhi/I2PRef.git

Cesarean Scar Defect (CSD) is one of the most prevalent complications following cesarean delivery. Transvaginal ultrasonography is widely used for primary CSD screening. Accurate determination of CSD outline and dimensions is crucial for treatment. However, CSDs are frequently overlooked by sonographers due to small size and irregular morphology, suboptimal image quality, and limited clinical awareness in resource-constrained settings. Despite artificial intelligence advances in medical imaging, no public dataset exists for transvaginal ultrasound CSD segmentation. To address this gap, we present a comprehensive CSD dataset comprising 1,111 images and 16 videos, yielding 501 positive samples with confirmed CSD and precise pixel-level manual annotations. Annotations are performed following standardized clinical guidelines through collaboration between experienced sonographers and trained PhD students. This work provides high-quality benchmark resources for advancing medical image segmentation algorithms and promoting clinical innovation. Ultimately, improved CSD diagnosis and subsequent treatment strategies can enhance the quality of life in women of reproductive age, representing significant value for both medical research and clinical practice.

Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typically follow either a two-stage paradigm that combines kinematic motion generation with physics-based tracking, or an end-to-end imitation-learning paradigm that directly generates actions from text. However, the former suffers from the inherent domain shift between kinematic generation and physics-based tracking, while the latter struggles with the substantial modality gap between textual commands and low-level actions, limiting effective semantic alignment. Notably, humanoid states encode rich motion dynamics that are more semantically aligned with textual descriptions than low-level actions, making them a natural basis for deriving behavioral intent. Building upon this insight, we propose MIND, a novel end-to-end diffusion framework for text-driven physics-based humanoid control that leverages behavioral intent as a semantic bridge between textual commands and low-level actions. At its core, MIND introduces a multi-scale intent diffusion mechanism, where a holistic intent predictor captures global behavioral dynamics to guide overall behavior synthesis, while an immediate intent predictor provides step-wise, fine-grained signals for local behavior refinement at each diffusion step. This hierarchical intent formulation imposes a structured inductive bias for humanoid control, improving semantic alignment and behavioral naturalness. Furthermore, MIND encodes humanoid states into a latent space to enable more effective semantic intent modeling. Extensive experiments demonstrate that MIND outperforms existing methods and synthesizes coherent, physically plausible, and semantically aligned humanoid behaviors from text commands. Project page: https://binlee26.github.io/MIND_page.

Monocular 3D shape recovery is fundamental to geometric understanding, yet achieving robust generalization across arbitrary viewpoints and unseen object categories remains a significant challenge. In this paper, we present a generalizable deformation learning framework that reconstructs 3D objects by explicitly deforming a category-level shape template to match the target observation. To address complex shape variations between the template and the target, we introduce a geometry-guided feature modeling mechanism. This process first enriches foundation features with template topology to yield a geometry-aware representation, which is then explicitly correlated with the target observation to guide precise deformation. Furthermore, to bridge the disparity between the fixed template and arbitrary target views, we propose a view-adaptive feature aggregation module. This module leverages multi-view template features and their corresponding camera poses to enrich the canonical template representation, ensuring robust feature alignment regardless of the target's perspective. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods in handling large shape variations and diverse viewpoints, exhibiting strong generalization to novel categories and effectively supporting downstream real-world dexterous robotic manipulation tasks. Project homepage: https://GODeform.github.io/

Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the fact that real-world object motion unfolds in three-dimensional space, while video observations provide only partial, view-dependent projections of such dynamics. To address these issues, we propose OrthoPhys, a two-stage framework that leverages orthogonal-view geometry guidance to enforce physical plausibility. Instead of directly generating unstructured 2D videos, our first stage generates synchronized, four-view orthogonal videos of the foreground dynamics. By incorporating a geometry-enhanced attention mechanism across these orthogonal views, this stage effectively enforces 3D spatial coherence and implicitly grounds the motion in physical attributes. In the second stage, these physically consistent orthogonal foregrounds serve as rigid guidance to synthesize the final complete video, seamlessly learning the interaction between foreground dynamics and the background context. To support this orthogonal-view training paradigm, we construct PhysMV, a dataset containing 40K scenes, each consisting of four orthogonal viewpoints, resulting in a total of 160K video sequences. Extensive experiments demonstrate that OrthoPhys significantly improves physical realism and spatial-temporal coherence over existing video generation methods. Project page: https://anonymous.4open.science/w/Phys4D/.

