Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelity generator into the unified training loop is computationally prohibitive, limiting achievable visual quality. We therefore propose Lumos-Nexus, a training-efficient unified video generation framework that facilitates the development of strong reasoning-driven generation capabilities while significantly enhancing visual fidelity. Lumos-Nexus adopts a two-stage design: 1) During training, only a lightweight generator is aligned with the understanding block to learn to take in reasoning-driven semantic control. 2) During inference, we introduce Unified Progressive Frequency Bridging (UPFB) to progressively hand off generation to a high-capacity pretrained generator in the shared latent space, enabling coarse-to-fine refinement and producing high-fidelity videos without compromising reasoning quality. To fill the gap in reasoning-driven video generation benchmarks, we introduce VR-Bench, which assesses a model's capability to translate inferred intent into coherent and semantically aligned video content. Extensive experiments demonstrate that Lumos-Nexus achieves substantial gains in visual realism and temporal coherence on VBench, while exhibiting strong reasoning-based generative performance on VR-Bench. Code and models are available at https://jiazheng-xing.github.io/nexus-lumos-home/.

Video vision-language models (VLMs) are increasingly used in long-horizon and streaming settings, yet most video encoders still rely on spatiotemporal self-attention, causing compute and latency to grow quadratically with the number of frames. Existing efficiency methods improve scalability but often lose accuracy relative to full self-attention, for example through aggressive frame/token dropping or coarse attention approximations. We introduce StateKV, an inference-time method that adapts pretrained long-video VLMs to linear-time video prefill by carrying cross-frame context in a fixed-capacity, importance-based recurrent state, paired with a second full per-frame cache used for decoding. Across three long-video benchmarks and seven models spanning three families and multiple scales, StateKV remains close to full self-attention and consistently outperforms dominant sliding-window / recency-based streaming approximations, without fine-tuning or architectural changes. StateKV also reduces video-prefill cost measured FLOPs, enabling stronger accuracy at a fixed compute budget by running larger models. These results suggest a practical step toward scalable long-video understanding.

Diffusion models have shown promising performance as data-driven priors for computational imaging, as well as some capacity to detect out-of-distribution (OOD) images. However, existing approaches to OOD detection often require some knowledge of the shifted distribution, fail to detect subtle or localized distribution shifts, and operate on full images, rather than the indirect measurements available in inverse problems. We propose an OOD detection metric based on the Kullback-Leibler divergence between the diffusion prior and the posterior distribution, that (i) does not require any calibration data or knowledge of the shifted distribution, and (ii) can detect whole images as OOD as well as localize OOD patches within an image. Experimentally, we show that this metric can detect subtle yet semantically meaningful distribution shifts, such as the shift from healthy liver CT scans to those with tumors, and generalizes across different types of diffusion models, datasets, and inverse problems. Our code can be found at https://github.com/voilalab/KLIP.

Dynamic scene reconstruction from monocular video remains a fundamental challenge in computer vision. Existing feed-forward methods predict 3D Gaussians pixel-wise for each frame, suffering from duplicated Gaussians and view-dependent biases that hinder effective learning of scene motion. We present C4G, a feed-forward 4D reconstruction framework built upon a compact set of timestamp-conditioned learnable Gaussian query tokens. Each token aggregates corresponding features across the full temporal context and decodes a 3D Gaussian whose position is modulated by the target timestamp, enabling globally coherent motion modeling without per-scene optimization. To capture fine-grained details, we further introduce a video diffusion model-based rendering enhancement module. Since our framework effectively aggregates features into Gaussians, we extend this capability to feature lifting, producing a 4D feature field that supports point tracking and dynamic scene understanding. C4G achieves strong novel-view synthesis performance using significantly fewer Gaussians and without requiring camera poses, while exhibiting stronger motion modeling and robustness to large temporal gaps.

Models for AI-based skin cancer screening suffer a severe performance drop when shifting from expert dermoscopic (source) images to consumer-grade clinical (target) images, hindering real-world deployment. Existing domain adaptation methods often ignore crucial semantic invariants, such as clinical concepts. While new foundation models like MONET can provide this semantic information as dense, probabilistic scores, this metadata is unavailable at test time, creating a deployment paradox for practical image-only screening tools. We address this gap by proposing CoFiDA-M, a privileged information framework that learns from concepts at training time but deploys as an image-only model. Our method trains a teacher network that uses MONET concept probabilities to guide a FiLM modulator, transforming visual features into a semantically ``edited" feature space. A lightweight, image-only student is then trained to reproduce this edited representation, not just the teacher's final predictions. This distillation ``bakes" the clinical reasoning into the student's weights. On a challenging multi-dataset benchmark, our image-only student significantly outperforms state-of-the-art approaches, especially in melanoma recall. Our work provides a practical and generalizable framework for leveraging noisy, probabilistic metadata as privileged information, demonstrating strong cross-dataset robustness and potential for real-world deployment beyond dermatology. Implementation code is available at: https://github.com/mmu-dermatology-research/CoFiDA.git

Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intrinsics of the diffusion process, we probe video diffusion transformers (DiTs) and uncover intrinsic turning points in the DiT denoising trajectory where conditioning text affects generation from global layout to fine-grained details. Building on this finding, we present TunerDiT, a simple yet effective progressive steering method that requires no additional training for multi-event generation. TunerDiT comprises two steering handles: (1) Event-Partitioned Masking that enforces event boundaries while allowing cross-event transition bands; (2) Cross-Event Prompt Fusion that injects neighboring event semantics for late-stage refinement. We contribute a self-curated prompt suite for benchmarking multi-event generation, i.e., Meve. TunerDiT achieves state-of-the-art performance across 8 metrics and offers a tunable trade-off between video consistency and event separation, compared with other training-free methods. The improvement in text alignment increases with the event count, indicating a scaling possibility with increasing event count.

While humans naturally gesture during speech, only a sparse subset of these movements are visually depictive and semantically linked to specific spoken words. Current multimodal models struggle to capture these semantic co-speech gestures, heavily bottlenecked by a lack of precisely annotated training data. To address this, we introduce the Gesture Recognition in the Wild (GRW) dataset, the first large-scale benchmark designed to map unconstrained human gestures to specific words with frame-accurate temporal boundaries. Comprising 156,688 manually annotated video clips, GRW spans a highly diverse 150-word taxonomy of physical actions, spatial descriptors, and abstract concepts. We leverage GRW to train video models to (a) classify gestures as semantic or not, (b) recognize the word corresponding to a co-speech gesture, and (c) temporally localize the gesture. We also use GRW to establish benchmarks for these three tasks.

Recent feedforward 3D reconstruction methods predict point maps and estimate global 3D geometry remarkably well. However, their predictions still exhibit inaccurate local surface geometry, which is clearly visible qualitatively but only weakly reflected in common metrics. To make these errors more explicit in evaluation, we introduce a point map normal metric that evaluates the local surface orientation induced by neighboring 3D predictions. To reduce these errors, we propose two complementary components: a point gradient matching loss that supervises depth-normalized 3D finite differences, and a Neighborhood Attention Decoder (NAD) that progressively upsamples features and uses Neighborhood Attention for local feature mixing. Across eight zero-shot monocular geometry benchmarks, our model, SurGe, achieves the best average rank for global point map AbsRel and consistently improves local point map and point map normal evaluations.

Most learning-based camera-LiDAR calibration methods treat each camera-LiDAR pair independently, ignoring the rigid geometric coupling in multi-camera platforms. As a result, per-camera estimates may be individually accurate yet inconsistent at the system level. We present a two-stage framework for joint multi-camera LiDAR extrinsic calibration that combines learned pairwise matching with geometric refinement. First, CMRNext is applied independently to each camera to produce initial extrinsic estimates and dense 2D-3D correspondences. These predictions are then jointly refined through a multi-frame bundle adjustment with reprojection, per-camera prior, and relative-pose prior terms. This approach converts pairwise predictions into a globally consistent multi-camera calibration. Experiments on KITTI (in-domain for CMRNext) and Walkley (out-of-domain) datasets show improved per-camera accuracy and inter-camera consistency. On KITTI, the method achieves 0.89 cm translation error and 0.038 rotation error. On Walkley, it reduces translation error from 108.6 cm to 3.1 cm, highlighting the benefit of explicit multi-camera coupling when single-camera predictions are less reliable.

Reasoning is essential for autonomous driving (AD) in long-tail scenarios, where vehicles must apply commonsense knowledge, understand spatial relations, infer agent interactions, and make safe decisions. However, existing AD datasets and benchmarks mainly target perception, prediction, or planning, and provide limited supervision for reasoning over realistic long-tail driving scenes. We introduce nuReasoning, a large-scale real-world dataset and benchmark for reasoning-centric AD. Following the lineage of nuScenes and nuPlan, nuReasoning advances real-world AD datasets and benchmarks toward reasoning in long-tail driving scenarios. The dataset contains 20,000 clips, each 20 seconds long, collected across multiple cities, with synchronized multi-camera images, LiDAR data, HD maps, object annotations, and human-verified reasoning annotations spanning Spatial Reasoning, Decision Reasoning, and Counterfactual Reasoning. Unlike prior datasets that focus primarily on visual question answering, nuReasoning supports both reasoning evaluation and planning evaluation, enabling a direct study of how reasoning supervision affects driving performance. Experiments show that fine-tuning VLMs on nuReasoning substantially improves driving-specific question answering, while incorporating reasoning supervision into VLA training improves planning performance even when textual reasoning outputs are disabled at inference time. These results establish nuReasoning as a foundation for evaluating and improving robust, interpretable, reasoning-driven AD systems in realistic long-tail settings.

Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succeed. Far less is known about ambiguous inputs (a worker in full gear, a figure seen from behind) cases common in practice yet rarely studied. We find that minimal prompting pressure exposes occupation-gender defaults when prompting ambiguous input images, with models collapsing to male even for strongly female-stereotyped occupations. But do these outputs reflect what models actually encode internally? We introduce LALS (Latent Association Leaning Score), a zero-shot metric that projects visual-token activations into the model's text-embedding space to measure concept associations per token and layer. Across 15 occupations, over 800 gender-ambiguous images, and four VLMs, internal representations and outputs are systematically decoupled: models often encode a female association internally yet output male. Layer-wise analysis reveals an asymmetric filter -- male signal amplifies end-to-end while female signal peaks mid-network and is suppressed before generation -- and a color ablation shows that culturally loaded visual cues such as clothing color further modulate these internal associations.

We present our approach to the FIFA Skeletal Tracking Challenge 2026, which requires estimating 3D world-space poses of soccer players from broadcast video. Our method finetunes SMPLest-X (ViT-H, 687 M parameters) via a stratified clip split, multi-task depth supervision, and broadcast augmentation, paired with a RAFT dense optical flow camera tracker, foot-plane anchoring, and two-pass temporal smoothing. Against the FIFA baseline score of 1.053 on the validation set, SMART achieves 0.647, a 38.6% improvement; on the held-out test set, SMART scores 0.593 (Global MPJPE: 0.324 m, Local MPJPE: 0.054 m).

Postoperative pancreatic fistula (POPF) is a serious complication after pancreatic resection, increasing morbidity, hospital stay, and healthcare costs. We present an automatic, end-to-end deep learning pipeline-from pancreatic segmentation to classification-for preoperative POPF risk estimation and stratification using preoperative CT scans. A data set with auto-segmented pancreas volumes and surgical outcomes was used to evaluate multiple architectures, including a custom lightweight 3D CNN baseline (CNN3D), R(2+1)D ResNet-18, and ResNet-MC3-18 models. Evaluation across multiple 3D architectures demonstrated promising predictive performance. This approach offers a clinically valuable tool and a methodological benchmark for pancreas-specific CT classification, supporting improved preoperative decision-making in pancreatic surgery.

Self-supervised novel view synthesis (NVS) remains challenging to scale, despite the abundance of video data, largely due to the brittleness of training on realistic videos and the hard-to-predict scaling behavior of multi-network system designs. We introduce RayDer, a unified, feed-forward transformer that consolidates camera estimation, scene reconstruction, and rendering into a single backbone, turning self-supervised NVS into a well-posed single-model scaling problem. A minimal dynamic state, treated as a nuisance factor, absorbs time-varying content and enables stable training on unconstrained real-world video. Importantly, RayDer keeps static-scene NVS as its target task: dynamic content is leveraged purely as scalable supervision, not reconstructed as in dynamic-scene (4D) NVS. Across multiple model sizes and orders of magnitude in data, RayDer exhibits clean power-law scaling with data and compute, and outperforms static-scene data mixtures. On a large number of benchmarks, RayDer achieves strong zero-shot open-set performance competitive with state-of-the-art supervised approaches. Project Page: https://compvis.github.io/rayder

Three-dimensional scene reconstruction depends on local image evidence that is both visually discriminative and geometrically useful. Fixed feature thresholds and uniform feature budgets are easy to deploy, but they can waste computation on repeated texture, low-parallax regions, or unstable points. This paper proposes an adaptive feature-optimized vision front end for 3D reconstruction. The method scores candidate features by texture, repeatability, distinctiveness, expected triangulation angle, and spatial coverage, then allocates a per-view feature budget to maximize useful tracks under a fixed reconstruction pipeline. A small synthetic multi-view prototype evaluates four selection policies across corridor, facade, object-table, and cluttered scenes. Compared with random, texture-only, and uniform-grid baselines, the adaptive policy obtains the best quality-aware completeness and the lowest aggregate reconstruction RMSE while preserving broad image coverage. The result is not a replacement for modern learned matching or neural reconstruction systems; it is a modular front-end policy that can make classical and learned 3D pipelines more deliberate about which visual evidence they spend compute on.

True video intelligence demands more than recognizing what is visible: it requires reasoning about why events unfold, predicting what would change under different conditions, and deciding what to do next. We refer to this progression, from perception through causal reasoning and simulation to strategic planning, as Strategic Video Intelligence (SVI). No existing benchmark evaluates this capability stack: in-the-wild videos lack verifiable ground truth for causal and strategic questions, while synthetic environments sacrifice the complexity of real multi-agent systems. To bridge this gap, we introduce SVI-Bench, a large-scale benchmark that leverages team sports as a dynamic microworld, combining the complexity of real-world multi-agent interaction (10-22 agents making coordinated decisions under adversarial pressure) with the verifiability of explicit rules and definitive outcomes. SVI-Bench comprises approximately 35K hours of broadcast video, 15M annotated actions, 15K hours of expert commentary, 23K game reports, and 103K structured statistical records across basketball, soccer, and hockey, all constructed via a data engine that transforms raw game data into a dense, cross-referenced corpus. We organize evaluation into 9 tasks spanning a progressive four-pillar hierarchy: Dynamic Scene Understanding, Causal Reasoning, Strategic Simulation, and Agentic Synthesis. Evaluating strong multimodal and agentic baselines, we find a capability cliff: models perform competently on perceptual tasks, achieving approximately 73% on fine-grained action QA, but degrade sharply at each successive cognitive level. Agentic tasks prove hardest: the strongest model achieves only 5% accuracy when required to autonomously gather and integrate evidence across a corpus of 1.8M clips.

Large vision-language models (LVLMs) have demonstrated strong general multimodal capability and are increasingly deployed in downstream systems. This trend has driven growing interest in LVLM personalization, which aims to enable models to quickly and effectively learn out-of-distribution multimodal concepts to meet user-specific needs. However, many existing methods rely on inference-time training, which reduces efficiency. They also struggle to maintain accuracy in complex multi-image, multi-concept settings. These limitations restrict the broader deployment of LVLM-based systems. Therefore, this paper proposes in-context prompt tuning (ICPT). Specifically, ICPT employs a lightweight projection module capable of operating in complex scenarios to extract fine-grained visual semantics from multiple reference images, seamlessly transforming these features alongside identity-label mappings into continuous prompts. To maximize computational efficiency, this module adaptively determines the prompt length based on the intrinsic visual complexity of each concept. Crucially, to overcome the environmental biases and cross-concept interference prevalent in real-world applications, we introduce two novel geometric regularizations. These constraints refine prompt representations by decoupling key identities from transient environmental states and separating concepts to avoid semantic confusion. Extensive experiments show that ICPT achieves state-of-the-art personalization accuracy across diverse tasks and LVLM backbones.

Video Object-Centric Learning (OCL) aims to represent objects as \textit{slot} vectors and maintain their consistency across frames. Slot-Slot Contrastive (SSC) loss has become the cornerstone for state-of-the-art (SOTA) video OCL methods. While highly effective, SSC relies on one-to-one object correspondence across frames and introduces an extra loss. Following Occam's Razor, we propose a paradigm shift: temporal consistency is better enforced as an implicit model design rather than an explicit loss. To elegantly exclude SSC (\textbf{xSSC}), we introduce two quasi-zero-overhead synergistic mechanisms: (\textit{i}) Chrono-Channel Decomposition (CCD) structurally disentangles slot representations along the channel dimension into \textit{static} and \textit{dynamic} sub-spaces, serving as an empirically unified information bottleneck; (\textit{ii}) Cross-Temporal Reconstruction (CTR) stochastically reconstructs target features of either the current or previous time step by fusing current slots' static channels and target slots' dynamic channels, using a single standard OCL decoder with minor training adaptation. Thereby, the slot sets inherently learn temporal consistency by minimizing the standard reconstruction error alone. Extensive experiments show that integrating xSSC into leading baselines not only improves training efficiency but also establishes new SOTAs on video object discovery and recognition tasks. Furthermore, our PCA and gradient analyses confirm that objects' time-invariant semantics and time-variant kinematics are encoded into the proposed sub-spaces. Our source code, model checkpoints and training logs are provided on https://github.com/Genera1Z/xSSC.

Humans easily determine which color belongs to which shape in multi-object scenes, an ability known as concept binding. Vision-language embedding models such as CLIP struggle with binding: they recognize individual concepts but fail to represent which concepts form which objects. Although CLIP behaves like a bag-of-concepts model in cross-modal retrieval, object information is recoverable from its image and text embeddings separately. We study this tension through the binding function, which maps concepts to scene embeddings. We find that scene embeddings decompose additively into object representations, explaining why uni-modal probes can recover object information. However, CLIP's binding function is high-complexity, which likely prevents the image and text encoders from learning a shared binding mechanism that generalizes to unseen concept combinations. We then ask whether this limitation is fundamental. We show that it is not. In controlled transformer models trained from scratch, binding generalization emerges with sufficient data coverage. These models learn low-complexity binding functions characterized by multiplicative interactions between concepts, enabling systematic generalization. Code is publicly available at https://github.com/oshapio/binding-concepts-complexity.