Clinicians trace cephalometric radiographs following a structured anatomical workflow, yet no prior system encodes this into computation. We present a five-phase anatomy-guided pipeline producing confidence-weighted spatial priors that shape HRNet-W32 training, achieving 1.04 mm mean radial error on 25 landmarks across 1,502 radiographs from 7+ imaging devices. A training x inference prior matrix isolates the mechanism: anatomical priors maintain a 1% validation-to-test gap versus 88% without priors (1.94 mm), despite identical validation convergence. The matrix establishes that all trained models are inference-independent, the expanded architecture alone provides no benefit, random priors yield partial but unstable improvement (1.72 mm), and only image-specific anatomically correct priors produce the 1.04 mm result -- functioning as a training-time regularizer requiring no automated prior generation at deployment. Five-fold cross-validation (p=0.0015), patient-level permutation testing (p<0.0001, n=151), quantified Grad-CAM analysis (88% vs. 74% in-zone activation, p<0.001), and clinical measurement validation (skeletal classification kappa=0.79-0.84, zero Class II<->III reversals, ICC>0.95) provide converging evidence. Cross-domain experiments on echocardiography, cervical spine, and hand radiography support the hypothesis that prior effectiveness scales with the spatial entropy of the landmark distribution.

Digital pathology archives increasingly contain multiple whole-slide images (WSIs) per case, capturing spatially distinct tumor regions and reflecting intrinsic morphological heterogeneity. However, most existing approaches rely on a single pathologist-selected slide, thereby discarding potentially informative evidence distributed across the remaining WSIs. To date, no autonomous framework has been proposed for comprehensive multi-WSI case processing. Here, we present an unsupervised framework for case-level analysis that integrates information from all available slides within a case. Rather than relying on a single designated slide, the proposed approach constructs case-level representations by selectively distilling informative patches across WSIs. We introduce Clustering-Based Redundancy-Reduced Instance Sampling for Pathology (CRISP), a two-stage framework that first reduces redundancy within individual WSIs and subsequently applies clustering-based sampling to select a compact yet representative set of patches for the entire case. The resulting patch set captures case-level heterogeneity while avoiding exhaustive processing of gigapixel images, and directly serves as a retrieval index. Using two Mayo Clinic breast cancer datasets for diagnosis and treatment planning, we demonstrate that CRISP consistently matches or surpasses the current standard practice of combined model and pathologist slide selection for patient/case search and retrieval. By automating case-level processing and eliminating subjective WSI selection, CRISP potentially enables the exploitation of clinically relevant information distributed across multiple WSIs that is currently overlooked.

Self-supervised learning (SSL) has emerged as a promising paradigm for addressing the annotation bottleneck in medical imaging by learning representations from unlabeled data. However, its effectiveness depends heavily on the design of the pretext task and its alignment with the downstream clinical-objectives. We present a systematic, task-oriented review of SSL in medical imaging, examining how different pretext-task formulations influence performance across classification, segmentation, detection, and other tasks. Following PRISMA guidelines, we analyze 75 studies published between 2017 and 2025 and organize them into four paradigms: contrastive, non-contrastive and predictive, generative and reconstruction-based, and hybrid learning. Rather than cataloguing methods by architecture, we map each paradigm to the downstream objectives it best supports. Our analysis shows there is no universally optimal SSL strategy; instead, performance is governed by the alignment between the pretext task, the imaging modality, and the target task. Contrastive methods learn global discriminative features and align well with classification, but may overlook subtle pathological patterns. Generative and spatial prediction-based approaches better preserve local anatomical structure, making them more suitable for segmentation and other dense prediction tasks, while hybrid methods offer the most balanced performance. We further show that modality-specific design is critical and that SSL provides its greatest benefit in low-label and few-shot regimes. Finally, we distill these findings into practical design guidelines and outline open challenges, including pathology-aware pretext task design, resource-efficient training for high-dimensional data, and standardized evaluation protocols. This work offers practical guidance for designing more effective and clinically relevant SSL frameworks in medical imaging.

The Flooded Road Environments Dataset (FRED) is, to our knowledge, the first multi-modal autonomous driving dataset specifically targeting the collection of data from scenarios involving water hazards on the road. The dataset contains images from a 2.3 MP FLIR Blackfly USB3 camera, 64-beam 360 degree point clouds from an Ouster OS1-64 LiDAR, and data from an iXblue ATLANS-C IMU corrected by a Geoflex RTK GNSS, from five separate locations captured both during and after flooding events. The data has been released in two formats: a KITTI-style format for easy integration with existing data tools, and the RTMaps format for direct replay of the vehicle's data capture. We provide semantic labels to enable the training and evaluation of both single-sensor and sensor-fusion methods for water hazard detection. Position and velocity, as well as data captured under dry conditions, are provided to enable the development of location-based detection methods that may incorporate maps, and to evaluate other tasks such as localisation and SLAM.

Fetal ultrasound is the cornerstone of antenatal care, and accurate recognition of a small set of standard anatomical planes underpins biometry, growth surveillance, and detection of structural anomalies. Deep learning classifiers now match or exceed expert accuracy on curated benchmarks, but most remain opaque and miscalibrated, leaving clinicians without the calibrated confidence or faithful explanations needed for safe decision support. We systematically reviewed 78 studies published between January 1, 2015 and April 30, 2026 that paired automated fetal plane classification with explainability or predictive uncertainty quantification, following PRISMA 2020. Pooled balanced accuracy across six standard planes was 0.93 (95% CI 0.91 to 0.95), but only 19 studies (24%) reported calibration and 14 (18%) reported selective prediction. We propose CALIB-XFUS, a 22-item reporting framework that operationalises calibration, explanation faithfulness, and fairness for regulated fetal ultrasound artificial intelligence. The framework spans six domains: clinical task and indication for use; dataset provenance and representativeness; model and training pipeline; calibration and selective prediction; explanation faithfulness and clinician validation; and post-market surveillance. We argue that uncertainty-calibrated, faithfully explained, and fairness-audited fetal ultrasound AI is now both technically feasible and regulatorily expected under the FDA Good Machine Learning Practice principles and the EU AI Act high-risk obligations.

Text-to-image models now generate graphic design at production scale, yet their supervision still comes primarily from photo-style preference datasets with a single overall verdict per comparison. Designers evaluate designs along several distinct axes (e.g., typography, layout, color harmony) that a single preference label collapses. We release \emph{TASTE} \textit{(Typography, Aesthetics, Spatial, Tone, Etc.)}, a multi-dimensional preference dataset in which two disjoint cohorts of five professional designers each ranked outputs from four current text-to-image models across nine criteria along with per-image hallucination flags. We pair the dataset with two contributions. First, a criterion-agnostic signal-validation framework based on Kendall's $τ$, majority-vote probability, and Condorcet cycles against exact iid-uniform nulls; the analysis reveals significant but moderate designer agreement, with every TASTE criterion rejecting the random-rater null. Second, we benchmark preference models on TASTE and find that off-the-shelf VLM judges and dedicated T2I scorers fail to reach majority agreement with the designer panel, while a small MLP head trained directly on TASTE substantially narrows the gap to the single-rater ceiling, setting a baseline for future TASTE-trained preference models.

We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous research-and-engineering by LLM-driven agents on a single professionally annotated UAV corpus. The same image set and the same per-class AP_50 metric are evaluated under two protocols. The VLM Track measures whether a fixed VLM can localise domain-specific damage from one image and one short prompt under a unified prompting, decoding and parsing pipeline. The Agent Track measures whether an autonomous agent, given only a written task brief, a small exploratory slice and a fixed interaction budget, can search the public web, adapt pretrained components, write training and inference code, and submit predictions through a scalar-feedback oracle on a hidden holdout. We benchmark a broad pool of closed-source frontier models and open-source VLMs together with several frontier LLM-driven agents. Both routes remain far from reliable performance in this wild setting: closed-source frontier models lead the VLM leaderboard but still leave more than half of the metric on the table; open-source grounders plateau well below them, and newer generations or reasoning-style variants do not consistently improve grounding; small targets collapse for every open-source model; agents lag the strongest VLM despite richer affordances, and several fail to land a valid submission within the budget. We release the code and data at https://anonymous.4open.science/r/wildroadbench-0607 to support reproducible follow-up research.

Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However, evaluating such frontier models remains a fundamental challenge. Existing benchmarks are limited in scope and data diversity, and rely on rigid evaluation pipelines, preventing systematic and reliable assessment of modern MSAV models. To bridge these gaps, we introduce MSAVBench, the first comprehensive benchmark and adaptive hybrid evaluation framework for multi-shot audio-video generation. Our benchmark spans four key dimensions, video, audio, shot, and reference, covering diverse task settings, varying shot counts of up to 15, and challenging non-realistic scenarios. Our evaluation framework improves robustness through an adaptive self-correction mechanism for shot segmentation, instance-wise rubrics for subjective metrics, and tool-grounded evidence extraction for complex judgments. Furthermore, MSAVBench achieves high alignment with human judgments, reaching a Spearman rank correlation of 91.5%. Our systematic evaluation of 19 state-of-the-art closed- and open-source models shows that current systems still struggle with director-level control and fine-grained audio-visual synchronization, while modular or agentic generation pipelines offer a promising path toward narrowing the gap between open- and closed-source models. The benchmark data and evaluation code are publicly available at https://github.com/ali-vilab/MSAVBench.