Reconstructing the complete geometry of a scene from a single RGB image remains challenging - especially when inferring hidden structures where visual evidence is incomplete. We introduce VolFill, a generative framework that predicts the 3D structure of the complete scene rather than relying on traditional pixel-aligned regression. Our method utilizes a hybrid 3D VAE to compress sparse truncated unsigned distance function grids into a compact latent space, paired with a latent Diffusion Transformer that denoises this representation to recover the complete scene. We condition the generation on geometry foundation models, leveraging rich spatial priors for robust reasoning. Unlike existing methods limited by per-ray constraints or unstructured point-cloud queries, VolFill provides a structured representation that supports direct surface extraction and occupancy queries at scale. Extensive experiments on the SCRREAM and NRGB-D datasets demonstrate that our approach significantly outperforms current baselines, providing a robust foundation for holistic spatial understanding.

With the rapid advancement of large multimodal models (LMMs), inference-time overhead has become a key bottleneck for real-world deployment. Existing methods typically prune visual tokens at prefill, assuming the required visual evidence remains static during reasoning. However, we empirically show that visual evidence is strongly step-dependent: only a sparse subset of visual tokens is critical at each decoding step, and the critical set evolves across reasoning. Furthermore, we identify a coupled bottleneck where redundant visual context can steer the model toward query-irrelevant regions, lengthening the reasoning trace. Guided by these insights, we propose VisionPulse, a step-wise visual token pruning framework during reasoning. VisionPulse computes a lightweight visual attention mass to estimate the step-wise retention budget by exploiting its strong positive correlation with LMMs' effective visual token usage and retain only the most critical tokens under this budget. By enforcing visual sparsity during reasoning, VisionPulse filters redundant visual context while preserving relevant visual evidence, shortening reasoning traces naturally. Extensive experiments show that VisionPulse only retains 5% of visual tokens per step with reasoning traces shortened by 11.2%, while keeping accuracy almost unchanged.

Contrastive decoding (CD) seeks to mitigate hallucinations in Large Vision-Language Models (LVLMs) by contrasting the output distributions of a standard model and a visually degraded model. However, existing training-free CD methods suffer from sub-optimal degraded branches: completely dropping visual tokens is too extreme and induces language hallucinations, while corrupting input images offers coarse control over visual evidence and suffers from high inference latency due to requiring two full forward passes. To address these dilemmas, we propose YARD, a training-free Y-Architecture Register Decoding framework. Motivated by the observation that reliable text-to-vision grounding predominantly emerges in the middle decoder layers, YARD constructs the degraded branch internally by sharing shallow-layer computations and branching exactly at this critical stage. For the degraded branch, YARD replaces patch-level visual tokens with register tokens, which preserve global image semantics but lack fine-grained local evidence. This image-aware yet locally under-grounded design provides a faithful contrastive signal without extreme modality mismatch, while the Y-architecture strictly avoids a costly second forward pass. Extensive experiments on generative and discriminative hallucination benchmarks demonstrate that YARD consistently achieves state-of-the-art hallucination mitigation across multiple LVLMs, alongside a significant reduction in inference latency.

Image Scanning Microscopy (ISM) is a fluorescence imaging technique that combines detector-array acquisition and computational reconstruction to achieve the theoretical resolution of an ideal confocal microscope, i.e., one operating with an infinitesimally small pinhole, while maintaining high signal-to-noise ratio. Among the reconstruction methods for obtaining the super-resolved image, multi-image deconvolution (MID) and its extension aimed at preserving the optical sectioning capability of confocal microscopy, known as super-resolution sectioning ISM (s$^2$ISM), are among the most widely used approaches. Both methods rely on Richardson--Lucy-type iterative schemes, whose semi-convergent behavior requires early stopping and often leads to noise amplification and reconstruction artifacts. In this work, we introduce a self-tuning explicit regularization framework for both MID and s$^2$ISM reconstruction. Within a Bayesian maximum a posteriori formulation, we combine a multi-frame Poisson data fidelity term with explicit regularization, considering $\ell_1$ and smoothed total variation penalties as representative examples. We further develop an automatic and ground-truth-free strategy for regularization parameter selection by adapting the residual whiteness principle to the multi-frame Poisson setting and introducing a spectral high-pass extension tailored to s$^2$ISM. The resulting framework enables stable reconstructions without empirical stopping rules. To demonstrate the proposed framework, we consider first-order optimization schemes based on proximal gradient and mirror descent methods with adaptive backtracking strategies. Experiments on simulated and real fluorescence ISM datasets demonstrate improved reconstruction stability and image quality with respect to unregularized approaches, while enabling robust super-resolution and optical sectioning in low-photon conditions.

Real-world image deblurring demands both high-fidelity restoration and computational efficiency, a balance existing methods often struggle to achieve. In this paper, we propose FSM-Net (Frequency-Spatial Multi-branch Network), a highly efficient solution that secured 2nd place in the NTIRE 2026 Challenge on Efficient Real-World Deblurring. FSM-Net pioneers a dual-domain approach: a novel Frequency Attention module explicitly recovers high-frequency structural details via FFT, while a Cross-Gated Vision E-Branchformer at the bottleneck captures global dependencies with linear complexity. To ensure robust convergence, we employ a progressive curriculum training strategy guided by a composite loss function (Multi-Scale Charbonnier, Structural Edge, and Frequency). Evaluated on the RSBlur benchmark, FSM-Net achieves an outstanding 33.144 dB PSNR with only 4.94M parameters and 159.35 GMACs (at 1920x1200 resolution). By effectively pushing the Pareto frontier of efficiency and quality, FSM-Net establishes a strong baseline for resource-constrained image restoration.

Autonomous robots in unknown indoor environments require both reliable collision avoidance and object-level understanding. Classical representations such as TSDF support safe planning but lack semantics, while photorealistic methods like Gaussian Splatting (GS) provide rich appearance yet suffer from soft geometry, limiting precise obstacle avoidance. We present LiftNav, a hybrid navigation framework built on GSFusion's TSDF+GS dual map, augmented with a real-time pipeline of YOLO-based detection, TSDF-based 3D lifting, and B-spline trajectory optimization. This design enables flexible semantic navigation without dense 3D embeddings. We further introduce a hinge-loss-based collision penalty that improves trajectory smoothness and safety. We evaluate our approach in a simulation using the Replica dataset. Compared against a state-of-the-art radiance field baseline we show a 100% feasibility rate and shorter trajectories.

Many modern generative models can be viewed as minimizing divergences between probability distributions, yet they rely on different algorithmic and geometric principles. Wasserstein gradient flows provide a continuous-time formulation for optimizing over distributions, and can be approximated through their implicit discretization via the Jordan-Kinderlehrer-Otto (JKO) scheme. In this work, we present a unified theoretical framework for generative modeling based on Wasserstein gradient flows, which we refer to as Generative Wasserstein Flows (GWF). We show that a broad class of existing methods can be derived as instances of parametric JKO schemes for $f$-divergence objectives, and we establish equivalences between several recently proposed algorithms. We extend this framework beyond f-divergence to Integral Probability Metrics and squared Maximum Mean Discrepancy, deriving new JKO-based generative algorithms, and clarifying their connections with GANs. We study empirically the impact of the JKO regularization for a wide set of objectives. Finally, we analyze parametric Wasserstein flows, where the dynamics are restricted to distributions induced by parametrized maps.

AI-based Visually Impaired Assistance (VIA) remains challenging, largely due to the high cost of human evaluation. The VLM-as-a-Judge paradigm may offer a promising alternative, although it has mostly been studied in general domains. We therefore ask whether such judges can be trusted for VIA tasks. To investigate this question, we introduce VIABLE (Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation), the first benchmark for VLM-as-a-Judge evaluation in VIA. VIABLE contains over 300K judgment samples across three scenarios and introduces an Effectiveness--Impartiality--Stability framework with a 12-mode failure taxonomy. Based on VIABLE, our systematic study of seven judges across different model scales shows that existing models are largely unreliable across all evaluation axes. The strongest judge, GPT-5.4, achieves only 52.6% single-failure diagnostic accuracy, yet exhibits the highest self-preference rate at 94.2%; while open-source judges are strongly biased and adversarially fragile. To address these issues, we propose VIA-Judge-Agent, a model-agnostic inference-time harness that augments judges with visual evidence extraction and a taxonomy-guided workflow. It enables positive improvements in diagnostic accuracy and downstream VIA responses more preferred by BLV users. Data and code are available at: https://github.com/YiyiyiZhao/VIABLE

Hateful meme detection remains a formidable challenge for vision-language models, as existing benchmarks are structurally observational - confounding rhetorical hate mechanisms with target community features and preventing causal evaluation of model vulnerabilities. To address this, we introduce FBHM, a systematically curated benchmark of Functionality Based Hateful Memes constructed along two orthogonal axes: 25 distinct rhetorical functionalities and 10 target communities (5,000 memes total). Benchmarking state-of-the-art VLMs reveals a severe generalization gap: models highly accurate on standard datasets catastrophically drop to near-random performance on FBHM, proving they exploit dataset-specific heuristics rather than robust multimodal reasoning. To efficiently close this gap, we propose LSV (learnable steering vectors), an ultra-low data regime strategy that applies a causal intervention objective on as few as 500 steering samples (50 unique base memes), boosting FBHM performance by ~30 Macro-F1 points while outperforming in-context learning and PEFT without degrading source-domain performance.

Recent advances in video generative models have promoted rapid progress in controllable world models. However, maintaining fine-grained spatio-temporal consistency under long-horizon reasoning remains a key challenge. In this work, we move beyond explicit 3D memory and coarse frame-level implicit modeling, and propose a fine-grained, learnable, and scalable memory for consistent world generation. We first identify two fundamental limitations of naïve learnable memory architectures in long-horizon extrapolation, namely computational inefficiency and attention dispersion. Through a systematic analysis of attention dispersion, we propose DecMem, a decoupled memory architecture that employs Sparse Global Memory for efficient fine-grained access to global history and Anchored Local Memory for stable and high-quality extrapolation. Extensive experiments demonstrate that DecMem significantly outperforms current state-of-the-art methods. By ensuring precise and efficient long-term memory and achieving superior extrapolation capabilities, DecMem enables minute-level controllable long video generation with high fidelity and consistency.

Multimodal hallucination remains a persistent challenge for Vision-Language Models (VLMs). Standard textual Direct Preference Optimization (DPO) often fails to mitigate it due to a lack of explicit visual supervision. While existing works introduce visual preference DPO by contrasting original images against negative ones, they suffer from a theoretically inconsistent objective caused by partition function mismatches and rely on coarse-grained negatives that could enable shortcut learning. In this work, we propose In-Context Visual Contrastive Optimization (IC-VCO). By placing contrastive images within a shared multi-image context, IC-VCO ensures a mathematically rigorous objective. We further introduce Visual Contrast Distillation (VCDist), an auxiliary reliability-gated regularizer that encourages consistency between multi-image contrastive training and single-image inference. Finally, we propose a contrastive sample editing strategy that generates hard negatives via precise semantic perturbations. Experiments on five benchmarks demonstrate IC-VCO's best overall performance and the effectiveness of our sample editing strategy. Code and data are available at https://github.com/OPPO-Mente-Lab/IC-VCO.

Deep neural networks (DNNs) are widely used, but interpreting what they actually learn remains difficult. A major obstacle is that individual neurons often encode multiple unrelated concepts, obscuring the decision process of the network. While prior work, such as sparse autoencoders, can separate these mixed signals into more meaningful, "monosemantic" features, this typically requires altering the model in ways that can degrade downstream performance. To overcome this, we introduce ELUDe (explicit, lossless, unsupervised disentanglement), a method for improving the interpretability of DNNs while preserving their functional equivalence. ELUDe breaks latent representations into clear, inspectable sub-units that behave like interpretable features, while guaranteeing that the model's outputs remain exactly the same. It requires no explicit training, no labels, and can be applied to pretrained models. ELUDe works by reorganizing how information flows between layers, re-routing concept-specific contributions while preserving the original computation by construction. Across several vision models, including DINOv2 and supervised ViT-B/16, ELUDe improves interpretability, keeps downstream accuracy unchanged, runs efficiently, and supports practical uses such as steering model representations. In short, ELUDe offers interpretability (almost) without a tradeoff: clearer, scalable, and actionable model insights with no loss in performance.

Undersampled magnetic resonance imaging (MRI) reconstruction seeks to recover temporally or contrast-varying image series from incomplete multicoil k-space data while preserving state-dependent fidelity for dynamic and quantitative MRI (qMRI). Existing scan-specific implicit neural representations (INRs) often use monolithic spatiotemporal coordinate fields, explicit subspaces, motion or deformation models, calibration variables, or sequence-specific quantitative signal models. These design choices can limit flexibility in sharing spatial information while adapting image synthesis across acquisition states. Moreover, many INR-based baselines remain computationally demanding, typically requiring per-scan optimization times on the order of hundreds to thousands of seconds. We propose MoE-dqINR, a scan-specific multicoil MRI reconstruction framework that factorizes the image-domain representation into shared spatial experts and a state-conditioned routing pathway. Spatial experts encode reusable coordinate-dependent image content, whereas routing weights, conditioned on ordered acquisition states, synthesize each dynamic frame or contrast state from a common expert bank. The representation is coupled to a multicoil MRI forward model, uses the normalized state index to drive routing in both dynamic and quantitative MRI. By separating shared spatial representation from state-dependent synthesis, the framework provides an image-first architecture for dynamic and quantitative MRI while reducing scan-specific INR optimization to approximately 30 s per scan in our experiments. The proposed formulation establishes state-conditioned mixture-of-experts INR as a scan-specific multicoil MRI reconstruction prior that unifies shared spatial representation, dynamic- and qMRI-specific synthesis, and practical per-scan efficiency.

Recent advances in Audio-LLMs like GPT-4o have ushered in an era of conversational interaction with language models. Conversational avatars however, still seem robotic in facial expression and conversational flow, in part due to sequential stages of speech recognition, text generation, turn-based text response, speech synthesis, and audio driven facial animation. Based on our insight that audio-tokens produced by current Audio-LLMs carry sufficient information to reconstruct a plausible facial performance, we present TokTalk, a system that directly outputs expressive facial animation in real-time from streaming audio-tokens. We construct a novel audio-token to 3D facial motion dataset, on which TokTalk is trained using a Chunk-based Conditional Flow Matching model. A lightweight adaptation strategy allows our trained model to seamlessly connect to any token-based Audio-LLM at minimal computational overhead. Our chunk-based processing further enables parametric trade-off between latency and facial quality, shown through ablation studies. We further show that the real-time performance of TokTalk is comparable in latency to prior art solutions, and significantly favorable (via a perceptual study) in terms of quality, expressivity and control of the 3D facial performance. We showcase TokTalk's flexibility using a chatbot Avatar, a voice-driven user Avatar, and an animation Director's interface, as diverse audio-visual face applications.

Copy Detection Patterns (CDPs) are structures printed on physical objects to enable cost-effective authentication. Verification is achieved by comparing a captured image with the digital template from which the CDP was printed. In practice, printer stochasticity and camera distortions hinder this comparison, limiting robustness against counterfeiting. Prior work addressed camera effects by synthesising reference images in the verification camera domain, but it ignored printing variability. We introduce an enrolment-based cross-camera dual-synthetic referencing framework. Each printed CDP is first captured by a controlled enrolment camera, and a deep-learning-based translator jointly exploits the digital template and the enrolled capture to generate a high-quality reference for the verification image. We provide an information-theoretic justification showing that the dual reference is more informative than template-based references. Experiments on heterogeneous mobile cameras demonstrate improved authentication performance, robustness to machine-learning-based copy attacks, and reliable verification from small CDP regions and on low-end devices.

The morphological analysis of mitochondria in fluorescence microscopy (FM) is crucial for understanding cellular health, energy production, and metabolic regulation. While foundation models like the Segment Anything Model (SAM) have revolutionized natural image segmentation, their direct application to FM is hindered by a significant domain shift characterized by diffraction-limited resolution, low contrast, and complex overlapping organelle networks. Furthermore, the development of robust models is bottlenecked by a severe lack of high-quality, manually annotated instance segmentation datasets for mitochondria. In this paper, we propose a scalable solution to this data scarcity by finetuning SAM exclusively on synthetically generated FM data. We simulate realistic mitochondria data and emulate the optical properties of fluorescence microscopes to create a large-scale annotated dataset. We evaluate our fine-tuned model on a curated dataset of real, manually annotated FM images. Qualitative and quantitative analyses demonstrate that our synthetically fine-tuned model improves precision and average dice score over strong baselines. This work establishes the potential of simulation-assisted training for FM instance segmentation.

We present SHELLS (Semantic Head Estimation via Layered Local Sampling), an efficient feed-forward framework for 3D head reconstruction in dense semantic correspondence from multi-view images. Existing methods typically refine vertices independently via localized feature volumes. This approach couples memory-intensive feature sampling to mesh resolution, which limits scalability for dense topologies (> 10k vertices) and introduces surface noise. In contrast, SHELLS decouples feature extraction from mesh resolution via a hierarchical sampling strategy. We extract multi-view features using a DINOv2 backbone with LoRA adaptation, projectively sample a sparse global feature cloud, and predict an intermediate coarse mesh. This coarse prior guides the construction of layered, surface-aware sampling shells that serve as a discrete search space for the final reconstruction. SHELLS maintains surface consistency while using 88% less inference GPU memory (2.4GB vs. 20GB) than volumetric baselines. It reduces median registration error by 21% to 29% with a 3.5x inference speedup (0.08s vs. 0.29s) for 18k-vertex meshes. Notably, our model is trained exclusively on synthetic data yet generalizes effectively to real-world captures, eliminating the need for the costly, pre-registered multi-view datasets common in prior work.

Driving Vision-Language-Action Models (Driving VLAs) aim to use language to improve end-to-end planning, but the language-action gap limits this promise. We propose DriveMA, a Driving VLA framework built on verifiable meta-actions, which summarize future ego motion into compact language-domain intentions and can be constructed from expert trajectories with a trajectory-grounded annotation pipeline and can be verified against generated trajectories through rule-based projection. DriveMA exploits this verifiability with action-centric supervised training and a data-efficient turn-level credit assignment reinforcement learning framework, explicitly aligning high-level decisions with low-level trajectory planning through dense rewards and precise credit assignment. DriveMA sets a new state of the art on the Waymo Open Dataset Vision-based E2E Driving, achieving a Rater Feedback Score of 8.060 with a 2B model and further improving it to 8.079 with a 4B model; it also obtains competitive closed-loop planning performance on NAVSIM. These results show that even a simple meta-action interface can achieve state-of-the-art planning when made verifiable and optimized for language-action alignment. Code, data, and models will be released to facilitate future research.

The layout-to-image (L2I) task enables fine-grained control over image generation via object categories and spatial layouts. However, existing L2I methods yield fragmented and distorted generations under few-shot atypical settings. We term this failure as representation fragmentation, arising from a granularity mismatch that entangles semantic identity with visual details. To address this issue, we propose a representation-driven framework that disentangles semantics from primitives for robust few-shot adaptation. Specifically, Semantic Anchoring aggregates categorical semantics into anchors for stable identity, while Primitive Imbuing models recomposable primitives for robust local detail modeling. Conceptual Steering further regulates optimization with a saliency-aware objective to preserve foreground semantic consistency. Extensive experiments demonstrate consistent improvements in the 5-shot regime over state-of-the-art L2I methods in both visual fidelity and alignment across diverse atypical domains. The source code is publicly available at https://github.com/iCVTEAM/DSP.

Multimodal large language models (MLLMs) have shown strong potential as embodied agents, yet embodied geo-localization remains underexplored due to the lack of fine-grained evaluation. We introduce ERGeoBench, a diagnostic benchmark for vision-driven embodied geo-localization. ERGeoBench evaluates models under three progressive settings -- single-view, panorama-view, and embodied-view -- where agents may actively acquire observations through sequential changes in yaw, pitch, and zoom. The benchmark contains 2,207 globally distributed street-view panoramas and measures four complementary capabilities: foundational perception, spatial awareness, common sense reasoning, and geo-localization reasoning. Evaluations of leading proprietary and open-source MLLMs show that current models can infer high-level geographic semantics, but still struggle with fine-grained perceptual operations, metric localization, and spatial consistency across views. We further observe that geo-localization is strongly correlated with the other capability dimensions, suggesting that accurate localization depends on integrated perception, spatial reasoning, and commonsense inference rather than isolated visual recognition. Overall, ERGeoBench provides a unified framework for diagnosing and advancing human-like embodied geo-localization. Project Page: https://kaixuewen.github.io/ERGeoBench/

Prompt learning is a new machine learning paradigm that has attracted ample attention due to its simplicity and proven efficacy. Despite its growing adoption, the security vulnerabilities associated with this paradigm remain underexplored. In this work, we take the first step to propose BadBone, a stealthy and adaptive backdoor attack against prompt learning using bi-level optimization. Instead of backdooring the prompt learning process, we aim to compromise a backbone model such that only target downstream tasks employing prompt learning inherit the backdoor vulnerability. Extensive experiments on three different models and three datasets from various domains show that our targeted/untargeted backdoored models achieve high attack performance while maintaining utility on both pre-training and downstream tasks. Moreover, we evaluate our approach against six state-of-the-art model-level defenses, including Neural Cleanse, ABS, MNTD, NAD, CLP, and D-BR. The results demonstrate that these defenses are largely ineffective against our backdoored models and thus leave the effective defense as an important direction for future work.

While retrieval is a core function of vision-language models, continually updating these models for retrieval tasks remains critically underexplored. Existing work often approaches continual retrieval through the lens of class-incremental learning (CIL), evaluating both standard CIL methods and retrieval-oriented adaptations in settings that may not fully capture the retrieval-specific dynamics. To address this, we introduce a new, principled evaluation framework for continual multimodal retrieval (CMR) spanning diverse visual domains, and systematically evaluate common approaches within this setting. Our empirical analysis shows that standard CIL methods fail to yield meaningful gains in our more challenging scenario. Therefore, we propose Dynamic Adapter Routing (DAR), a novel approach based on adapters selected through prototype-based routing and combined via model merging.DAR achieves superior performance over the previous baselines and demonstrates strong generalization under out-of-distribution evaluation. Our results highlights the unique challenges of CMR and encourages further research in this direction.

Procedural activities follow well-defined structures: whether we consider a cooking recipe or a mechanic repairing a car, these activities naturally decompose in a hierarchy of steps and sub-steps. Traditional approaches for step grounding require extensive annotations and scale poorly. Instead, we argue that such hierarchical structure can emerge naturally from uncurated videos of human activities through recurring patterns of co-occurring actions and activities. Our approach builds on HiERO, a weakly-supervised representation learning approach that maps close in the feature space actions that are functionally related to each other, leveraging only fine-grained action-level narrations. In this feature space, procedure steps can be detected by a simple clustering, with no additional task-specific fine-tuning. For the Ego4D Step Grounding challenge, we augment this approach by ensuring fine and coarse level agreement in step assignments, enforcing strict temporal monotonicity of the grounded steps and post-processing the detected steps to reduce the impact of noisy predictions. We call this approach HiERO-StepG and it achieves 56.27 % on the R@1 (IoU = 0.3) metric on the global leaderboard at submission time, ranking second while being completely zero-shot and not requiring procedure-specific annotations. Project page: https://github.com/andreazenotto/HiERO-StepG.

Monocular 6-DoF spacecraft pose estimation methods predominantly process individual frames, discarding the temporal information present in an image sequence acquired during spacecraft manoeuvres. Few temporal approaches require full backbone fine-tuning or auxiliary optical flow networks, risking catastrophic forgetting or increasing computational cost, respectively. We propose TALON (Token-Aligned Lightweight adapters for Orbital Navigation): spatiotemporal 3D adapters injected before the self-attention layers of a frozen ViT vision transformer, combined with a patch-token alignment loss that geometrically grounds the adapted features to keypoint structure through a prototype-conditioned KL-divergence objective. Pre-attention placement allows the frozen attention to reason over temporally enriched tokens, achieving stronger performance with a single adapter per block than post-attention alternatives. The alignment loss shapes the intermediate representations so that each keypoint induces a spatially precise activation in the token field, while the framework adds less than 5% parameters to the frozen backbone. On SPADES dataset, TALON reduces the pose error by 50% over the prior state-of-the-art, and on SwissCube dataset it surpasses the prior best by 21.8% in ADD-0.1d accuracy. Zero-shot cross-domain evaluation from sim-to-real on SPARK real data reduces pose error by 4.7x, and ablations characterise the role of adapter depth across in-domain and cross-domain settings.

Masked Generative Models (MGMs) enable parallel decoding and achieve strong performance across modalities, but require full-sequence bidirectional transformers at every step, making training costly and degrading quality under low sampling budgets. Existing work improves efficiency via better samplers or cheaper fixed-depth denoisers, but they still allocate a fixed amount of denoiser computation to each refinement step. We introduce Fixed-Point Masked Generative Models (FP-MGMs), which replace part of the denoiser with a fixed-point solver over shared attention layers to enable adaptive depth with fewer parameters. To make it more effective for masked generation, we first introduce a cross-step consistency loss, which aligns hidden representations at neighboring denoising steps and, second, three-state reuse (3SR) which warm-starts the solver using the previous solution by treating differently unchanged, still-masked, and newly revealed tokens respectively. Together, these components define our complete training-to-inference framework for fixed-point masked generation, \emph{CoFRe}. We also show that pre-trained MGMs can be converted into FP-MGMs with short fine-tuning, avoiding full retraining. Across modalities, CoFRe improves the quality and cost trade-off. On OpenWebText, CoFRe reduces parameters by 38.8\%, training time by 11.5\%, and VRAM by 16.9\%, while improving generative perplexity from 830.8 to 101.8 at a budget of $96$ transformer-block forward passes, compared to MDLM. In ImageNette, CoFRe reduces training time by 48.6\% and VRAM by 50.7\%, while improving FID in all sample budgets tested. Overall, CoFRe offers a practical framework for cheaper training and stronger low-budget masked generation.

AI systems are increasingly used to support educational content creation, yet it remains unclear whether they can generate outputs that faithfully represent the pedagogical concepts they are intended to teach. Thus, we introduce equation-to-visual generation, a task that, in contrast to conventional image generation, requires producing pedagogically meaningful visuals from arithmetic equations while precisely preserving their numerical and relational structure. Informed by interviews with teachers and an analysis of educational materials, we construct E2V-Bench, a benchmark spanning four pedagogically grounded visual types, along with automatic metrics for evaluating visual correctness. Our evaluation reveals that recent text-to-image (T2I) models frequently fail on this task, with errors dominated by incorrect object counts and broken relational structure. Building on this, we explore benchmark-guided enhancement strategies. These strategies improve representative models, while the remaining gap calls for stronger numerical and relational grounding in future T2I models.

Accurate weather forecasts are essential across various domains and are safety-critical in extreme weather conditions. Compared to simulation-based forecasting, data-driven approaches show greater efficiency, enabling short-term, high-resolution nowcasting. In particular, diffusion models proved effective in weather nowcasting due to their strong probabilistic foundation. However, existing methods rely on deterministic compression to reduce the complexity of high-dimensional weather data, limiting their ability to capture uncertainty in the decoding process. In this work, we introduce $\textbf{FREUD}$, a $\textbf{Fr}$ame-wise $\textbf{E}$ncoder and $\textbf{U}$nited $\textbf{D}$ecoder model based on rectified flow transformers for efficient compression of spatio-temporal weather data. Frame-wise encoding enables continuous forecast updates, while the unified video decoder ensures temporal consistency. Our uncertainty-preserving first stage allows us to capture aleatoric uncertainty via ensembling, which is particularly beneficial for extreme weather events with high decoding variability. We achieve state-of-the-art performance in precipitation nowcasting with a compact latent-space rectified flow transformer on the SEVIR benchmark and show further performance gains by model and test-time scaling. Code available here: https://github.com/CompVis/weather-rf

Safe human--robot collaboration requires more than visual description: a monitor must determine whether the robot body is safely separated, already colliding with the scene or a person, or about to collide. We call this capability collision grounding: binding visual observations to robot body geometry, camera viewpoint, scene layout, human proximity, and temporal motion in order to infer present and imminent contact. We introduce TouchSafeBench, a physics-grounded benchmark for evaluating collision grounding in vision-language models (VLMs). Built in Habitat~3.0, TouchSafeBench contains 2,940 simulated indoor co-presence episodes across social navigation and social rearrangement, with synchronized multi-view RGB-D observations, top-down trajectory maps, calibrated camera metadata, and simulator-derived contact labels. We study two deployment-facing tasks: classifying the current safety state and warning about imminent collision before contact. Across three frontier or robotics-oriented VLMs and nine visual representations, current models remain far from reliable: the best average Macro-F1 stays below 50\%, explicit depth is not automatically transformed into robot-body collision evidence, and robot--scene contact is consistently harder than human-contact risk. TouchSafeBench reveals a central limitation of embodied VLMs: visual fluency does not imply physical accountability. Reliable robot safety monitors will need representations that explicitly bind viewpoint, robot morphology, metric geometry, and future collision. We will release the benchmark upon acceptance.

Recently, thanks to the advent of Multimodal-LLMs, deepfake detectors are striving not only to be generalizable but also interpretable. We propose that these two challenges can effectively be tackled jointly, since describable artifacts typically generalize better, opening the possibility to use language as a regularization mechanism. Since deepfake detection generally suffers from overfitting to low-level domain-specific artifacts, our intuition is that an LLM that has been pretrained on language would prefer high-level artifacts that can be described better. This way, we can use high-level features where possible, while training the model to use low-level features where necessary. We utilize a dual-encoder architecture, pairing a frozen specialist detector with a LoRA-tuned MLLM encoder, and a two-stage training curriculum: first, a binary alignment phase demonstrates that the intrinsic capability of MLLMs can effectively combine features to mitigate overfitting to dataset-specific artifacts. To further bolster generalization and achieve interpretability, we employ a reinforcement learning stage that encourages the model to generate descriptive reasoning before classifying, using only binary labels. By rewarding this "explain-then-classify" behavior, we explicitly incentivize the model to prioritize high-level, robust features. Crucially, this process yields both interpretable descriptions and a further boost in cross-dataset performance, even when reasoning chains are omitted at inference. Extensive experiments on benchmark datasets validate our approach, outperforming state-of-the-art methods by a large margin.

We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effectiveness in ResNet-based image classification on CIFAR-10. Across three teacher-student pairs -- R50->R18, R34->R18, and R50->R34 -- we compare Logit-KD and Feature-KD under controlled, reproducible conditions (3 seeds, mean+/-std reported throughout). We report three main findings. First, student capacity is a key moderating factor in distillation gain: R34 students benefit substantially more from KD than R18 students even when teacher-student accuracy gaps are comparable, with the strongest gain of +0.30pp observed for R50->R34 Feature-KD versus +0.18pp for R34->R18 Feature-KD and +0.00pp for R34->R18 Logit-KD. Second, implementation correctness critically affects Feature-KD: a gradient clipping bug that excluded projection layers suppressed Feature-KD performance and produced misleading comparisons with Logit-KD. After correction, Feature-KD matches or outperforms Logit-KD in two of three pairs, reaching 95.55% on R50->R34 against a baseline of 95.25%. Third, input-resolution-aware architecture is a prerequisite for effective distillation: correcting the ResNet stem for 32x32 inputs raises teacher accuracy by over 5pp -- an order of magnitude larger than any KD gain. All code and results are available at github.com/umutonuryasar/kd-capacity-gap.

Detecting covariate shift is critical for building reliable vision systems. While most prior work focuses on improving robustness to shift, explicitly detecting covariate shift remains underexplored. Existing approaches typically rely on fully supervised training, requiring labeled examples from both original and shifted distributions, which is often impractical. In this paper, we show that covariate shift detection can be effectively addressed with weaker supervision using Positive Unlabeled (PU) learning. However, under covariate shift, in distribution and shifted data overlap significantly, making classical PU methods unstable and sensitive to noise. To overcome this challenge, we introduce Spectral PU Neighborhood Annotation (SPUNA), a geometry aware framework that progressively discovers shifted data by leveraging the local manifold structure of visual features. Extensive experiments show that SPUNA achieves state of the art performance in PU settings and remarkably matches the performances of fully supervised methods. Moreover, our approach transfers robustly across different types of shifts, demonstrating strong generalization capabilities.

Plain Transformers have become the de-facto architecture for processing text, audio, image, and video, offering a unified backbone for multimodal learning. However, state-of-the-art architectures for point cloud semantic segmentation remain dominated by U-Nets architectures where convolutions are interleaved with local or windowed attentions. In this work, we show how to effectively leverage vanilla, non-hierarchical ViTs for segmentation of large-scale automotive lidar scenes. We bridge the performance gap thanks to a carefully designed tokenizer, a lightweight decoder segmentation head, and tailored data augmentations. Our approach, VaViT for Vanilla ViT, matches or exceeds the performance of state-of-the-art methods while maintaining the simplicity of ViT architecture. We provide extensive evaluations on nuScenes, SemanticKITTI, and Waymo Open Dataset to validate the efficiency of our method. Code and models are available at https://github.com/valeoai/VaViT.

Object detection in real-world scenarios remains challenging due to diverse image degradations and heterogeneous object distributions, which significantly hinder the generalization of existing detectors. Conventional approaches, including scene-specific representation learning and end-to-end pipeline design, are inherently limited by their reliance on predefined conditions and lack adaptability to dynamic environments. In this paper, we propose DetAS, an agentic detection framework that formulates object detection as a dynamic decision process. Instead of relying on static pipelines, DetAS leverages a Multimodal Large Language Model (MLLM) as a central agent to adaptively compose detection workflows by selecting from a toolbox of restoration modules and specialized detectors. Specifically, DetAS consists of two key components: Self-Adaptive Image Restoration, which dynamically determines whether and how to enhance images for downstream detection, and Multi-Expertise Detection, which integrates multiple domain-specialized detectors and resolves their predictions through instance-level reasoning. To further improve decision quality under fine-grained conditions, we introduce Self-Evolving Experience Harvesting and extend the framework to DetAS-X, which accumulates node-level decision experience from a small set of annotated data and enables experience-aware reasoning during inference. This mechanism allows the system to progressively refine its decision policy and adapt to diverse real-world scenarios. Extensive experiments on six challenging benchmarks demonstrate that DetAS-X significantly outperforms existing MLLM-based detectors, achieving an average improvement of 28.36% in F1 score, with up to 37.01% gain on DarkFace. These results demonstrate the promise of agentic detection and establish a solid foundation for its application in complex and dynamic environments.

Given the surge of harmful AI-generated imagery online, reliably distinguishing authentic images from generated ones has become an urgent research topic. While many proposed detection methods perform well under controlled settings, they often collapse when tested on real-world data. A potential root cause are subtle biases in the detectors' training data. As a result, detectors may rely on spurious correlations instead of learning true forensic artifacts. While a recent line of work has identified the problem, there is not yet an established protocol to evaluate how biased a detector actually is. In this work, we therefore take a step back: First, we discuss what it means for a detector to be biased, and how this differs from a lack of robustness. Second, we propose BIAS-ID, a transparent framework for analyzing and quantifying the presence of transformation biases in AI-generated image detectors. We validate our framework by performing an evaluation of six detectors across two datasets, revealing that several state-of-the-art detection methods are strongly affected by biases. Our results highlight the importance of bias-aware evaluation for developing reliable AI-generated image detectors.

Humans can effortlessly perceive spatial layouts, form cognitive representations, reason about spatial relations, and translate such reasoning into actions in everyday 3D environments. Although recent vision-language models (VLMs) have shown promising performance on observation-conditioned spatial perception and reasoning tasks, it remains unclear whether they can build coherent spatial understanding, act upon it, and refine their actions through multi-turn feedback. To study this problem, we introduce \textbf{SpatialAct}, a simulator-grounded benchmark for probing \textit{action-conditioned spatial reasoning} in 3D scenes. Starting from the most challenging setting, Multi-turn Interactive Refinement, we further design its decomposed counterpart, Single-step Error Detection and Fix, together with five fundamental spatial ability tasks to diagnose the underlying causes of model failures. Experiments reveal a clear reasoning-to-action gap: current VLMs can perform well on isolated spatial reasoning tasks, but struggle to maintain coherent spatial beliefs and produce reliable actions during multi-turn feedback, substantially underperforming humans. These results suggest that current VLM agents still lack robust spatial state tracking under action-induced environment changes, even when low-level control is abstracted away.

In-context localization (ICL) seeks to localize a target object specified by a small set of support examples in a query image, operating on the fly without training or parameter updates. Despite rapid advances in vision-language models (VLMs), achieving category-agnostic and visually grounded ICL remains an open problem, even though it is essential for applications such as image editing, personalized visual search, and retrieval. Existing methods are fragile and rely on explicit category supervision, which not only limits applicability in realistic settings with unnamed or instance-specific objects but also introduces category bias that steers predictions toward semantic priors rather than visual evidence. We introduce a two-stage training framework that explicitly optimizes in-context attention between support bounding boxes and query images without category supervision. We further refine localization via reinforcement learning using Group Relative Policy Optimization (GRPO) to directly minimize localization error. This formulation enforces visual correspondence over semantic priors, yielding robust instance-level localization. Empirically, a 7B-parameter model trained with our objectives outperforms models up to 72B parameters, demonstrating that context-aware localization objectives can surpass scaling alone. Comprehensive ablations validate the contribution of each component.