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM answers fine-grained questions more accurately when conditioned on evidence-centered crops than on the corresponding full images, suggesting that many failures stem from difficulty to focus on relevant evidence rather than insufficient local recognition ability. Motivated by this observation, we propose Vision-OPD (Vision On-Policy Distillation), a regional-to-global self-distillation framework that transfers the model's own privileged regional perception to its full-image policy. Vision-OPD instantiates two conditional policies from the same MLLM: a crop-conditioned teacher and a full-image-conditioned student. The student generates on-policy rollouts, and Vision-OPD minimizes token-level divergence between the teacher and student next-token distributions along these rollouts. This enables the model to internalize the benefit of visual zooming without external teacher models, ground-truth labels, reward verifiers, or inference-time tool use. Experiments on multiple fine-grained visual understanding benchmarks show that Vision-OPD models achieve competitive or superior performance against much larger open-source, closed-source, and "Thinking-with-Images" agentic models. The code is available at https://github.com/VisionOPD/Vision-OPD

Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and fine-grained glyph-level structure. Prior methods often improve this ability through architecture-specific modules or encoder modifications, which complicate deployment across foundation models. We study text rendering as a post-training preference-alignment problem and propose TextAlign, a non-invasive framework that keeps the generator architecture unchanged. The key component is a hierarchical vision-language model (VLM)-based reward that decomposes rendering errors into global, word, and glyph levels, then converts binary defect judgments into a scalar preference signal. The resulting signal supports both Group Relative Policy Optimization (GRPO) and Direct Preference Optimization (DPO). Experiments on FLUX.1-dev and Z-Image-Turbo show consistent gains in OCR-based text accuracy without degrading general generation quality. Compared with strong foundation and text-rendering baselines, including SD3.5, Qwen-Image, AnyText, and TextDiffuser, these results indicate that reward design offers a scalable alternative to model redesign for improving text rendering.

In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information. The dominant connector-based paradigm projects visual features into textual sequence, enabling unified multimodal alignment and reasoning within a generative architecture. However, our experiments reveal two key limitations: (1) Although visual information serves as the core evidential modality in MLLMs, it is treated on par with textual tokens, diminishing the unique contribution of the visual modality; (2) As generation length increases, particularly within a limited context window, the model's dependence on visual information progressively weakens, resulting in deteriorated vision-language alignment and reduced consistency between generated content and visual semantics. To address these challenges, we propose the Vision Inference Former (VIF), a lightweight architectural module that establishes a direct bridge between pure visual representations and the model's output space. Specifically, VIF continuously injects visual semantics throughout the decoding phase of the inference process, ensuring that the model remains firmly grounded in visual content during generation. We conduct experiments on 14 benchmark tasks covering general reasoning, OCR, table understanding, vision-centric evaluation, and hallucination. Experimental results show that VIF consistently improves model performance across diverse architectures while introducing minimal additional overhead. The code for this work is available at https://github.com/Dong-Xinpeng/VIF.

The generation of production-ready quad-dominant meshes is a cornerstone of modern 3D content creation. Generating anisotropic quad-dominant meshes from point clouds is challenging, as existing methods are typically limited to producing either pure triangular meshes or pure quadrilateral meshes with isotropic densities. In this paper, we present QuadLink, a unified framework consisting of three stages for quad-dominant mesh generation by linking points into structured faces. QuadLink formulates polygonal mesh generation as a hybrid centroid-conditioned vertex linking model: it first predicts a unified set of anchors (vertices and face centroids), then learns centroid-conditioned links that associate vertices with face centroids, and finally assembles polygonal faces with a quad-first strategy guided by robust geometric verification strategies. This link-based formulation enables efficient generation of sparse and anisotropic quad-dominant meshes with coherent edge flow and meanwhile supporting hybrid polygonal topology. To construct training data for this model, we further introduce a Tri-to-Quad Operator that converts artistic triangle meshes into quad-dominant training data via global merge selection. Extensive experiments show that QuadLink produces production-ready quad-dominant meshes from point clouds and achieves improved geometric fidelity and topological quality compared to prior baselines. Our method natively supports hybrid polygonal topology, generalizing to arbitrary n-gon meshes without architectural changes.

Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and substantial computational overhead. We propose Video-OPD, an efficient post-training framework for TVG inspired by recent advances in on-policy distillation. Video-OPD optimizes trajectories sampled directly from the current policy, thereby preserving alignment between training and inference distributions, while a frontier teacher supplies dense, token-level supervision via a reverse KL divergence objective. This formulation preserves the on-policy property critical for mitigating distributional shift, while converting sparse, episode-level feedback into fine-grained, step-wise learning signals. Building on Video-OPD, we introduce Teacher-Validated Disagreement Focusing (TVDF), a lightweight training curriculum that iteratively prioritizes trajectories that are both teacher-reliable and maximally informative for the student, thereby improving training efficiency. Empirical results demonstrate that Video-OPD consistently outperforms GRPO while achieving substantially faster convergence and lower computational cost, establishing on-policy distillation as an effective alternative to conventional reinforcement learning for TVG.