Recently, convolutional neural networks (CNNs) have become popular for image classification due to their effectiveness in computer vision tasks. Now, researchers are exploring the potential of vision transformers (ViTs) in remote sensing and Earth observation. However, traditional Real-Valued networks often overlook important phase information in Complex-Valued (CV) data like polarimetric synthetic aperture radar (PolSAR) data. To address this, new CV deep architectures have emerged. HybridCVNet, a novel hybrid network, blends CV-CNN and CV vision transformer (CV-ViT) techniques. It efficiently combines CV 3D and 2D CNNs as feature extractors, enhancing PolSAR image classification by extracting complementary information and effectively leveraging interdependencies within the data. Experimental results from widely-used PolSAR datasets show HybridCVNet outperforms other methods, achieving an overall accuracy of 97.39% on the Flevoland dataset and showing promise even with just a 1% sampling ratio, with a Kappa value of 0.972 on the San Francisco dataset. Source code is accessible through https://github.com/mqalkhatib/HybridCVNet

Estimating 3D attributes directly from images has advanced rapidly with the Visual Geometry Grounded Transformer (VGGT), which predicts camera parameters, depth maps, and point clouds in a single forward pass. However, its 1.2B-parameter scale severely limits deployment on resource-constrained platforms such as UAVs and mobile AR devices. To address this limitation, we introduce QVGGT, a tailored quantization framework designed to compress VGGT. Our approach starts from the observation that transformer blocks within VGGT exhibit heterogeneous sensitivity to quantization. We thus analyze per-block quantization sensitivity and propose a selective mixed-precision strategy that allocates higher precision to the most fragile transformer blocks. To address the amplification of quantization error caused by high-variance camera and register tokens, we further introduce token filtering with camera information compensation, which removes these outliers from activation calibration and restores their geometric cues using a PCA-derived global compensation token. Finally, we develop a task-aware scale search mechanism that evaluates candidate quantization scales not only through layer reconstruction but also through multi-head supervision and cross-head geometric consistency among camera poses, depth maps, and point maps. Extensive experiments on multiple geometry perception benchmarks demonstrate that QVGGT achieves near-lossless W4A16 quantization, preserving the accuracy of all 3D prediction heads while delivering 3$\sim$4.9$\times$ memory reduction and up to 2.8$\times$ real hardware speedup over FP32. Our approach makes high-fidelity 3D perception feasible on edge devices, enabling practical deployment of feed-forward 3D reconstruction models in real-world constrained environments.

Recent perception-free end-to-end (E2E) autonomous driving methods bypass explicit perception outputs by compressing dense image patch tokens into compact scene tokens for downstream trajectory generation and scoring. While these scene tokens form a compact visual bottleneck for the planner, they receive supervision solely from the planning objective, providing limited constraints on the encoded visual information. To address this limitation, we introduce Neural Token Reconstruction (NTR), a representation learning framework to directly constrain the compact scene-token bottleneck in perception-free driving. NTR introduces a self-distillation masked latent reconstruction objective that reconstructs masked patch-level latent features using only compact scene tokens as reconstruction memory. This forces reconstruction gradients to pass exclusively through the scene-token bottleneck, encouraging scene tokens to preserve richer and less redundant visual representations for planning. We further introduce semantic priors derived from foundation-model annotations as a weak semantic interface biasing reconstruction targets toward driving-related structures without introducing explicit perception heads. All auxiliary reconstruction components are removed at inference time, leaving the deployed planner unchanged. NTR achieves state-of-the-art performance on three public autonomous driving benchmarks, including 8.0461 RFS on Waymo E2E and 94.1 PDMS / 90.9 EPDMS on NavSim1&2. The learned scene tokens exhibit lower pairwise redundancy and higher effective rank, indicating that effective bottleneck supervision improves both compact visual representation learning and planning performance.

Dual-hand action segmentation, densely predicting actions for both hands from untrimmed videos, is essential for understanding complex bimanual activities. However, it poses several unique challenges: complex inter-hand dependencies, visual asymmetry between hands, representation conflicts where the dominant hand monopolizes gradients, and semantic ambiguity in fine-grained actions. We propose Polyphony, a three-stage method to address these challenges through: (1) an Alternating Dual-Hand Vision Transformer that alternates training between left- and right-hand mini-batches to ensure balanced gradient contributions from both hands while sharing a spatio-temporal encoder; (2) Semantic Feature Conditioning that aligns visual features with structured, compositional action descriptions to enhance discrimination of semantically similar actions; and (3) Diffusion-Based Segmentation with cross-hand feature fusion for inter-hand coordination and adaptive loss weighting for balancing performance. Polyphony achieves state-of-the-art on both dual-hand datasets (HA-ViD, ATTACH) with improvements up to 16.8 points, and on the single-stream Breakfast dataset (82.5%), outperforming the prior best method that uses a 12x larger backbone. Notably, our unified model with a single shared backbone surpasses baselines requiring separate per-hand models. Code is at https://github.com/x-labs-xyz/Polyphony-Dual-hand-Action-Segmentation.

In this work we introduce a novel approach to domain incremental learning, adapting models over time to evolving, non-stationary data. In contrast to other works, we do not attempt to avoid catastrophic forgetting, but rather allow it and exploit it. Our model combines a main task head with a self-supervised masked autoencoder (MAE) head. We then learn domain-specific LoRA adapters during incremental training. Each adapter specializes to its domain, naturally inducing forgetting on other domains in both heads. At inference, we perform online test-time training on the self-supervised MAE head to identify which LoRAs best matches the current input, so the model can `remember' the domain again. Our scheme is especially well-suited to real-world streaming data, such as video, where consecutive samples are highly correlated and domain shifts are gradual. We demonstrate our method on domain-incremental action recognition and semantic segmentation tasks.

While visually grounded Chain-of-Thought (CoT) has emerged as a promising paradigm to enhance fine-grained perception in multimodal large language models (MLLMs), its efficacy during the inference phase remains underexplored. In this work, we empirically find that mandating explicit object boxes in visually grounded CoT during inference often degrades performance compared to standard textual CoT, which reasons without explicit visual grounding. We hypothesize that the visual localization capability can be internalized into the textual CoT and that the mandatory explicit grounding introduces unnecessary interference with the model's primary objective of answer prediction. To address this problem, we propose Internalizing Visually Grounded Reasoning (\textbf{iVGR}), a novel reinforcement learning framework that transfers localization capabilities into the textual reasoning process. We employ a dual-stream training strategy, where a textual stream is aligned with a high-quality visually grounded stream via a proposed consistency reward, enabling the model to localize accurately without explicit grounding during inference. Extensive experiments demonstrate that our method significantly outperforms existing baselines on fine-grained benchmarks, while maintaining the flexibility to support tool-assisted inference workflows.

The Panoptic Quality (PQ) metric is the standard for jointly evaluating instance and semantic segmentation. However, its original definition relies on a One-to-One matching between predicted and ground truth segments, which is only straightforward when the IoU threshold exceeds 0.5. Below 0.5, multiple matching strategies emerge in a poorly explored problem space. We systematically elucidate this space by recasting segment matching as a constrained bipartite assignment problem. Independently bounding the prediction- and ground-truth-side degrees yields four matching strategies: One-to-One, Many-to-One, One-to-Many, and Many-to-Many. We show that the first three are well-defined within the PQ framework, while Many-to-Many falls outside it. These strategies become relevant when instances are fragmented, adjacent objects are difficult to delineate, or annotations are noisy. Central to our framework is a vertex-based accounting of TP, FN, and FP, anchored to ground truth and predicted segments rather than to matching edges. We further show that the framework extends naturally to part-aware panoptic segmentation, and we explore part-aware evaluation on biomedical data. Across configurable case studies we report how different combinations of thresholds and matching strategies behave in practice. We release a unified open-source package built on Panoptica. It exposes Voronoi-based region-wise analysis, part-aware evaluation, and Area Under Threshold Curve computations as configurable options.

Breast cancer is a major global health concern, and mammography screening plays a central role in early detection. The large volume of screening examinations creates a substantial workload for radiologists, making accurate and consistent report generation a critical clinical challenge. Existing automated mammography report generation methods primarily focus on direct visual-to-text mapping, while overlooking the structured clinical reasoning process followed by radiologists in real-world practice. To address this limitation, we propose MammoRG, a mammography report generation framework that explicitly simulates the clinical reporting workflow by following the BI-RADS guideline and incorporating prior clinical knowledge to produce diagnostic reports. Specifically, MammoRG adopts a two-stage training framework. In the first stage, the model learns to integrate clinically relevant prior knowledge from a patient's four-view mammograms through classification-based supervision. In the second stage, a terminology-aware supervised fine-tuning strategy is introduced to model mammography-specific clinical terms as atomic semantic units, enabling the generation of high-quality reports with improved clinical consistency. To facilitate clinical efficacy evaluation of generated reports, we further develop MammoRGTool, a dedicated mammography report parsing tool that extracts structured clinical information from free-text reports. Extensive experiments demonstrate that MammoRG consistently outperforms existing methods across multiple clinical efficacy metrics, particularly in diagnosis-related BI-RADS F1, where it surpasses the second-best model by 2.73%, 2.04%, 1.90%, and 3.27% on the internal, external 1, external 2, and VinDr-Mammo datasets, respectively.

Mislabeled samples in training datasets severely degrade the performance of deep networks, as overparameterized models tend to memorize erroneous labels. We address this challenge by proposing a novel approach for mislabeled data detection that leverages training dynamics. Our method is grounded in the key observation that correctly labeled samples exhibit consistent entropy decrease during training, while mislabeled samples maintain relatively high entropy throughout the training process. Building on this insight, we introduce a signed entropy integral (SEI) statistic that captures both the magnitude and temporal trend of prediction entropy across training epochs. SEI is broadly applicable to classification networks and demonstrates particular effectiveness when integrated with contrastive language-image pretraining (CLIP) architectures. Through extensive experiments on four medical imaging datasets -- a domain particularly susceptible to labeling errors due to diagnostic complexity -- spanning diverse modalities and pathologies, we demonstrate that SEI achieves state-of-the-art performance in mislabeled data identification, outperforming existing methods while maintaining computational efficiency and implementation simplicity. Our code is available at https://github.com/MedAITech/SEI.

Blind and low-vision (BLV) audiences remain underserved by visual art descriptions, particularly across languages and in museum settings where privacy and intellectual-property constraints may favour small on-premise vision-language models (VLMs). This pilot study investigates curator-guided multilingual art description with Qwen2.5-VL-3B-Instruct for German, Romanian, and Serbian. We construct a parallel BLV-oriented caption corpus from artwork images and metadata, and compare language-specific LoRA adapters with a single multilingual adapter under a fixed backbone and training budget. Evaluation combines automatic lexical and embedding-based metrics with an LLM-as-Judge protocol calibrated against a small Romanian BLV pilot study. Under our pilot setup, language-specific adapters show more stable controllability and visually grounded description quality for Romanian and Serbian, while multilingual adaptation remains competitive in German. We frame these findings as deployment-oriented evidence for small on-premise VLMs, and highlight the need for larger BLV user studies and broader language coverage before drawing general conclusions about multilingual accessibility.

Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning. However, constructing effective memory goes beyond memory module design and basic requirements such as accuracy and fidelity; the key challenge lies in determining what to memorize. Multimodal agents, such as embodied agents, continuously perceive, reason, and act in real or virtual environments, receiving an unbounded stream of multimodal observations. From this combinatorial explosion of information, an agent must selectively retain content that is relevant to its role in the environment and valuable for future tasks. To bridge this gap, we frame memory generation as a learnable memorization policy and introduce TaskMem (Task-focused Memorization Policy Learning), a reinforcement-learning-based framework that enables the policy to dynamically adjust its focus to the demands of real tasks encountered in the environment. TaskMem adopts a two-phase training paradigm: Phase One learns how to memorize by optimizing memory quality under fundamental fidelity requirements; Phase Two occurs after deployment, where the agent learns what to memorize by tuning an adapter on its base MLLM, using recent environment tasks to define a reward model that guides the memorization policy toward task-relevant content. To evaluate our approach, we reformulate VideoMME, EgoLife, and EgoTempo into streaming benchmarks that simulate a realistic setting in which an agent processes streaming observations and handles tasks arriving online. To isolate memory assessment, the questions must be answered using only the agent's memory, without access to raw video. Built on Qwen3-VL-30B-A3B, TaskMem improves VQA accuracy by 6.3%, 7.0%, and 5.3% on these benchmarks, respectively.

Accurately predicting future events is fundamental to content understanding and decision-making across various domains. While prior research has primarily focused on text or short-video scenarios, long-video event prediction, characterized by vast multimodal context and more complex narratives, remains underexplored. Meanwhile, although recent Long-Video Language Models (LVLMs), built on Large Language Models (LLMs) and Vision-Language Models (VLMs), have shown promise in long-video question answering and summarization, they struggle to generalize to event prediction, as they can neither precisely extract event-related details nor perform fine-grained analysis of event development. To address this gap, we propose VISTA, a multi-level event semantics mining framework for long-video event prediction. Initially, VISTA applies a character-centric visual prompt to precisely extract event-related visual details, enhancing detail-level semantics; subsequently, it employs a knowledge-enhanced iterative retrieval strategy, guiding the LLM to progressively construct logically coherent event chains, thereby improving event-level narratives; ultimately, VISTA adopts a human-like propose-then-retrieve strategy to generate diverse future-oriented proposals and integrate multi-level clues, producing robust and accurate predictions. Extensive experiments on real-world datasets validate the effectiveness of VISTA for long-video event prediction.

We introduce HQ-JEPA, a hybrid quantum-classical joint-embedding predictive architecture for cross-modal remote sensing representation learning. The proposed framework extends JEPA-style masked latent prediction to paired Sentinel-1 and Sentinel-2 imagery by predicting masked target representations from visible context regions while aligning heterogeneous modality features in a shared embedding space. To improve representation quality, HQ-JEPA combines four complementary objectives: latent token prediction, cross-modal token alignment, SIGReg-based Gaussian regularization in the fused latent space, and a differentiable SWAP-test-based Fidelity Quantum Similarity (FQS) loss. Unlike pixel reconstruction methods, HQ-JEPA learns semantic representations directly in latent space and uses quantum state-overlap-based similarity as an additional regularization signal. We evaluate the pretrained encoder on GeoBench classification and segmentation tasks under linear probing and fine-tuning settings. Results show that HQ-JEPA achieves competitive and often superior performance over strong self-supervised and remote sensing foundation-model baselines, demonstrating the benefit of integrating predictive self-supervision, cross-modal geometric regularization, and quantum fidelity-based representation learning for remote sensing applications.

Dense self-attention is the compute and quality bottleneck of long-video diffusion inference: cost grows quadratically with the sequence length, and beyond the training horizon the model converges to near-static output, that is, "frozen" repetitive video. State of the art approaches are either too costly, e.g., they require retraining, or fail to satisfy both performance and quality objectives in a scalable manner. To this end, we introduce Long Video Sparse Attention (LVSA), a training-free model-agnostic block-sparse attention for video diffusion transformers that combines a structured window pattern with rotating global anchors, thus removing the fixed-grid bias which causes long-range temporal artifacts. LVSA, combined with a FlashInfer kernel, reduces compute up to 3.17x on Wan 2.1 1.3B at a 6x horizon, 2.98x on Wan 2.1 14B at a 6x horizon, and 3.33x on HunyuanVideo 1.5 at a 1.5x horizon, compared to dense attention. Beyond reducing compute, LVSA enables HunyuanVideo 1.5 generation at a 2x horizon, which is otherwise out-of-memory on a single GPU. Moreover, LVSA provides speedups up to 2.41x compared to RIFLEx and 3.27x compared to UltraViCo on Wan 2.1 1.3B. To demonstrate applicability across diverse platforms, we apply LVSA on NPUs and achieve speedups up to 2.71x on Wan 2.2 A14B and 3.24x on Wan 2.1 1.3B compared to dense attention. To evaluate quality in a fair way, we introduce VQeval, a tool properly scoring loopy video failures, which instead are rewarded in state of the art evaluators like VBench-Long. LVSA is quality-neutral for generation at training horizon length and quality-positive at extended lengths.

Recent crack segmentation methods often follow generic semantic segmentation designs, using stronger backbones, hybrid CNN-Transformer-Mamba encoders, and auxiliary enhancement branches. Although effective, this raises whether stronger generic feature mixing is the most suitable direction for crack segmentation. We instead formulate crack segmentation as sparse structural recovery. Cracks have limited category-level semantics but strong morphological regularities, being thin, sparse, anisotropic, locally fragmented, and easily confused with textures or shadows. Thus, the key bottleneck lies in preserving weak structural evidence, recovering directional continuity, and suppressing background coupling. We propose RIFT, a compact family of morphology-aligned crack segmentation models. Rather than compressing a complex generic architecture, RIFT is simple by design, preserving local evidence, aggregating cooperative directional continuity, and restoring crack structures through lightweight multi-scale fusion. Experiments on four public benchmarks show that RIFT achieves the best or tied-best results across the 16 main metrics against reproduced representative baselines. RIFT-B gives the strongest overall accuracy, while RIFT-T provides the best deployment efficiency with only 0.47M parameters and high inference speed. Topology-aware evaluation, ablations, transfer experiments, and visualizations further verify that task-aligned simplicity can match or surpass complex hybrid architectures when its inductive bias fits crack morphology. Code: https://github.com/xauat-liushipeng/RIFT

Vision-Language-Action (VLA) models have demonstrated promising capability in autonomous driving, highlighting the potential of unified multimodal architectures for jointly modeling perception and planning. However, how current VLA-based driving behavior is grounded in visual information remains poorly understood. Existing evaluation protocols mainly focus on aggregate performance metrics, lacking structured and practical diagnostics to quantify visual-behavior dependency. In this work, we introduce a structured multi-level visual perturbation framework to analyze visual-behavior dependency in VLA-based driving models systematically. The framework organizes controlled visual perturbations along three complementary dimensions: channellevel degradation, information-level disruption, and structurelevel modification. We apply it to VLA-based driving systems and evaluate behavioral responses under both open-loop trajectory prediction and interactive closed-loop safety evaluation. Experimental results reveal evaluation-dependent dependency patterns and uneven visual grounding across abstraction levels. These findings call for more structured analyses and principled design of VLA driving models to better understand how visual information shapes behavior and develop safer, more robust systems.

Streaming video generation models typically rely on temporal-centric memory, which organizes historical context as raw frames, chunk segments, or unclustered tokens. This organization frequently leads to identity drift and semantic inconsistency when entities exit the frame or during interactive prompt transitions. To address these limitations, we propose SlotMemory, an object-centric Key-Value memory mechanism for streaming video diffusion. Our approach shifts the memory abstraction from "when" an event occurred to "what" is being represented by decomposing the transformer's key-value manifold into discrete, reusable semantic slots. By utilizing these slots as routing addresses to index and store high-fidelity key-value tokens, we enable entity-level persistence and prompt-aware retrieval across long horizons. Evaluated on 60-second interactive narratives using the Wan2.1-T2V-1.3B backbone, SlotMemory achieves a state-of-the-art quality score of 81.61 and a 22.8 percent relative improvement in dynamic consistency over the strongest existing streaming baseline. Our results demonstrate that structured semantic representation, rather than raw temporal capacity, is the essential primitive for persistent long-form video synthesis. Our codes and checkpoints are available at https://tj12323.github.io/SlotMemory/.

Video-language models can process only a limited number of frames, making frame selection a key bottleneck for efficient video captioning. Most captioning pipelines still rely on uniform sampling, which is computationally cheap but agnostic to visual content. Adaptive frame sampling has recently emerged as a promising approach for selecting the most informative frames from a video; however, existing methods remain computationally expensive. We introduce PEEK, an efficient dynamic frame sampling method that distills caption-conditioned frame relevance rankings from a stronger teacher model into a lightweight temporal model that operates only on visual content. We find that, overall, on ActivityNet Captions and MSR-VTT, our method outperforms state-of-the-art methods across all evaluated downstream vision language models, especially when only one or two frames are selected for captioning, obtaining the best CIDEr for most frame budgets. On ActivityNet Captions, PEEK is particularly strong, winning 14 out of 16 configurations. Zero-shot evaluation on MSR-VTT shows that our model transfers best at low frame budgets, while results at four and eight frames are more mixed as temporal coverage and visual diversity become increasingly competitive. Compared with recent adaptive baselines, PEEK is both more accurate in the low-budget regime and more efficient: it adds only $5.2\%$ to the captioning time, compared with $65.4\%$ for CSTA and $211.9\%$ for MaxInfo. We release our code and pre-trained checkpoint at https://github.com/momentslab/peek.

Infant biometrics presents unique challenges due to the physiological differences between infants and adults, compounded by the scarcity of available data for research that limits the development of robust matching systems. This paper proposes a novel data augmentation method that uses iterative techniques to generate diverse variants of segmented fingerprints by inducing errors in a convolutional neural network trained to extract fingerprint ridges and valleys. Experiments on real infant fingerprints demonstrate the method's effectiveness in expanding fingerprint variability, with augmentations exhibiting significant fluctuations in minutiae counts while still retaining visual similarity to the originals. The study also highlights the method's customizable nature for applying varying levels of changes to fingerprint segmentations. Future research includes training segmentation and matching neural networks using datasets augmented by the proposed framework.

Inference-time reward alignment steers pretrained diffusion and flow-based generative models to satisfy user-specified rewards without retraining. Recently, Sequential Monte Carlo (SMC) has emerged as a powerful framework for this task by iteratively filtering and propagating multiple particles. However, we show that standard SMC-based methods often suffer from poor performance because they initialize particles from a standard prior, whereas high-reward regions in complex reward landscapes are extremely rare. Further, we show that even recent reward-aware initial sampling approaches remain vulnerable to getting trapped in local modes, as complex reward landscapes are often multi-modal. To overcome these limitations, we propose PATHS (PArallel Tempering for High-complexity reward Sampling), a novel initialization method that couples multiple sampling chains through parallel tempering. PATHS maintains a ladder of reward-tempered chains and periodically performs Metropolis swaps, enabling efficient exploration across flattened reward landscapes, thereby mitigating the mode-trapping issues. Our analysis reveals that this mechanism substantially enhances the finite-budget exploration of rare, high-reward regions that are typically challenging to sample. Experiments on layout-to-image and quantity-aware generation show that PATHS achieves consistent gains in alignment quality, particularly on complex prompts.

The tasks of object removal and inpainting 3D Gaussian Splatting (3DGS) scenes face challenges such as 3D consistency across camera views. In comparing 2D inpainters and their suitability for the 3D domain, we find that reconstruction-based inpainters outperform generative diffusion models in 3D consistency. Integrating these 2D inpainters into different single-step methods for creating and finetuning 3DGS scenes, our results indicate that initializing the scene from scratch produces higher quality results than finetuning the existing scene. Using a state-of-the-art generative 2D inpainter, we create a straightforward baseline to underline the importance of object removal before inpainting in the 3D setting. Since 360° datasets rarely include real-world ground truths, and challenging occlusion scenarios are equally sparse, we introduce a novel multi-object scene with recorded ground truth data and many views with object occlusions.

Modern 3D medical vision-language models (VLMs) can generate fluent radiology-style text while exhibit critically low pathology detection and output diversity, collapsing to generic templates that under-report rare yet critical findings. We identify this failure mode as Template Collapse. This failure stems from the unique constraints of 3D medical imaging, e.g., limited data, severe label imbalance, and weak signals from volumetric encoders. Under these constraints, text-generation objectives encourage shortcut learning and fluent but weakly grounded reports. We systematically diagnose the Template Collapse through clinical fidelity, output diversity, normal-template bias, and rare-finding survival. To mitigate it, we propose CLarGen, a decoupled framework that separates what to say (clinical detection) from how to say it (language synthesis). CLarGen uses (i) a Latent Query Transformer for multi-label pathology detection, (ii) pathology-guided retrieval for clinically matched exemplars, and (iii) a medical language model to synthesize the final report from detected findings and retrieved context. Across state-of-the-art 3D CT report generation baselines, CLarGen mitigates Template Collapse and substantially improves clinical accuracy (macro-F1 0.487 vs. 0.189; CRG 0.472 vs. 0.368) while maintaining fluent reporting. Our results suggest that explicit, measurable clinical grounding is essential for template-collapse-resistant 3D CT report generation. Code will be released upon acceptance.

Despite the remarkable success of multi-modal bird's-eye view (BEV) perception in autonomous driving, current systems exhibit a critical vulnerability: existing fusion mechanisms are highly brittle to sensor corruptions, often causing catastrophic performance degradation. This vulnerability largely stems from the fact that standard fusion frameworks typically integrate multi-modal representations in a static manner, leading to a precipitous performance collapse under missing or corrupted modalities. In contrast, we show that graceful degradation is achievable through active modality reliability assessment. To this end, we present Grace-BEV, a lightweight and plug-and-play framework that enforces active reliability awareness during multi-modal fusion. Instead of relying on computationally expensive cross-modal interactions, Grace-BEV leverages the aligned BEV space to explicitly assess modality trustworthiness via a TrustGate Router and dynamically recalibrate feature integration using the FailSafe Fusion Block. Furthermore, we devise a Three-Phase Training strategy with Modality Dropout to prevent modality dominance and encourage balanced cross-modal learning under unreliable inputs. Extensive experiments on nuScenes-R and nuScenes-C show that Grace-BEV maintains robust performance across diverse corruption settings. Notably, under catastrophic LiDAR failures where standard baselines collapse to 0.0% mean Average Precision (mAP), Grace-BEV restores performance to as high as 34.7% mAP. Moreover, it improves clean accuracy by up to 1.4%, achieving a strong trade-off between robustness and efficiency.

Accurate 3D medical image segmentation requires both long-range volumetric context and fine boundary preservation. CNN-based methods have limited global dependency modeling, while Transformer-based models are often computationally expensive for dense 3D inputs. Recent Mamba-based methods provide an efficient alternative, but existing volumetric designs still depend on repeated high-resolution scanning, forward-only sequential modeling, and fixed directional summation, causing high cost, scan-order bias, and suboptimal directional aggregation. We propose BiSegMamba, an efficient bidirectional tri-oriented Mamba network for 3D medical image segmentation. BiSegMamba follows a compact-to-detail design, where a progressive compacting stem (PCS) enables efficient latent-space reasoning while retaining shallow high-resolution features for reconstruction. A multi-scale spatial mixer (MSSM) captures local anatomical patterns in early stages, and the proposed bidirectional tri-oriented Ortho Mamba (Bi-ToOM) block models long-range dependencies from multiple orthogonal views using jointly processed forward and backward scan sequences. Adaptive directional fusion (ADF) learns input-dependent channel-wise weights across scan orientations, replacing fixed summation with orientation-aware fusion. Experiments on a collected carotid CTA dataset and three public benchmarks, BraTS2023, ACDC, and AMOS-CT, show that BiSegMamba generalizes well across vascular, cardiac, brain tumor, and abdominal multi-organ segmentation tasks. Compared with SegMamba-V2, BiSegMamba achieves slightly better performance on BraTS2023 and clear improvements on ACDC and the carotid dataset, while reducing computational cost by up to 77.9% FLOPs, demonstrating a strong accuracy-efficiency balance for general 3D medical image segmentation.

Text-based human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the consistency of the original motion. Existing diffusion-based approaches often rely on heuristic similarity cues or coarse global conditioning, leading to motion distortion and suboptimal semantic alignment. The key challenge lies in balancing change (i.e. precisely editing target regions) and invariance (i.e. preserving unedited parts). To handle such challenge, we propose an Omni-Supervised Positive-Negative Learning framework, named OmniME. Our method integrates three complementary components: (1) retrospective feature supervision that enforces coarse-to-fine consistency across transformer layers,(2) motion preservation mechanism that focuses on subtle variations according to the source-target similarity, and (3) triplet-based semantic alignment that strengthens text-motion correspondence. Together, these components form a unified supervision paradigm that balances change and invariance. Extensive experiments on the MotionFix and STANCE Adjustment datasets demonstrate that OmniME achieves state-of-the-art performance in editing alignment, validating the effectiveness of our unified learning framework. Our source codes and models have been released at: https://github.com/rocket-ycyer/OmniME.git

The core of vision-language models lies in measuring cross-modal similarity within a unified representation space. However, most image-text matching or multi-class image classification datasets lack fine-grained cross-modal matching annotations, forcing the continuous similarity space into binary classification boundaries. This compression induces false negative samples and significantly impairs the generalization performance of cross-modal tasks. While prior research has attempted to mitigate this by modeling intra-modal ambiguity, it often overlooks inherent annotation flaws, leading to suboptimal uncertainty allocation. To address these challenges, we propose a Variational Adapter for Cross-modal Similarity Representation (VACSR). This approach reformulates image-text matching with fine-grained semantic scarcity as a variational inference problem. It constructs a latent space for cross-modal similarity and uses regularization techniques to mitigate overfitting to binary annotations. Experiments on image-text retrieval, domain generalization, and base-to-novel generalization demonstrate the proposed method's effectiveness and robust generalization ability.

Modern vision models process images in a single feed-forward pass, which limits their ability to recover missing evidence or refine uncertain representations under incomplete observations. Inspired by the iterative nature of human perception, we introduce PRISM (Progressive Reasoning through Iterative Slot Memory), a pyramid vision architecture that reasons over images through iterative refinement. At a high level, PRISM groups visual features into object-centric representations, retrieves relevant patterns from a learned memory, and iteratively refines the representation to resolve ambiguity and recover missing information. This organize-recall-refine process operates recurrently across multiple scales, enabling progressive improvement of visual representations. Across standard vision tasks, including image classification, object detection, and semantic segmentation, PRISM achieves competitive performance while demonstrating improved robustness under incomplete observations such as occlusion. These results suggest that iterative reasoning with structured representations and memory is a promising direction for building more resilient and adaptive vision models. Source code and models will be released.

Semantic road segmentation is important for autonomous driving, but existing methods suffer severe performance degradation under low-light conditions. Many existing multi-modal fusion methods do not explicitly adapt to illumination-dependent changes in modality reliability, which can propagate degraded RGB features into the fused representation at night. We propose IAF-Net (Illumination-Adaptive Fusion Network), an end-to-end framework with illumination-adaptive fusion for robust road segmentation across different lighting conditions. It dynamically adjusts fusion weights of RGB and geometric features via the core Illumination-Adaptive Fusion (IAF) module, and enhances low-light feature selection with a brightness-modulated attention decoder. We also construct two dedicated datasets: nuScenes Nighttime Road Segmentation (nuScenes-NRS) and CARLA Multi-Weather Road Segmentation (CARLA-MWRS). Experiments on nuScenes-NRS show state-of-the-art overall performance among the compared methods, while CARLA-MWRS further validates robustness across adverse weather conditions. Ablation studies on a 40% training subset further highlight the importance of the IAF module, which provides the largest individual gain of 0.70% in MaxF.

Text-to-motion generation has progressed rapidly in recent years, offering an expressive interface for animation and human-computer interaction. However, current models remain brittle when handling prompts that describe multiple actions occurring at the same time. Rather than realizing all components of a composite description, models frequently prioritize a single dominant action and neglect the rest, leading to incomplete or ambiguous motion. We present MultiAct, an unpaired, inference-time framework for compositional text-to-motion synthesis that operates directly on pretrained motion generators without retraining or architectural modification. Our method counteracts semantic collapse by adaptively amplifying cross-attention scores associated with underrepresented prompt components. We note that effective modulation depends on prompt-specific choices, such as which tokens and layers to target, and introduce a lightweight auxiliary decision scheme that determines the most effective attention-strengthening parametrization. Extensive quantitative and qualitative evaluations demonstrate that MultiAct consistently outperforms existing baselines on composite prompts, achieving improved semantic coverage while preserving motion realism. Project page: https://natsala13.github.io/multiact.github.io.

As large-scale visual-document corpora such as arXiv papers and enterprise PDFs continue to grow, visual-document retrieval has gained increasing attention; yet it still lacks a deployable system that lexically indexes visual documents to serve queries without neural encoding at scale. Existing methods either achieve strong retrieval quality with VLM-based dense or multi-vector models but require neural query encoding at serving time, or avoid query encoding with OCR- or caption-based BM25 at the cost of time-consuming text extraction or generation. To fill this missing serving regime, we present V-SPLADE, an inference-free sparse retriever for visual-document retrieval. However, such inference-free multimodal learned sparse retrieval systems remain underexplored and have not yet shown dense-level effectiveness under high sparsity. We attribute this limitation to a lexical grounding problem: visual sparse representations often fail to capture the lexical content embedded in document images. To address this problem, we introduce caption-gated token supervision, a training-only signal that uses VLM-generated captions as lexical cues to activate retrieval-relevant vocabulary dimensions. With this supervision, V-SPLADE improves average NDCG@5 across six visual-document retrieval benchmarks by +13.8pp over the same-scale dense baseline and by up to +6.3pp over OCR- or caption-based BM25 baselines. On an 18.7M-document corpus, it more than doubles R@5 over the same-scale dense baseline and further improves competing retrievers through score fusion by up to +2.4pp R@5. Code will be released soon at https://github.com/naver/v-splade.

Reinforcement learning with verifiable rewards (RLVR) improves vision-language models (VLMs) by optimizing outcome rewards derived from final answers. However, such outcome-only rewards do not tell the model which image regions justify an answer. For questions that require visual grounding, these rewards cannot distinguish responses supported by relevant visual evidence from those produced by language-prior shortcuts or lucky guesses. We introduce EASE (Evidence-Anchored Spatial Attention), which augments multimodal RLVR with visual-evidence process supervision. EASE converts annotated evidence regions into a smoothed visual-token target and uses it to guide response-to-image attention during RL training, but only on high-reward trajectories. The annotations are used solely as privileged training labels, while inference requires only the original image and question. Across Qwen2.5-VL-7B, Qwen3-VL-4B, and Qwen3-VL-8B, EASE raises average scores over DAPO by 2.5 to 3.1 points on perception, hallucination, visual math, and multimodal reasoning benchmarks. Diagnostics and ablations show that EASE better aligns visual attention with annotated evidence regions.

Hallucination remains one of the key challenges undermining the reliability of Large Vision-Language Models (LVLMs). But what makes an LVLM hallucinate less? Many existing efforts focus on improving internal components of the model. We argue that hallucination fundamentally stems from how the model architecture is designed. To investigate this, we factor the architecture design into three dimensions: Linguistic Foundation (LF), Visual Representation (VR), and Semantic Alignment (SA), and categorize hallucinations into Co-occurrence, Similarity, and previously overlooked Uncertainty types. Building on this formulation, we propose CoSimUE, a benchmark that creates fine-grained hallucination scenarios through controlled textual perturbations and random perturbations, enabling mapping between design choices and hallucination behaviors. Experiments across 7 design aspects show that: 1) the widely emphasized scaling of model parameters has only limited impact on reducing all three types of hallucinations; 2) larger and better-trained language foundations can reduce co-occurrence hallucinations; 3) stronger visual encoders and higher resolutions mitigate similarity errors; 4) effective alignment strategies alleviate uncertainty hallucinations. 5) Furthermore, cross-dimensional analysis reveals that jointly enhancing visual fidelity and alignment quality yields the most comprehensive improvements. This study provides the first systematic exploration linking architecture-level design to hallucination robustness, offering practical guidance for developing reliable and efficient LVLMs.

Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconstruction but suffer from dense, entangled latents that are poorly suited for semantic control, whereas discrete VQ-based models enable autoregressive generation yet struggle with gradient sparsity, unstable training, and codebook collapse. In this work, we introduce MergeTok, a unified tokenizer that jointly optimizes continuous (VAE) and discrete (VQ) tokenizers within a encoder-decoder architecture, leveraging token merging techniques as a semantic bridge. By clustering similar tokens during encoding, MergeTok establishes a structural prior that provides dual supervision signals: (i) it imposes merged-token semantic alignment in the VAE branch, regularizing its latent space toward disentangled, semantic-aware representations; (ii) it derives group-wise constraints, promoting intra-group diversity and inter-group exclusivity that stabilize VQ training. MergeTok shows competitive reconstruction and generation performance on ImageNet-256, with substantially lower rFID than strong VAE and VQ models under matched token budgets, while producing semantically-organized token representations compatible with both autoregressive and diffusion generators. This shows that a single architecture can endow visual tokenizers with robust semantic organization and generator-friendly discreteness.

The shortage of legally compliant data for face recognition training has sparked growing interest in using synthetic data as an alternative. While recent diffusion-based methods enable the generation of photorealistic face images with strong identity adherence and data diversity, their downstream recognition performance still exhibits a significant synthetic-real gap. This paper identifies visual tendency as a previously underexplored limitation, whereby synthetic data exhibit an unrealistic prevalence of visual attributes and thus deviate from the real-data distribution. Visual tendency can be attributed to the generator's conditioning on identity embeddings, through which co-occurring residual visual cues are unintentionally absorbed into learned identity semantics. To discourage the generator from exploiting such visual cues, this paper proposes SteerFace, a simple and efficient training framework that perturbs identity embeddings by steering them toward random orthogonal directions on the embedding hypersphere. The perturbation serves as an identity-preserving regularizer that penalizes the generator's reliance on non-identity components, as supported by theoretical analysis. This paper further introduces an adaptive strategy that learns perturbation strengths with both sample-wise preference and favorable overall statistics. Extensive experiments show that SteerFace effectively mitigates visual tendency, outperforms prior methods in downstream face recognition, and generalizes well across different training datasets and generation pipelines.