In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions. Our method is built upon the X-Restormer baseline, which captures both channel-wise global dependencies and spatially-local structural information through its dual-attention design (Multi-DConv Head Transposed Attention and Overlapping Cross-Attention), augmented with the spatially-adaptive input scaling mechanism from Restormer-Plus. We adopt a two-stage training strategy with dual-model ensemble inference. In the first stage, Model B is trained from scratch on a large-scale diverse dataset randomly sampled from the FoundIR training set (approximately 800 GB out of 4.84 TB), covering five degradation types: blur, haze, rain, snow, and composite conditions such as co-occurring rain and haze. In the second stage, Model A is fine-tuned on the WeatherStream dataset (rain and snow splits) using Model B's final checkpoint as pretrained initialization, enabling efficient domain adaptation with a substantially smaller dataset. To better preserve structural details during training, we propose a novel Gradient-Guided Edge-Aware (GGEA) Loss, which applies Sobel operators to the ground-truth image to construct a spatially adaptive weight map that assigns higher supervision to edge and high-frequency regions. This is incorporated alongside L1 and Multi-Scale SSIM losses in a unified training objective. At inference time, predictions from the two models are fused via a weighted average, out = 0.4 x outA + 0.6 x outB, where the higher weight assigned to Model B reflects its stronger generalization ability from large-scale pretraining. With these strategies, our proposed method successfully ranks 1st in the challenge.

Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructions. However, these models often struggle with complex instructions involving combinatorial editing operations or inter-step dependencies. This difficulty stems from the limitations of two canonical paradigms: (1) single-turn editing, which attempts to apply all instructed edits in one pass, often fails to parse the complex instruction accurately and causes undesired edits; and (2) sequential editing can decompose the task into simpler steps but suffers from compounding errors introduced by the sequential execution, leading to low-fidelity results. To derive a robust solution for complex image editing, we examine editing behaviors of different paradigms under a unified in-context editing framework, and study how the benefits of sequential decomposition can be balanced against its error-accumulation drawbacks. We further develop a synthetic data pipeline that constructs editing tasks of varying instruction complexity, allowing us to curate a large-scale editing dataset with high-quality decomposed sequences. By finetuning on synthetic data, we discovered that with properly designed editing paradigms, sequential decomposition yields robust improvements even as task complexity increases. Furthermore, the decomposition skills learned from synthetic tasks can transfer to real images by co-training with real-world editing data, demonstrating the promise of sim-to-real generalization for tackling complex image editing across broader domains.

The Platonic Representation Hypothesis suggests that neural networks trained on different modalities (e.g., text and images) align and eventually converge toward the same representation of reality. If true, this has significant implications for whether modality choice matters at all. We show that the experimental evidence for this hypothesis is fragile and depends critically on the evaluation regime. Alignment is measured using mutual nearest neighbors on small datasets ($\approx$1K samples) and degrades substantially as the dataset is scaled to millions of samples. The same behavior is observed beyond text-image, for text-audio and text-video alignment. The alignment that remains between model representations reflects coarse semantic overlap rather than consistent fine-grained structure. Moreover, the evaluations in Huh et al. are done in a one-to-one image-caption setting, a constraint that breaks down in realistic many-to-many settings and further reduces measured alignment. We also find that the reported trend of stronger language models increasingly aligning with vision does not appear to hold for newer models. Overall, our findings suggest that the current evidence for cross-modal representational convergence is considerably weaker than subsequent works have taken it to be. Models trained on different modalities may learn equally rich representations of the world, just not the same one.

Recently impressive performance has been achieved in Concept Bottleneck Models (CBM) by utilizing the image-text alignment learned by a large pre-trained vision-language model (i.e. CLIP). However, there exist two key limitations in concept modeling. Existing methods often suffer from pre-training biases, manifested as granularity misalignment or reliance on structural priors. Moreover, fine-tuning with Binary Cross-Entropy (BCE) loss treats each concept independently, which ignores mutual exclusivity among concepts, leading to suboptimal alignment. To address these limitations, we propose Concept-wise Attention for Fine-grained Concept Bottleneck Models (CoAt-CBM), a novel framework that achieves adaptive fine-grained image-concept alignment and high interpretability. Specifically, CoAt-CBM employs learnable concept-wise visual queries to adaptively obtain fine-grained concept-wise visual embeddings, which are then used to produce a concept score vector. Then, a novel concept contrastive optimization guides the model to handle the relative importance of the concept scores, enabling concept predictions to faithfully reflect the image content and improved alignment. Extensive experiments demonstrate that CoAt-CBM consistently outperforms state-of-the-art methods. The codes will be available upon acceptance.