Variational autoencoders (VAEs) compress high resolution CT volumes into compact latents while preserving clinically relevant structure. However, training CT-specific VAEs from scratch or heavily fine-tuning them incurs substantial computational and engineering cost, and often degrades under heterogeneous scanners, protocols, and diseases. This paper makes a progressive stride toward training-free medical VAEs by leveraging a critical observation: a single Foundation VAE, pretrained at scale on natural images and videos, can serve as a unified interface for CT Reconstruction, Augmentation, and Generation. With both encoder and decoder frozen, the Foundation VAE reconstructs CT volumes with preserved anatomy while suppressing acquisition noise; training segmentation models on these reconstructions improves surface accuracy by 3.9% NSD on average for pancreatic tumor and lung tumor. Within the same Foundation VAE latent space, a conditional latent diffusion model achieves 3.9% lower average FVD with 36.2% higher CT CLIP score, and improves multi-disease generation faithfulness across 18 types by 2.76% AUC. These results demonstrate Foundation VAEs as a practical interface for scalable CT representation reuse and faithful CT generation. Our code and demo are available at https://github.com/qic999/Foundation-VAE.

Existing agentic reinforcement learning methods for GUI grounding have limitations at two levels. At the data level, current approaches typically treat all training samples equally, although their training value to the baseline model varies with difficulty. Overlooking this can greatly reduce training efficiency or even cause collapse. At the strategy level, existing frameworks struggle to balance the trade-off between cropping larger regions for sufficient context and smaller ones for reduced redundancy, a tension inherent to tool-augmented grounding agents. In addition, overly complex decision-making is difficult for small-parameter models and significantly increases inference time. To address these issues, at the data level, we propose GUI-D, a data mining and difficulty scoring pipeline that identifies the training-worthy samples by proper testing and assigns difficulty scores to guide subsequent training weights. At the strategy level, we propose GUI-C$^2$, which employs an area-gated coarse-to-fine refinement mechanism that progressively narrows the visual field via model-internal uncertainty signals, adaptively reserving context for large targets while amplifying precision for small ones, reinforced by improvement-aware stage rewards that ensure each refinement genuinely advances grounding. Meanwhile, we simplify the decision-making process to greatly reduce additional inference time. Finally, extensive experiments show that our method achieves state-of-the-art performance. The code and data will be publicly available.

Dynamic scene reconstruction and novel view synthesis are fundamental to next-generation visual intelligence applications such as virtual reality, robotics, and digital twins. However, high-fidelity reconstruction of complex, time-varying scenes from arbitrary viewpoints remains a significant challenge. Existing dynamic 3DGS methods suffer from computational inefficiency, since they model all Gaussians as dynamic components. While recent decomposition-based approaches address this issue, they still struggle with degraded reconstruction quality and prolonged training time. To mitigate these limitations, we propose a novel dynamic reconstruction framework built upon an efficient static-dynamic decomposition strategy using a Feed-Forward Gaussian Splatting encoder and an optical flow model. By eliminating redundant computations on static regions, our method achieves state-of-the-art performance, outperforming existing baselines across rendering quality, training and rendering speed, and storage efficiency. Notably, on the Neural 3D dataset, our framework requires only 10 minutes for training and achieves a rendering speed of over 700 FPS on a single NVIDIA RTX 5090 GPU at resolution of 1352x1014. Furthermore, our decomposition strategy eliminates the need for COLMAP preprocessing and enables deterministic initialization, thereby enhancing both efficiency and reproducibility.

Object counting remains fragmented across domain-specific datasets and task formulations, despite rapid progress in generalist vision models. Existing counting models are often tailored to scenarios such as crowds, vehicles, cells, crops, or remote-sensing objects, and thus struggle to generalize across categories, visual domains, object scales, and density distributions. In this paper, we study text-guided object counting across domains, where a model takes an image and a natural-language query as input and returns an instance-grounded set of target points whose cardinality gives the count. This formulation unifies category-conditioned counting with interpretable spatial localization. To support this setting, we construct CLOC, a Cross-domain Large-scale Object Counting dataset that reorganizes diverse public data sources into a unified benchmark. CLOC covers six visual domains: General Scene, Remote Sensing, Histopathology, Cellular Microscopy, Agriculture, and Microbiology, with about 220K images, 619 categories, and 15M object instances. Based on CLOC, we propose Count Anything, a generalist model for text-guided object counting. Unlike density-map-based methods, which dominate counting models, Count Anything adopts discrete instance points and performs dual-granularity instance enumeration. A Region-level Sparse Counter provides object-level anchors for large and sparse targets, while a Pixel-level Dense Counter handles small, crowded, and weakly bounded targets via dense point prediction. A point-centric supervision strategy enables learning from heterogeneous annotations, and Complementary Count Fusion combines both counters in a parameter-free manner. Extensive experiments show that Count Anything achieves strong accuracy and multi-domain generalization, outperforming existing open-world counting methods. Code is available at: https://github.com/Mengqi-Lei/count-anything.

Lower extremity computed tomography (CT) contains clinically relevant information for body composition analysis, sarcopenia assessment, and musculoskeletal disease monitoring, but extracting these measurements at scale requires accurate tissue segmentation and an automated quantification workflow. Existing public segmentation tools are not designed for comprehensive lower extremity CT analysis, particularly for clinically important inter/intramuscular adipose tissue, and most public methods only provide mask prediction rather than an end-to-end quantification system. To address this problem, we present LegSegNet, a deep learning system for lower extremity CT tissue segmentation and body composition quantification. Given an input CT scan, LegSegNet segments bone, skeletal muscle, subcutaneous adipose tissue, and inter/intramuscular adipose tissue. It then computes quantitative tissue measurements for downstream analysis. We developed the segmentation model using 1,302 manually annotated CT slices and evaluated it on 900 held-out test slices, with all annotations reviewed by radiologists. We benchmark LegSegNet against a broad set of 2D segmentation methods, including CNN-based models, transformer-based models, and finetuned foundation models, and further evaluate its generalization on an external public CT dataset. LegSegNet achieves the best overall segmentation performance, with an average Dice score of 89.31 on the held-out test set. To our knowledge, LegSegNet is the first publicly available end-to-end system for lower extremity CT tissue segmentation and quantification, providing a practical evaluation tool for future computer vision research in medical image analysis. The code and model weights are available at: https://github.com/mazurowski-lab/LegSegNet

Multimodal Large Language Models (MLLMs) have demonstrated significant achievements in general visual question answering (VQA) tasks. However, they remain brittle on mechanical engineering drawings, where high annotation density and weak domain knowledge, compounded by unreliable spatial relation reasoning under strict projection rules and geometric constraints, make decisive cues easy to miss and frequently lead to wrong answers. To bridge this gap, we introduce the first comprehensive mechanical drawing understanding dataset, MechVQA, created through a semi-automated construction and quality-control pipeline. MechVQA contains 3.3k high-density pictures with 21K question-answer pairs, spanning 10 different fine-grained tasks across three capability levels: Recognition, Reasoning, and Judging, providing a testbed to evaluate and improve MLLM understanding on real-world mechanical drawings. On top of MechVQA, we then develop the MechVL model through a multi-stage training paradigm, building a strong domain-specialized baseline. Extensive experimental results demonstrate that MechVL outperforms the strongest closed-source baseline by 7.57 percentage points on the MechVQA total score, significantly enhancing mechanical drawing understanding ability and providing a reusable foundation for deploying MLLMs in mechanical design and inspection scenarios.

Gait recognition is a biometric technique that identifies individuals based on their walking patterns, offering advantages in long-range, non-intrusive scenarios. However, real-world scenarios often involve heterogeneous sensing modalities such as LiDAR and RGB cameras, making LiDAR-Camera Cross-modal Gait recognition (LCCGR) a critical yet challenging task due to the substantial modality gap between 2D videos and 3D point cloud sequences. To address this challenge, we propose TCFDNet, a Text-guided Cross-modal Feature Disentanglement Network, which leverages modality-aware textual priors as semantic anchors to guide the learning of disentangled modality-shared representations. Specifically, we construct a Gait Modality Text Dictionary (GMTD) using large language models to generate rich semantic descriptions of gait across modalities and viewpoints. A CLIP-based Multi-grained Feature Encoder then aligns visual and textual features within a unified vision-language space. Furthermore, the Text-guided Feature Disentanglement (TFD) module selects the topk matched textual descriptions to reconstruct modality-specific representations and derive modality-shared features via residual decomposition and orthogonality constraints. To mitigate the fragility of the disentangled shared features, we propose a Feature Stability Enhancement (FSE) module, which models spatial and channel-wise correlations to improve feature robustness. In addition, a cross-modal patch exchange strategy is introduced to further improve generalization. Extensive experiments on SUSTech1K and FreeGait datasets demonstrate that TCFDNet achieves new state-of-the-art results and validate the effectiveness of the proposed modules.

Precise camera pose control is critical for video diffusion, yet maintaining geometric consistency remains a challenge. Existing methods that directly inject numerical camera parameters into the diffusion backbone often fail to bridge the gap between abstract coordinates and visual content, leading to structural distortions. To address this issue, we propose CameraNoise, a flow-to-noise warping method that encodes camera motion into a temporally coherent stochastic representation. Unlike conventional conditioning, CameraNoise embeds camera poses directly into the noise space. This decouples motion from scene appearance while faithfully preserving trajectory dynamics. Specifically, we introduce a novel Geometry-guided Reprojection Flow and a noise warping algorithm, which jointly preserve the Gaussian prior of diffusion and ensure consistent noise propagation under camera transformations. By integrating CameraNoise into the diffusion process, our framework delivers stable, high-fidelity videos. Extensive experiments demonstrate that our approach significantly outperforms prior methods in both visual quality and trajectory faithfulness. The project page and code are available at: https://gulucaptain.github.io/CameraNoise/.

A key challenge in Visual Place Recognition (VPR) is matching query images against reference maps captured under diverse environmental conditions and viewpoints. While multiple reference traversals improve robustness, existing fusion strategies either aggregate references uniformly or rely on heuristic selection, without distinguishing descriptor variations that preserve stable place identity from those caused by changing conditions or viewpoints. In this paper, we propose DisPlace, a multi-reference VPR framework that fuses multiple reference descriptors into a single compact and discriminative place representation. DisPlace formulates descriptor fusion as a generalized eigenvalue problem that maximizes between-place separability while suppressing within-place variation across references, rather than preserving overall descriptor variance. Unlike existing multi-reference fusion methods, DisPlace exploits variation across reference traversals to identify which linear combinations of descriptor dimensions preserve place identity and which capture condition- or viewpoint-specific variation. We evaluate DisPlace on Oxford RobotCar, Nordland, Pittsburgh30k, and Google Landmarks v2 across six state-of-the-art VPR descriptors. DisPlace outperforms seven multi-reference baselines in 49 out of 54 appearance-varying conditions, consistently improves descriptor-level fusion performance under viewpoint and unstructured settings, and requires less storage during inference than all compared fusion methods.

In the era of Large Video-Language Models (LVLMs), the computational necessity of sparse frame sampling creates a fundamental ``temporal gap'', rendering models blind to critical causal transitions. Existing solutions relying on generative hallucination (e.g., latent diffusion) or autoregressive extrapolation often fail to maintain semantic consistency over long horizons, suffering from object vanishing and energetic instability. We propose a paradigm shift from probabilistic generation to variational mechanics with the \textbf{Semantic Least Action Principle (SLAP)}. Drawing a rigorous isomorphism between classical mechanics and semantic dynamics, we model the latent video trajectory as a path on a Riemannian manifold governed by a Semantic Lagrangian. By formulating the interpolation task as a Boundary Value Problem (BVP) solved via the discrete Euler-Lagrange equations, SLAP naturally enforces object persistence without pixel-level rendering. Extensive experiments show the effectiveness of our proposed SLAP.

Large Vision-Language Models have achieved unprecedented success in zero-shot recognition by aligning visual features with broad semantic concepts. However, this semantic abstraction creates a critical vulnerability in open-world deployment: the ``Hubris of Semantics'', where models force-fit unknown anomalies into known categories with high confidence due to the lack of explicit negative knowledge. To address this \textit{Open-World Trustworthiness Paradox}, we propose \textbf{Immuno-VLM}, a bio-inspired framework that adapts the biological principle of \textbf{Immunological Negative Selection} to high-dimensional latent spaces. Departing from traditional Open-Set Recognition methods that rely on passive density estimation or inefficient pixel-space outlier generation, Immuno-VLM leverages the generative reasoning of Large Language Models to actively hallucinate ``Semantic Antibodies'', textual descriptions of near-distribution outliers (e.g., look-alikes, contextual anomalies) that effectively bound the decision space of known classes.Extensive experiments on ImageNet-1K and four challenging OOD benchmarks reveal that Immuno-VLM establishes a new state-of-the-art.

This paper addresses the task of temporal sentence grounding (TSG). Although many respectable works have made decent achievements in this important topic, they severely rely on massive expensive video-query paired annotations, which require a tremendous amount of human effort to collect in real-world applications. To this end, in this paper, we target a more practical but challenging TSG setting: unsupervised temporal sentence grounding, where both paired video-query and segment boundary annotations are unavailable during the network training. Considering that some other cross-modal tasks provide many easily available yet cheap labels, we tend to collect and transfer their simple cross-modal alignment knowledge into our complex scenarios: 1) We first explore the entity-aware object-guided appearance knowledge from the paired Image-Noun task, and adapt them into each independent video frame; 2) Then, we extract the event-aware action representation from the paired Video-Verb task, and further refine the action representation into more practical but complicated real-world cases by a newly proposed copy-paste approach; 3) By modulating and transferring both appearance and action knowledge into our challenging unsupervised task, our model can directly utilize this general knowledge to correlate videos and queries, and accurately retrieve the relevant segment without training. Extensive experiments on two challenging datasets (ActivityNet Captions and Charades-STA) show our effectiveness, outperforming existing unsupervised methods and even competitively beating supervised works.

Malaria remains a leading cause of mortality in sub-Saharan Africa, where scarce diagnostic infrastructure makes timely, accurate diagnosis particularly challenging. While deep learning offers a compelling path toward automated malaria screening, clinical adoption is hindered by computational cost and opacity in decision-making. This work benchmarks four deep learning models spanning a wide range of designed design architectures and model capacities on the NLM-Malaria dataset, jointly evaluating predictive performance, robustness, and post-hoc explainability. We find that lightweight, efficient-by-design models match their heavier counterparts in predictive performance, and the Friedman test confirms no statistically significant performance differences. CAM-based XAI methods consistently localize diagnostically relevant regions, while fine-grained attribution methods produce less targeted explanations, particularly with heavier backbones. Robustness evaluation under three types of image corruption further reveals that model confidence degrades faster than accuracy, providing a practical signal for human review. However, no XAI method is robust to corruption, with explanation reliability degrading at noise levels plausible in clinical practice, even when predictions remain accurate. These findings support the deployment of lightweight architectures for malaria diagnosis in resource-constrained settings, while highlighting the vulnerability of post-hoc explanations as an important consideration for responsible clinical deployment.

Generating clinically useful pathology reports for pathology cases from whole-slide images (WSIs) is challenging due to gigapixel resolution, long visual-token sequences, and the complexity of case-level reasoning, where a single case may contain multiple WSIs with heterogeneous tissues and ambiguous findings. We present a simple token-efficient vision--language model for case-level synoptic report generation that remains practical under constrained GPU memory. Our architecture follows a minimal three-component design: a frozen pathology patch encoder, a lightweight two-layer MLP vision-language aligner, and a large language model decoder, with an explicit WSI marker token to separate slides within a case. Training proceeds in two supervised stages: (1) aligner-only WSI captioning using heterogeneous WSI-text pairs, and (2) case-level supervised fine-tuning on case-report pairs for structured report generation. To reduce sequence length, we represent each slide using $512 \times 512$ patches at $5\times$ magnification, which reduces the average sequence length by up to $64\times$ times compared to the commonly used $20\times$ patches. Combined with efficient training techniques, we enable practical training with only half a NVIDIA H100 GPU. Across both training stages, our approach achieves high ROUGE-L/METEOR/BLEU-4 scores while being substantially more efficient in memory and runtime. In AI-based evaluations, our model is consistently preferred over strong baselines. Extensive ablations characterize performance-efficiency trade-offs and identify simple choices that improve robustness in multi-WSI settings. Overall, this work provides a strong, reproducible baseline for efficient pathology report generation, lowering the barrier to multi-WSI VLM research under limited compute.

Urban villages, the widespread informal settlements which have emerged as a result of rapid urbanization, are now major residential hubs for migrant workers in large cities in China. The dense arrangement of buildings in these areas often leads to unreliable GPS signals, while incomplete mapping data further impairs accurate route planning and navigation. These issues not only hinder everyday mobility but also pose significant challenges for emergency response, as confusing road layouts and GPS inaccuracies can complicate evacuation efforts. To address these challenges, we propose a practical vision-based geo-localization solution tailored for dense urban environments. Our approach features a low-cost data collection pipeline utilizing a dual-camera system, comprising a panoramic camera and a smartphone camera, to capture synchronized 360-degree panoramas and query images. Using Shipai Village, a well-known densely populated urban village in Guangzhou, as a case study, we develop a specialized image geo-localization dataset. We then assess and compare the performance of existing models across various scene types to identify their strengths and weaknesses. The findings demonstrate both the potential and limitations of visual-based localization in dense urban-village environments. Our framework aims to enhance pedestrian navigation, last-mile delivery, and emergency management in areas with poor GPS coverage, ultimately supporting the vulnerable populations living within these informal settlements.

Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their application and benefits for vision-language models (VLMs) remain underexplored. We present a systematic study of TTC across seven VLMs and six benchmarks, specifically analyzing feature-based scoring and majority voting methods. We find that feature heuristics fail and voting yields only modest gains in single-model settings. We theoretically show that this limitation stems from a lack of prediction diversity: when outputs are highly correlated, voting provides little benefit. In contrast, multi-model ensembles offer richer diversity, yet standard majority voting fails to account for varying model capabilities. To address this, we propose Entropy-based TTC (ETTC), which selects the most confident prediction based on predictive entropy. Our method reduces to majority voting in the single-model case, but in model ensembles, it leverages confidence disparities to prioritize stronger models. We prove that ETTC outperforms majority voting under mild assumptions and empirically demonstrate that it consistently surpasses both voting and the best individual model. Crucially, our results show that smaller models can synergistically enhance larger ones, unlocking ensembling gains not achievable with standard strategies.