Existing lip-sync deepfake detectors rely on pixel artifacts or audio-visual correspondence, and both fail under generator or language shift because the features they learn are tied to the training distribution. We take a different approach. Authentic lip motion is constrained by tissue mechanics and neuromuscular bandwidth; current generators typically do not impose these constraints, producing trajectories with elevated variance in velocity, acceleration, and jerk that real speech does not exhibit. We exploit this signal, which we term temporal lip jitter, by computing kinematic statistics from 64 perioral landmarks over short sliding windows and feeding them into a lightweight three-branch network. The model uses only landmark coordinates: no pixels, no audio, and no voiceprint data. We train only on English data and test in a zero-shot setting on five unseen generators and seven languages.

Real-world image dehazing (RID) aims to remove haze-induced degradation from real scenes. This task remains challenging due to non-uniform haze distribution, spatially varying color shifts, and the scarcity of paired real hazy-clean data. In PRISM, we propose Proximal Scattering Atmosphere Reconstruction (PSAR), a physically structured framework that jointly reconstructs the clear scene and scattering variables under the atmospheric scattering model, making the restoration process more interpretable in complex real-world conditions. To bridge the synthetic-to-real gap, we design an online non-uniform haze synthesis pipeline and a Selective Self-Distillation Adaptation (SSDA) scheme for unpaired real-world scenarios, which enables the model to selectively learn from high-quality perceptual targets while leveraging its intrinsic scattering understanding to audit residual haze and guide self-refinement. Experiments on real-world benchmarks demonstrate that PRISM achieves competitive performance on RID tasks.

Decreasing sequence length is a common way to accelerate transformers, but prior token reduction work often targets classification and reports proxy metrics rather than end-to-end latency. For semantic segmentation, token reduction is further constrained by the need to reconstruct dense, pixel-aligned features, and on modern accelerators the overhead of computing merge maps can erase expected gains. We propose Mutual Pair Merging (MPM), a training-free token aggregation module that forms mutual nearest-neighbor pairs in cosine space, averages each pair, and records a merge map enabling a gather-based reconstruction before the decoder so that existing segmentation heads can be used unchanged. MPM introduces no learned parameters and no continuous compression knob (no keep-rate or threshold). The speed-accuracy trade-off is set by a discrete insertion schedule. We benchmark end-to-end latency on an NVIDIA H100 GPU (with and without FlashAttention-2) and a Raspberry Pi 5 across standard segmentation datasets. On ADE20K, MPM reduces per-image latency by up to 60% for ViT-Tiny on Raspberry Pi 5, and increases throughput by up to 20% on H100 with FlashAttention-2 while keeping the mIoU drop below 3%. These results suggest that simple, reconstruction-aware, training-free token merging can translate into practical wall-clock gains for segmentation when overhead is explicitly accounted for.

We study how different visual information sources contribute to human decision making in dynamic visual environments. Using Atari-HEAD, a large-scale Atari gameplay dataset with synchronized eye-tracking, we introduce a controlled ablation framework as a means to reverse-engineer the contribution of peripheral visual information, explicit gaze information in the form of gaze maps, and past-state information from human behavior. We train action-prediction networks under six settings that selectively include or exclude these information sources. Across 20 games, peripheral information shows by far the strongest contribution, with median prediction-accuracy drops in the range of 35.27-43.90% when removed. Gaze information yields smaller drops of 2.11-2.76%, while past-state information shows a broader range of 1.52-15.51%, with the upper end likely more informative due to reduced peripheral-information leakage. To complement aggregate accuracies, we cluster states by true-action probabilities assigned by the different model configurations. This analysis identifies coarse behavioral regimes, including focus-dominated, periphery-dominated, and more contextual decision situations. These results suggest that human decision making in Atari depends strongly on information beyond the current focus of gaze, while the proposed framework provides a way to estimate such information-source contributions from behavior.

Camera-based 3D Semantic Scene Completion (SSC) is a critical task for autonomous driving and robotic scene understanding. It aims to infer a complete 3D volumetric representation of both semantics and geometry from a single image. Existing methods typically focus on end-to-end 2D-to-3D feature lifting and voxel completion. However, they often overlook the interference between high-confidence visible-region perception and low-confidence occluded-region reasoning caused by single-image input, which can lead to feature dilution and error propagation. To address these challenges, we introduce an offline Visible Region Label Extraction (VRLE) strategy that explicitly separates and extracts voxel-level supervision for visible regions from dense 3D ground truth. This strategy purifies the supervisory space for two complementary sub-tasks: visible-region perception and occluded-region reasoning. Building on this idea, we propose the Visible-Occluded Interactive Completion Network (VOIC), a novel dual-decoder framework that explicitly decouples SSC into visible-region semantic perception and occluded-region scene completion. VOIC first constructs a base 3D voxel representation by fusing image features with depth-derived occupancy. The visible decoder focuses on generating high-fidelity geometric and semantic priors, while the occlusion decoder leverages these priors together with cross-modal interaction to perform coherent global scene reasoning. Extensive experiments on the SemanticKITTI and SSCBench-KITTI360 benchmarks demonstrate that VOIC outperforms existing monocular SSC methods in both geometric completion and semantic segmentation accuracy, achieving state-of-the-art performance.

Geo-Foundation Models (GFMs) have been evaluated across diverse Earth observation task including multiple domains and have demonstrated strong potential of producing reliable maps even with sparse labels. However, benchmarking GFMs for Cryosphere applications has remained limited, primarily due to the lack of suitable evaluation datasets. To address this gap, we introduce \textbf{Cryo-Bench}, a benchmark compiled to evaluate GFM performance across key Cryospheric components. Cryo-Bench includes debris-covered glaciers, glacial lakes, sea ice, and calving fronts, spanning multiple sensors and broad geographic regions. We evaluate 14 GFMs alongside UNet and ViT baselines to assess their advantages, limitations, and optimal usage strategies. With a frozen encoder, UNet achieves the highest average mIoU of \textbf{66.38}, followed by TerraMind at \textbf{64.02} across five evluation dataset included in Cryo-Bench. In the few-shot setting (10\% input data), GFMs such as DOFA and TerraMind outperform UNet, achieving mIoU scores of \textbf{59.53}, \textbf{56.62}, and \textbf{56.60}, respectively, comapred to U-Net's 56.60. When fully finetuning GFMs, we observe inconsistent performance across datasets and models. However, tuning learning rate along with finetuning substantially improves GFM performance. For example, evaluation on two representative datasets (GLID and CaFFe) shows an average relative improvement of \textbf{12.77\%}. Despite having minimal Cryosphere representation in their pretraining data, GFMs exhibit notable domain adaptation capabilities and produce meaningful results across tasks. Based on our findings, We recommend encoder fine-tuning with hyperparameter optimization optimization to achieve the best possible performance, while using frozen encoders when users need quick results without extensive experimentation.(\href{https://github.com/Sk-2103/Cryo-Bench}{GitHub}).

High-resolution content creation is rapidly emerging as a central challenge in both the vision and graphics communities. Images serve as the most fundamental modality for visual expression, and content generation that aligns with the user intent requires effective, controllable high-resolution image manipulation mechanisms. However, existing approaches remain limited to low-resolution settings, typically supporting only up to 1K resolution. In this work, we introduce the task of high-resolution image editing and propose a test-time optimization framework to address it. Our method performs patch-wise optimization on high-resolution source images, followed by a fine-grained detail transfer module and a novel synchronization strategy to maintain consistency across patches. Extensive experiments show that our method produces high-quality edits, facilitating high-resolution content creation.

While automated sleep staging has achieved expert-level accuracy, its clinical adoption is hindered by a lack of auditable reasoning. We introduce SleepVLM, a rule-grounded vision-language model (VLM) that stages sleep from multi-channel polysomnography (PSG) waveform images and generates clinician-readable rationales based on American Academy of Sleep Medicine (AASM) scoring criteria. Utilizing waveform-perceptual pre-training and rule-grounded supervised fine-tuning, SleepVLM achieved Cohen's kappa of 0.767 on a held-out test set (MASS-SS1) and 0.743 on an external cohort (ZUAMHCS), matching state-of-the-art performance. Independent expert evaluation by two trained sleep technologists further validated the model's reasoning quality, with mean scores of 3.75-3.96 out of 5 across factual accuracy, evidence comprehensiveness, and logical coherence on both datasets. By coupling competitive performance with transparent, rule-based explanations, SleepVLM may improve the trustworthiness and auditability of automated sleep staging in clinical workflows. To facilitate further research in interpretable sleep medicine, we release MASS-EX, a novel expert-annotated dataset.

In this paper, we introduce NAS3R, a self-supervised feed-forward framework that jointly learns explicit 3D geometry and camera parameters with no ground-truth annotations and no pretrained priors. During training, NAS3R reconstructs 3D Gaussians from uncalibrated and unposed context views and renders target views using its self-predicted camera parameters, enabling self-supervised training from 2D photometric supervision. To ensure stable convergence, NAS3R integrates reconstruction and camera prediction within a shared transformer backbone regulated by masked attention, and adopts a depth-based Gaussian formulation that facilitates well-conditioned optimization. The framework is compatible with state-of-the-art supervised 3D reconstruction architectures and can incorporate pretrained priors or intrinsic information when available. Extensive experiments show that NAS3R achieves superior results to other self-supervised methods, establishing a scalable and geometry-aware paradigm for 3D reconstruction from unconstrained data. Code and models are publicly available at https://ranrhuang.github.io/nas3r/.