This work introduces mathematical morphology-an established visual computing theory-into machine learning to exploit shape and density aspects often overlooked by standard techniques. We propose a fast clustering algorithm based on morphological reconstruction that accurately preserves cluster shapes and density. This scheme offers unique features: an intrinsic sense of maximal clusters, cost-free noise removal, and diverse growth patterns controlled by structuring elements.Additionally, we propose a novel distance metric combining Minkowski and Chebyshev distances, highly efficient for morphological dilations. In $Z^2$ discrete neighbourhood iterations, it is roughly 1.3 times faster than Manhattan and 329.5 times faster than Euclidean distances. When evaluated using a k-Nearest Neighbours (k-NN) classifier across 33 UCI datasets against 14 other distances, our metric achieved above-average accuracies most frequently (26 of 33 cases) and the best overall accuracy in 9 cases.Finally, we introduce novel morphological classifiers. Unlike current literature, this proposal uniquely models shape, density, and fractal information in datasets.

This work proposes a context-aware middleware for medical workflow organization and efficiency improvement. In hospitals, laboratories and teleradiology companies, each physician or technician is specialized in a specific kind of diagnosis or analysis. Therefore, certain types of medical images are often forwarded to a certain physician or a certain group. This forwarding is time consuming. That is, repeatedly deciding who would be the best physician, whether he is available at a certain moment given a certain context is exhaustive and may be very inefficient. Thus, the proposed middleware has the ability to process and collect data from images analyzed by each medical staff. Based on the collected data and current clinical context, the middleware is able to infer who would be the best fit staff to receive a certain incoming medical image.

Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spots, aggregating diverse perspectives via multi-agent collaboration has emerged as a promising paradigm. While this approach has shown great success in textual QA, its potential in the multimodal domain remains under-explored. Existing multi-agent VQA methods predominantly adapt text-centric protocols, focusing on textual discussions while ignoring the alignment of visual information. In this work, we reveal a key insight: answer-level agreement is insufficient for reliable multi-agent VQA; \textit{aligned visual evidence} -- shared support from the image regions agents rely on -- is essential for trustworthy consensus. To leverage this insight, we propose EAGLE (\textbf{E}vidence-\textbf{A}ligned \textbf{G}rounded mu\textbf{L}ti-agent r\textbf{E}asoning), a training-free evidence-centered framework for coordinating multiple VLM agents. EAGLE explicitly exposes each agent's grounding regions as visual evidence, enables mutual verification over the evidence, and uses evidence consistency to guide final decision-making. Experiments on six VQA benchmarks show that EAGLE achieves best average performance across domains while remaining lightweight, interpretable, and practical for deployment.

Zero-shot Temporal Action Localization (ZS-TAL) aims to detect and locate previously unseen actions in untrimmed videos. However, existing approaches primarily focus on modeling long-range contextual information, often neglecting the critical relative-offset-based local correlations between video frames. Furthermore, their performance is hindered by limited feature representation capabilities due to the shallow nature of their network architectures. In this paper, we address these limitations by introducing a novel local-global multi-scale feature representation module. We propose a novel multi-scale encoder architecture, termed ConTrans, that integrates convolutional (Conv) inductive biases with transformer Self-attention to jointly capture fine-grained local dependencies and long-range global context, leading to more comprehensive feature representations than existing methods. Experimental evaluations on the ActivityNet-1.3 and THUMOS14 datasets demonstrate that ConTrans significantly outperforms existing methods, establishing a new benchmark for ZS-TAL.

Recovering ego-camera orientation from manipulation video is a prerequisite for disentangling hand motion from camera motion, a key step in imitation learning from egocentric demonstrations. The obvious approach, inferring orientation from scene geometry, fails when hands occlude the frame: VGGT, a 1B-parameter scene reconstruction model, scores worse than a constant predictor on the TACO benchmark. We identify an alternative visual concept that is present precisely when scene geometry is absent: kinematic coupling dynamics, the structured physical relationship between wrist motion and camera orientation imposed by the arm-shoulder-head chain. We find that this concept is compact (4D inter-wrist features outperform 126D full hand keypoints), temporal (requiring a GRU over short windows rather than per-frame retrieval), and physically grounded (transferring zero-shot across datasets because it is rooted in anatomy rather than scene appearance). Trained only on tabletop manipulation, WristCompass transfers zero-shot to Epic Kitchens cooking video, achieving 14.3$^\circ$ median geodesic error and approaching the performance of a 1B-parameter scene model at 200K GRU parameters.

Embodied agents have made strong progress in navigating to target objects, but reaching the goal vicinity does not guarantee that the agent has found the correct instance: subtle attribute differences (e.g., "white floral" vs. "white striped") often require close-range, multi-view inspection. We address this gap with Active Instance Verification (AIV), a task in which an agent actively selects viewpoints around a candidate object to decide whether it matches a fine-grained natural-language description. We formalize AIV as a finite-horizon decision process and introduce PInVerify, an offline embodied benchmark for AIV: 3,000 evaluation episodes across 18 object categories, delivered as multi-view captures with a 6-sector navigation topology that exposes trap views (navigable but uninformative) and unreachable sectors. As reference baselines we build a training-free pipeline and a LoRA-fine-tuned end-to-end agent around open-source multimodal large language models (MLLMs) at on-device scale ($\leq$8B parameters), with attribute decomposition, a visibility-weighted multi-view tracker, and three next-best-view (NBV) strategies. In our evaluation across Qwen3-VL (4B/8B), SenseNova-SI-1.2-InternVL3-8B, CLIP, and SigLIP2, the best MLLM-based baseline exceeds the best embedding baseline by 4.9 pp; GT-box ablations show a +3.1 pp detection gap; and we do not observe reliable gains from active viewpoint selection within the tested NBV strategies. A LoRA-fine-tuned agent (SFT+GSPO) reaches 85.6%. PInVerify aims to support further work on active, fine-grained semantic verification in embodied AI. Code: https://github.com/Avalon-S/PInVerify.

While automated diagnosis systems have achieved remarkable success in computed tomography (CT)-based lung cancer screening, their development remains limited by the scarcity of diverse, annotated pulmonary nodule datasets. Diffusion-based generative models offer a promising strategy for data synthesis; however, many existing conditional approaches primarily optimize spatial reconstruction losses, which encourage voxel-wise similarity but may inadequately constrain lesion-level intensity distributions. As a result, these methods may produce over-smoothed texture profiles and underrepresent the distinct attenuation characteristics of different nodule subtypes, including solid, part-solid, and ground-glass nodules. To address this challenge, we propose a controllable latent diffusion model that synthesizes pulmonary nodules within full 3D CT volumes while accurately modeling nodule-specific intensity distributions. Specifically, rather than relying solely on spatial losses, we introduce a histogram-based regularization term that constrains voxel intensity distributions during the generative process. The model combines subtype, spatial mask, and Hounsfield unit (HU) histogram conditioning with the differentiable feature-space histogram regularization term to better align lesion-level intensity distributions, improving the visual plausibility and subtype consistency of synthesized nodules. Extensive experiments on lung CT data demonstrate that our framework achieves strong visual realism, validated through both quantitative metrics and a visual Turing test. Furthermore, when used for data augmentation, the generated nodules improve performance in downstream clinical tasks, particularly for underrepresented nodule subtypes, and show a potential benefit for subtype-informed malignancy classification.

Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains one of the most labor-intensive parts of paper preparation. Existing automated systems each target a single figure type under text-only input, leaving the diversity of types and conditions researchers actually use unaddressed; their raster outputs further cannot be locally revised. Because scientific figures are structured compositions of discrete semantic components, the localized errors generators produce on such layouts demand not a stronger backbone but a harness. We instantiate this harness in two complementary systems: Crafter, a multi-agent harness for figure generation that generalizes across figure types and input conditions without architectural changes, and CraftEditor, which applies the same pattern to convert raster outputs into editable SVGs. Moreover, we introduce CraftBench, a benchmark spanning three figure types and four input conditions with human quality annotation. Experiments show that Crafter substantially outperforms both standalone generators and the agentic baseline on PaperBanana-Bench and CraftBench, with ablations confirming each component's independent contribution; CraftEditor faithfully converts outputs into editable SVGs that surpass all baselines. Our code and benchmark are available at https://github.com/HaozheZhao/Crafter.

Chain-of-thought (CoT) reasoning has significantly improved the reasoning ability of large vision-language models (LVLMs) by verbalizing intermediate reasoning steps in natural language. However, such discrete textual rationales are often insufficient for encoding continuous visual evidence. Recent work addresses this limitation by moving reasoning into continuous latent space. Despite promising progress, existing methods leave latent reasoning insufficiently connected to the compositional and relational structure of visual evidence. To address this gap, we introduce ReGuLaR, a relation grounded latent reasoning framework that explicitly grounds latent states in these critical yet overlooked visual evidence. ReGuLaR uses a training-time ReGFormer to focus latent reasoning on question-relevant objects and inter-object relations, while at inference time the model reasons and generates answers without invoking the ReGFormer. To support training ReGuLaR, we construct RGROUNDING-351K, a real-world vision-language dataset annotated with key object bounding boxes and inter-object relations. Extensive experiments across diverse benchmarks show that ReGuLaR consistently outperforms existing approaches and achieves state-of-the-art performance. We include our code in the submission and will release the code and training data publicly upon acceptance.

Adversarial patches are physical patterns attached to real objects to mislead AI vision systems. Their real-world risk is not determined by a single successful prediction, but by whether they remain effective after deployment under changing viewpoints, distances, and scene conditions. We refer to this property as scene robustness, the effectiveness of a deployed patch across conditions in a real environment. Yet existing evaluations do not measure scene robustness well: real image benchmarks are realistic but fixed, while simulators are controllable but not grounded in a specific real scene. We present AdvScene, a scene-grounded framework for measuring the scene robustness of adversarial patches in reconstructed real environments. AdvScene reframes evaluation as operational measurement: given a fixed deployed patch, it characterizes the patch's operational envelope - where and when the attack succeeds - as a function of viewpoint, distance, and scene context. A key challenge is that the attack is typically defined only in a single anchor view, while evaluation requires a representation that remains faithful under viewpoint changes. We formalize this as a constrained lifting problem and introduce Adversarial Patch-to-Scene Embedding (APSE), which resolves cross-view ambiguity while preserving attack-critical appearance and enforcing locality, target-surface attachment, and cross-view consistency. We validate AdvScene using real-world physical data and conduct a comprehensive evaluation of existing adversarial patches. Our results show that AdvScene reveals substantial scene-dependent variation in attack effectiveness that is not captured by existing image-centric or simulator-based evaluations.

Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semantic understanding. However, 3D understanding still largely relies on expert vision models with complex task-specific designs. The key argument this work wants to make is that VLMs are native 3D learners. Our in-depth large scale study shows that 1) focal length unification, 2) text-based pixel reference and 3) data mixture and scaling, are all you need for effective 3D learning. Model architecture changes, large models, heavy data augmentations, and complex losses including the regression formulation, many of which form the foundation of expert vision models, are actually not necessary conditions. As a result, we propose VLM3, a scalable method with the simplest design that enables standard VLMs to master diverse 3D tasks. VLM3 not only advances the VLM depth estimation accuracy by a large margin (0.84 -> 0.9), but also enables diverse 3D tasks such as pixel correspondence, camera pose estimation and object-level 3D understanding, matching expert vision model accuracy while maintaining standard architectures and text-based training. We believe VLM3 opens up a new paradigm for simple and scalable 3D learning.

Spatial reasoning is a fundamental capability for vision-language models (VLMs) deployed in real-world environments. However, visual observations are inherently limited representations of a 3D world: occlusion can render objects invisible, and perspective can make geometric properties misleading. Despite this, existing spatial reasoning benchmarks typically assume that observations are sufficient and reliable, focusing on whether models produce correct answers rather than whether they recognize when a question cannot be answered and what additional observations would be needed. In this work, we challenge this assumption by constructing a controlled evaluation framework, SpatialUncertain, and introducing two types of observation challenges: (1) occlusion, which hides target information, and (2) perspective ambiguity, which produces misleading visual cues. For each configuration, we design spatial questions that are answerable under clean observations but require abstention under the introduced challenges. We further evaluate whether models can identify which additional viewpoints would resolve perspective ambiguity. Our results across a diverse set of frontier open- and closed-source VLMs reveal two consistent failure modes. First, models are prone to overconfident answering, attempting to solve spatial reasoning tasks even when visual evidence is incomplete or misleading, with average accuracy around 30\% under occlusion and below 10\% under perspective ambiguity. Second, even when additional views are available, some models perform near random chance in identifying which would provide reliable evidence. Together, our findings call for moving beyond answer correctness toward evaluating whether models know when to abstain and how to seek reliable evidence.

Visual monitoring systems that rely on cloud-based AI inference expose raw image data to external services, creating fundamental tensions with the data-minimisation principle of the General Data Protection Regulation (GDPR). This paper presents a proof-of-concept privacy-by-design pipeline that resolves this tension by confining all inference entirely to the edge device. A YOLOv5n-seg model compiled for a Hailo-8L AI accelerator delivers real-time object detection on a Raspberry Pi 5, from which raw pixel buffers are immediately discarded after inference. A stateful trigger engine forwards minimal JSON event payloads to a locally hosted instance of Phi-3 Mini (3.8B parameters, Q4_0 quantisation), which synthesises one-to-two sentence natural-language alerts for a human operator. No image data crosses the network boundary at any point; only the generated text alert is transmitted. We describe the full system architecture and implementation, report measured inference latency and resource utilisation on the target hardware, and present representative generated alerts. The results demonstrate that combining a dedicated neural-network accelerator with an on-device large language model on a single-board computer is not only feasible but produces practically deployable, human-readable monitoring output while aligning with GDPR Art. 5(1)(c) by design.

Autoregressive (AR) video generation extends videos by producing latent chunks sequentially, but scaling to long videos requires repeated access to a growing historical KV cache. Existing methods reduce this cost by truncating the KV cache or compressing it into implicit memory, but both lose explicit access to query-relevant historical details. We propose OmniMem, an explicit full-range memory retrieval framework that performs sparse KV retrieval over the historical cache. To make this practical for chunk-based AR video generation, OmniMem addresses two issues: (i) local bias in sparse KV selection and (ii) Union Explosion in memory access. Adaptive Window Exclusion removes local-window blocks from the selection candidates when sufficient long-range history is available, preserving the sparse budget for informative long-range retrieval. Query-Shared KV Selection reduces cross-query diversity, while Per-Head Scattered KV Access avoids expanding head-specific selections into a large selected KV buffer. This allows each attention head to retrieve non-contiguous KV blocks according to its own selection pattern. Experiments on long-video generation show that OmniMem improves Dynamic Degree by 52.3% and preserves strong consistency over strong baselines, while maintaining comparable memory usage.

Generating physics diagrams from text requires strict adherence to physical laws. While current generative models produce visually plausible outputs, they systematically hallucinate force vectors, ignore conservation laws, and violate geometric constraints. We present PhyDrawGen, a neuro-symbolic pipeline that decouples semantic scene understanding from physical constraint satisfaction. First, a large language model extracts a typed scene graph from the problem text. A deterministic solver then converts this graph into a Planar Straight-Line Graph (PSLG), encoding force balance, optical paths, and field topologies as exact geometric primitives. Finally, a fine-tuned Qwen-VL model implements a visually grounded propose-verify loop to iteratively correct any constraint violations. Evaluated on a benchmark of 1,449 problems spanning mechanics, optics, and electromagnetism, PhyDrawGen significantly outperforms GPT-5-image, Gemini 2.5 Flash, and Gemini 3 Pro, demonstrating robust physical accuracy even on unusual-object problems.

Brain cancer's severity necessitates precise brain tumor segmentation, which is crucial for effective brain tumor diagnosis. Manual identification, burdened by high costs, labor, and error risks, highlights the need for automated methods. In this study, we introduce the Global Context-aware Squeeze and Excite Residual UNet (GCSER-UNet), which facilitates a fusion of spatial and channel-wise attention and thus enhances the model's capacity to capture intricate spatial dependencies and contextual information. GCSER-UNet efficiently extracts tumor segments from multimodal MRI slices, delivering exceptional performance. Evaluations on benchmark databases exhibit its superiority, achieving a notable 94 percent dice score on the TCGA LGG dataset, surpassing the state-of-the-art dice score of 91.8 percent. In the BraTS 2020 dataset, the proposed GCSER-UNet ensemble approach yielded dice scores of 95 percent, 92 percent, and 90 percent for the tumor regions - Whole Tumor (W), Tumor Core (T), and Enhancing Tumor (E), respectively. The current state-of-the-art dice scores were 94 percent, 93 percent, and 88 percent. These compelling outcomes highlight the efficacy of GCSER-UNet in precise brain tumor segmentation and thus can aid neurologists in effective brain cancer management and treatment planning.

Global localization in geometrically aliased, quasi-static environments such as grocery stores, offices, schools, and hospitals poses a significant challenge for mobile robots. Grocery stores with parallel aisles and a long tailed distribution of products, as well as offices and labs with repetitive furniture such as chairs, desks, monitors, and doors, exemplify common indoor environments that present geometric and even semantic ambiguity. Traditional approaches rely either on distinct geometric features or on domain-specific vision pipelines that struggle with long-tail semantic distributions and transient visual clutter. We present VLM-GLoc, a method for hierarchical semantic Monte Carlo Localization (MCL) that leverages open-vocabulary Vision-Language Models (VLMs) as a unified semantic observation front-end. We hypothesize a three-fold benefit from VLMs: (1) extracting highly discriminative rich text features, (2) implicit quality filtering of blurry or dynamic objects, and (3) permanence reasoning for targeted data augmentation. We introduce an inverse semantic proposal mechanism that seeds particles via text-to-map retrieval. Evaluated across two real-world environments with different characteristics and two different platforms: a 3,500 sq. ft. grocery store with a cellphone and a 3,700 sq. ft. lab space with a quadruped, VLM-GLoc achieves 70% and 74% global localization success respectively, substantially outperforming traditional geometry-only and domain-specific baselines.

The recent surge in 4D Gaussian Splatting (4DGS) has achieved impressive dynamic scene reconstruction. While these methods demonstrate remarkable performance, the specific drivers behind such gains remain less explored, making a systematic understanding of the underlying principles challenging. In this paper, we perform a comprehensive analysis of these hidden factors to provide a clearer perspective on the 4DGS framework. We first establish a controlled baseline, FreeTimeGS_ours, by formalizing and reproducing the heuristics of the state-of-the-art FreeTimeGS. Using this framework, we dissect 4DGS along its fundamental axes and uncover key secrets, including the emergent temporal partitioning driven by Gaussian durations and the discrepancy between photometric fidelity and spatiotemporal consistency. Based on these insights, we propose FreeTimeGS++, a principled method that employs gated marginalization and neural velocity fields to achieve superior stability and robust dynamic representations. Our approach yields reproducible results with reduced run-to-run variance. We will release our implementation to provide a reliable foundation for future 4DGS research.