Computational pathology has advanced rapidly in recent years, driven by domain-specific image encoders and growing interest in using vision-language models to answer natural-language questions about diseases. Yet, the core problem behind pathology question-answering remains unsolved, considering that a gigapixel slide contains far more information than necessary for a given question. Pathologists naturally navigate tissue and morphology complexity by scanning broadly, and zooming in selectively according to the clinical questions. Current models, in contrast, rely on uniform patch sampling or broad attention maps, often attending equally to irrelevant regions while overlooking key visual evidence. In this work, we try to bring models closer to how humans actually examine slides. We propose a question-guided, tissue-aware, and coarse-to-fine retrieval framework, HistoSelect, that consists of two key components: a group sampler that identifies question-relevant tissue regions, followed by a patch selector that retrieves the most informative patches within those regions. By selecting only the most informative patches, our method becomes significantly more efficient: reducing visual token usage by 70% on average, while improving accuracy across three pathology QA tasks. Evaluated on 356,000 question-answer pairs, our approach outperforms existing methods and produces answers grounded in interpretable, pathologist-consistent regions. Our results suggest that bringing human-like search and attention patterns into WSI reasoning is a promising direction for building practical and reliable pathology VLMs. Code is available at https://github.com/winston52/HistoSelect.

Speculative Jacobi Decoding (SJD) offers a draft-model-free approach to accelerate autoregressive text-to-image synthesis. However, the high-entropy nature of visual generation yields low draft-token acceptance rates in complex regions, creating a bottleneck that severely limits overall throughput. To overcome this, we introduce SJD-PAC, an enhanced SJD framework. First, SJD-PAC employs a proactive drafting strategy to improve local acceptance rates in these challenging high-entropy regions. Second, we introduce an adaptive continuation mechanism that sustains sequence validation after an initial rejection, bypassing the need for full resampling. Working in tandem, these optimizations significantly increase the average acceptance length per step, boosting inference speed while strictly preserving the target distribution. Experiments on standard text-to-image benchmarks demonstrate that SJD-PAC achieves a $3.8\times$ speedup with lossless image quality. Code is available at https://github.com/KangJialiang/SJD-PAC.

Distilling knowledge from large Vision-Language Models (VLMs) into lightweight networks is crucial yet challenging in Fine-Grained Visual Classification (FGVC), due to the reliance on fixed prompts and global alignment. To address this, we propose PAND (Prompt-Aware Neighborhood Distillation), a two-stage framework that decouples semantic calibration from structural transfer. First, we incorporate Prompt-Aware Semantic Calibration to generate adaptive semantic anchors. Second, we introduce a neighborhood-aware structural distillation strategy to constrain the student's local decision structure. PAND consistently outperforms state-of-the-art methods on four FGVC benchmarks. Notably, our ResNet-18 student achieves 76.09% accuracy on CUB-200, surpassing the strong baseline VL2Lite by 3.4%. Code is available at https://github.com/LLLVTA/PAND.

Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Recently, interest has surged in developing methods, such as vision-language models (VLMs), to extract tables directly in their full page or document context. However, a lack of annotated data has made progress difficult to demonstrate. To address this, we create a new large-scale dataset, PubTables-v2. PubTables-v2 unifies TE across various levels of surrounding context and, notably, is the first benchmark for multi-page TE. Our evaluations reveal that while current frontier models strongly outperform ($+0.354\ \textrm{GriTS}_\textrm{Con}$) small models on the most complex task (full-document multi-page TE), this gap can be closed or even reversed ($-0.056\ \textrm{GriTS}_\textrm{Con}$) on narrower tasks (cropped table extraction) with targeted training. Data is available at https://huggingface.co/datasets/kensho/PubTables-v2. Code and models will be released.

Prevailing High Dynamic Range (HDR) video reconstruction methods are fundamentally trapped in a fragile alignment-and-fusion paradigm. While explicit spatial alignment can successfully recover fine details in controlled environments, it becomes a severe bottleneck in unconstrained dynamic scenes. By forcing rigid alignment across unpredictable motions and varying exposures, these methods inevitably translate registration errors into severe ghosting artifacts and temporal flickering. In this paper, we rethink this conventional prerequisite. Recognizing that explicit alignment is inherently vulnerable to real-world complexities, we propose LoCAtion, a Long-time Collaborative Attention framework that reformulates HDR video generation from a fragile spatial warping task into a robust, alignment-free collaborative feature routing problem. Guided by this new formulation, our architecture explicitly decouples the highly entangled reconstruction task. Rather than struggling to rigidly warp neighboring frames, we anchor the scene on a continuous medium-exposure backbone and utilize collaborative attention to dynamically harvest and inject reliable irradiance cues from unaligned exposures. Furthermore, we introduce a learned global sequence solver. By leveraging bidirectional context and long-range temporal modeling, it propagates corrective signals and structural features across the entire sequence, inherently enforcing whole-video coherence and eliminating jitter. Extensive experiments demonstrate that LoCAtion achieves state-of-the-art visual quality and temporal stability, offering a highly competitive balance between accuracy and computational efficiency.