3D audio and novel-view acoustic synthesis models are usually evaluated with global metrics.However, global metrics often hide where and why binaural prediction fails. We propose a full-reference diagnostic framework that uses time-frequency audio error maps for magnitude, ILD, IPD, temporal alignment, loudness, and high-frequency failures, forming a 3D Audio Error Map (3DAE Map) for visual inspection. We frame these diagnostics into a model-agnostic benchmark, Spatial Audio Error Bench (3DAE Bench), which takes arbitrary ground-truth and predicted binaural pairs and reports the prediction quality of audio novel-view synthesis models. Experiments on ViGAS outputs over Replay-NVAS and SoundSpaces show different dominant failure modes: temporal misalignment on Replay-NVAS and ILD mismatch on SoundSpaces. Overall, the framework provides interpretable failure-mode summaries and intuitive visual maps for audio Novel-view-synthesis model development optimization.

Recent advances in 4D Human-Object Interaction (HOI) generation have enabled increasingly realistic motion synthesis, particularly for single-object manipulation. Yet current research overlooks an inherent property of human behavior: people naturally coordinate both hands and manipulate multiple objects simultaneously. To address this gap, we present Dex2HOI, a unified diffusion model for single- and two-object HOI synthesis from text. At its core, Dex2HOI employs a Dual-Stream Diffusion approach, where each object is processed in a dedicated interaction stream and coordinated through bidirectional cross-attention. To synthesize the final motion, we introduce a Motion Fusion Network integrated with novel hand-relative object representations and contact-aware conditioning applied across the whole sequence. By sampling the diffusion process autoregressively over prefix-conditioned windows, Dex2HOI generates arbitrarily long sequences at real-time speed omitting redundant test-time optimization, achieving up to x540 inference speed-up over prior state-of-the-art methods. Extensive evaluation on both single- and two-object benchmarks demonstrates state-of-the-art quantitative results, marking a step beyond conventional single-object HOI generation and toward expressive multi-object manipulation. Code and models will be released upon acceptance.

Recent progress in video diffusion models has enabled remarkable generative fidelity, yet leveraging these priors for restoration remains limited by the strong coupling between conditional and unconditional branches in standard classifier-free guidance. We introduce a training-free framework that enhances distorted and low-resolution videos by decoupling these signals in time. Our proposed Decoupled Time Guidance (DTG) evaluates the unconditional branch at a cleaner diffusion timestep, providing a lookahead prior that preserves geometry while suppressing replication of warped content. This temporal bias is annealed throughout sampling, allowing the model to transition from structure correction to detail refinement without retraining. Combined with any off-the-shelf restoration module in a plug-and-play manner, our approach improves perceptual coherence and restores plausible structure in AIgenerated and real-world videos alike. To facilitate evaluation, we curate GenWarp480, a benchmark of 4,400 distorted 480p videos synthesized from diverse text-to-video models. GenWarp480 focuses on characteristic generative degradations such as warped faces, body misalignments, and spatial artifacts, providing a purpose-built testbed for assessing robustness to generative errors. Extensive experiments demonstrate that our method achieves significant improvements in structural fidelity and temporal stability without any model training.

Real-time streaming video-to-video editing (V2V) is critical for interactive applications such as live broadcasting and gaming, yet it remains a formidable challenge due to the stringent requirements for temporal consistency and inference throughput. In this paper, we present SANA-Streaming, a system-algorithm co-designed framework for high-resolution, real-time streaming video editing on consumer GPUs, with the following three core designs: (1) Hybrid Diffusion Transformer architecture introduces softmax attention in part of the blocks to improve local modeling capabilities while preserving the efficiency of linear layers. (2) Cycle-Reverse Regularization is a novel training strategy that enforces semantic consistency by predicting source frames from generated content via flow matching, improving temporal consistency without requiring paired long edited videos. (3) Efficient System Co-design combines fused GDN kernels and Mixed-Precision Quantization (MPQ) optimized for the NVIDIA Blackwell (RTX 5090) architecture. By profiling real-world throughput, our MPQ maximizes Tensor Core utilization while maintaining generation quality. The resulting system achieves real-time 1280 x 704 resolution editing at 24 end-to-end FPS on a single RTX 5090 GPU, with the DiT core running at 58 FPS. Experimental results demonstrate that our co-design approach significantly outperforms existing SOTA methods in both temporal coherence and system throughput.

Functional Magnetic Resonance Imaging (fMRI) provides non-invasive access to dynamic brain activity by measuring blood oxygen level-dependent (BOLD) signals over time. However, the resource-intensive nature of fMRI acquisition limits the availability of high-fidelity samples required for data-driven brain analysis models. While modern generative models can synthesize fMRI data, they often remain challenging in replicating their inherent non-stationarity, intricate spatiotemporal dynamics, and physiological variations of raw BOLD signals. To address these challenges, we propose Dual-Spectral Flow Matching (DSFM), a novel fMRI generative framework that cascades dual frequency representation of BOLD signals with spectral flow matching. Specifically, our framework first converts BOLD signals into a wavelet decomposition map via a discrete wavelet transform (DWT) to capture globalized transient and multi-scale variations, and projects into the discrete cosine transform (DCT) space across brain regions and time to exploit localized energy compaction of low-frequency dominant BOLD coefficients. Subsequently, a spectral flow matching model is trained to generate class-conditioned cosine-frequency representation. The generated samples are reconstructed through inverse DCT and inverse DWT operations to recover physiologically plausible time-domain BOLD signals. This dual-transform approach imposes structured frequency priors and preserves key physiological brain dynamics. Ultimately, we demonstrate the efficacy of our approach through improved downstream fMRI-based brain network classification. The code is available at https://github.com/htew0001/DSFM.git .

Spiking neural networks (SNNs) hold promise for demonstrating superior learning and representation capabilities in deep models. Given the tremendous success of ResNet in deep learning, it would naturally follow to train deep SNNs with residual learning. However, existing residual structures for constructing deep SNNs still present challenges of spike redundancy or information loss, as well as redundant learning. In the present study, we first aim to address issues of relative spike redundancy in identity mapping and information loss in non-identity mapping. To this end, we propose an OR-ADD (OA) shortcut connection to merge output spikes/currents from two branches in the residual structure. Furthermore, to mitigate redundant learning in the backbone branch of the residual structure, we introduce the concept of XOR meta-residuals, i.e., selecting pre-learning residuals using the Exclusive-OR (XOR) operation for the backbone branch. Finally, by integrating the OA shortcut and XOR meta-residuals, we devise the XOR residual block and further construct XOResNet with varying depths based on this block. Extensive experiments on four datasets, Fashion-MNIST, CIFAR-10, CIFAR-100, and miniImageNet, show that the proposed XOResNet outperforms existing state-of-the-art deep SNNs optimized via gradient descent. These results validate the effectiveness of our OA shortcut and XOR meta-residual components in overcoming fundamental limitations of residual learning in SNNs, providing new architectural insights for building high-performance neuromorphic systems.

Self-supervised online traversability estimation enables robots to continuously learn from unlabeled open-world experiences and adapt their navigation behavior toward safe and efficient trajectories. Existing approaches either rely on handcrafted proprioceptive traversability scores, limiting robot-agnosticism, or cluster prior data, preventing online learning. Moreover, many continual learning methods incur substantial memory and computational costs, hindering onboard deployment. We introduce COTRATE, an online learning framework for continuous traversability estimation from multimodal, unlabeled robot experience. Our method first infers robust traversability scores using a robot-agnostic, learning-based online terrain assessment module operating on proprioceptiveand inertial signals. These scores then supervise a visual traversability network through a novel alignment loss that associates visual embeddings with online terrain assessments. To mitigate forgetting during continual learning with minimal overhead, we propose a diversity-aware feature selection strategythat preserves performance using a compact replay memory. We further show that the learned traversability representation supports knowledge transfer across different robot platforms with different locomotion kinematics. We evaluate COTRATE on a dataset of $\approx$ 50,000 images collected with two robotic platforms across 11 outdoor terrains, and benchmark it on navigation tasks in three representative outdoor environments. We make the dataset, code, and trained models publicly available.

While spatial foundation models have demonstrated impressive performance on standard datasets, a critical question remains: are they truly all-round players capable of generalizing robustly across diverse downstream tasks, arbitrary viewpoints, shifting scene domains, varying input densities, and specific hardware constraints? Answering this overarching question requires a holistic assessment, yet current models are mainly evaluated on specific domains for which they were specifically designed or trained. Such evaluations are intrinsically limited by narrow paradigm coverage, limited scene domains, and arbitrary frame sampling, making it fundamentally difficult to assess their true generalization capabilities. To address this gap, we present SpatialBench, a cross-paradigm, domain-diverse benchmark for spatial foundation models with deterministic sampling. SpatialBench features unprecedented scale and rigorous deterministic design, comprising 19 datasets and 546 scenes across 5 diverse spatial domains. It comprehensively evaluates 41 models across 6 paradigms on 5 task suites under 4 different input density settings. Our extensive evaluation reveals that current models are not yet all-round players, and uncovers crucial insights for future advancement. Specifically, we demonstrate that full-context attention maximizes accuracy while bounded-memory strategies unlock long-sequence scalability. Moreover, our empirical evaluations in challenging embodied and egocentric tasks demonstrate that strict domain alignment and high data quality are far more critical to performance than simple dataset scaling. Furthermore, to address the largest data gap identified in our analysis, we go beyond evaluation by introducing a large-scale dataset, DA-Next-5M, and a strong baseline model, DA-Next, pushing the boundaries of spatial representation learning.

Recent feed-forward geometry foundation models have demonstrated impressive generalization by recovering depth and poses in a single forward pass. However, these models are typically constrained by a global coordinate frame assumption. This dependency becomes a significant bottleneck for long-context and streaming reconstruction, as it forces the network to maintain an arbitrary temporal origin and handle translation magnitudes that grow unbounded over time. Our solution, which we call $R^3$, employs relative regression. We employ a lightweight MLP to predict confidence-weighted relative constraints. These confidences serve as a unified anchor: weighting losses during training and guiding pose aggregation during inference. $R^3$ supports both full-context offline reconstruction and causal, bounded-memory streaming. Our evaluation in both offline and streaming settings validates the effectiveness of our relative mechanism. Project page: https://kevinxu02.github.io/r3-site

While diffusion models excel at generating high-quality images, their tendency to memorize training data poses significant privacy and copyright risks. In this work, we for the first time identify that memorization induces internal numerical instability, often manifesting as visually ``broken'' artifacts. Inspired by stability analysis in numerical methods, we introduce empirical stability regions based on latent update norms to quantitatively characterize stable behavior during generation. Leveraging this, we propose a principled, on-the-fly framework for step-wise detection and adaptive mitigation. Our approach suppresses memorization without altering prompts or guidance, thereby preserving semantic fidelity and image quality. Extensive experiments on Stable Diffusion 1.4 demonstrate that our method achieves an AUC $>0.999$ detection performance and a $0.0\%$ memorization rate after mitigation with negligible overhead ($\approx0.01$s per image).

Image generation models have evolved from text-conditioned pixel synthesis toward multimodal agents endowed with visual comprehension and tool invocation capabilities. Yet, existing agents remain at the mercy of underlying black-box image models. Their workflow is trapped in a repetitive cycle of prompt rewriting for generation refinement, leaving them with no mechanism to directly manipulate the canvas. In essence, the potential of LLMs to serve as a genuine "brush" for precise visual construction remains largely untapped. In this paper, we propose GenClaw, a code-driven agentic image generation paradigm that empowers the agent to create like a human artist: first conceptualizing, then sketching, and finally coloring. Specifically, the agent first constructs the conceptual knowledge and context through search and reasoning. It then utilizes code (e.g., SVG, HTML, ThreeJS) to render executable visual sketches. Finally, it employs an image generation model to supplement textures, materials, and photorealism. In this workflow, code serves as a controllable intermediate canvas bridging linguistic reasoning and pixel synthesis, seamlessly integrating programmatic logic with the visual expressiveness of generative models. By transforming image generation from a black-box paradigm into a staged process akin to authentic human creation, GenClaw offers a step toward for highly controllable and interpretable visual generation systems.

Recent feed-forward 3D reconstruction transformers have scaled to over a billion parameters, following the broader trend of increasing model capacity in computer vision. Yet emerging evidence suggests that contiguous transformer layers often behave like repeated applications of similar operations, and multi-view reconstruction transformers refine their predictions progressively across decoder depth. We posit that model depth partially buys iteration, paid for inefficiently in unique parameters, and instead make that iteration explicit in architecture. Our model, DéjàView, applies a single looped transformer block recurrently to per-view features for K refinement steps. Trained once, it exposes K as an inference-time compute knob, matching or outperforming substantially larger feed-forward baselines across five reconstruction benchmarks spanning indoor, outdoor, object-centric, and driving scenes, while using a fraction of their parameters and comparable or lower compute. Importantly, the same looped block formulation outperforms an otherwise identical variant with independent per-step parameters under matched training data and compute, suggesting that explicit iteration is not merely a compute-efficient substitute for capacity but a stronger inductive bias for multi-view 3D reconstruction.

This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built upon a plain transformer architecture without task-specific architectural modifications, ViGeo supports streaming, full-sequence, and long-video inference within a unified model. The key design is dynamic chunking attention, which exposes the model to both bidirectional and causal temporal contexts during training and allows it to adapt its attention pattern at test time without retraining. To improve supervision quality, we further introduce a completion-based data refinement framework. This framework trains a video depth completion teacher that conditions on sparse and noisy annotations and exploits video/multi-view context to produce dense, temporally coherent, and geometrically reliable training targets. Beyond depth and point maps, ViGeo also predicts surface normals within the same framework. Trained solely on public datasets, ViGeo achieves state-of-the-art performance across online, offline, and long-video depth estimation, surface normal estimation, and video point map estimation.

Integrating open-vocabulary semantic information into dynamic 3D scene representations is essential for long-term embodied scene understanding. However, existing methods often suffer from fragile instance association due to incomplete cross-view cues, while their limited ability to handle object-level topological changes restricts long-term robotic task execution. Moreover, current 3D scene understanding methods either rely on simple feature matching without explicit spatial reasoning or assume offline ground-truth 3D geometry. To address these challenges, we present DGSG-Mind, a hybrid instance-aware 3D Gaussian dynamic scene graph system with an embodied reasoning agent. Our system couples a probabilistic voxel grid with explicit 3D Gaussians to enable robust cross-modal instance fusion and incremental semantic mapping. It handles dynamic changes through Gaussian-based visual relocalization and localized masked refinement guided by geometric-semantic consistency. Built on the instance Gaussian map, DGSG-Mind further constructs a hierarchical scene graph and develops the 3D Gaussian Mind, which integrates structural relations, spatial-semantic information, and visually annotated RoI Gaussian renderings for multimodal reasoning. Extensive experiments show that DGSG-Mind achieves the best zero-shot 3DVG performance among methods operating on self-reconstructed maps, while also delivering strong performance in 3D open-vocabulary semantic segmentation and scene reconstruction. We further deploy DGSG-Mind on real-world robots to demonstrate its target-oriented reasoning and dynamic update capabilities. The project page of DGSG-Mind is available at https://icr-lab.github.io/DGSG-Mind

Histological scoring is essential for diagnosing Non-Alcoholic Fatty Liver Disease (NAFLD), yet its automation remains challenging due to the high annotation cost and negative transfer among the strongly correlated NAFLD Activity Score (NAS) indicators in multi-task learning. To address this issue, we propose a subspace-decoupled multi-task Vision Transformer (ViT) that integrates lightweight task-specific Adapters with orthogonality-based constraints. This design constructs independent feature subspaces for steatosis, ballooning, and inflammation, effectively reducing task interference while retaining shared representations. We further construct a curated multi-task mouse NAFLD histology dataset with expert annotations for all NAS components. Experimental results demonstrate that the proposed method improves multi-task stability and generalization with substantially reduced computational cost compared to training separate single-task models. The code and the curated dataset have been prepared and will be made publicly available upon acceptance to support reproducibility.

Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokenizations. Compact set-based representations discard deterministic spatial ordering, leading to ambiguous sequence prediction, while uniform or octree-based voxel grids preserve ordering at the cost of severe redundancy and excessively long sequences. This structural trade-off limits stable and efficient autoregressive 3D generation. We present SuperVoxelGPT, a representation-first framework that resolves this tension through adaptive and deterministically ordered supervoxel tokenization. Given a prompt, we first predict a coarse geometric saliency distribution and construct a shape-adaptive supervoxel partition using saliency-guided centroidal Voronoi tessellation, allocating fine-grained cells to complex regions and larger cells to smooth regions. Conditioned on the text and ordered supervoxel layout, we introduce a SuperVoxelVAE and fine-tune a pretrained MLLM to autoregressively generate supervoxel tokens. Experiments on Trellis-500K show that SuperVoxelGPT reduces token sequence length to 12.8% of uniform voxel tokenization while achieving state-of-the-art generation quality and an average 10$\times$ speedup over prior methods.

Creating relightable urban scenes from images or videos is widely useful but highly ill-posed. Urban environments are typically unbounded and extend beyond the visible regions. As a result, many portions of the scene remain unobserved, yet these invisible regions can cast shadows onto visible areas. Reasonably modeling shadows cast by such invisible regions is challenging and poses a significant obstacle to creating relightable urban scenes. At the same time, sparse input views and complex illumination conditions further complicate relighting, as they introduce severe ambiguities in material decomposition. In this paper, we propose Shadow-guided Relightable Urban Scene with Generation model (SRUG), a novel framework designed to address relighting challenges in urban scenes. SRUG leverages shadows to guide a 3D completion model for recovering the geometry of invisible regions, promoting the synthesis of physically reasonable shadows. In addition, SRUG employs an iterative material decomposition scheme that applies the large material model (LMM) to provide material supervision and iteratively decompose the scene's material properties, enabling robust material decomposition. Building upon these components, we introduce a physically-based lighting model that captures the complex illumination of urban scenes and supports reliable relighting. Extensive quantitative evaluations and visual comparisons demonstrate that our method outperforms existing approaches in both novel view synthesis and relighting tasks.

This study addresses the partial-to-complete geometry reconstruction of deformable objects (DOs) from point-cloud observations toward precise DO manipulation. Recent DO reconstruction approaches often adopt implicit neural representations (INRs) to model continuous surfaces as well as capture structural variability. However, these methods typically rely on object-specific shape priors that improve training stability and limit generalization. To figure it out, we introduce ParCo-SDF, a two-stage partial-to-complete signed distance field (SDF) reconstruction framework consisting of temporal geometry encoding followed by FiLM-conditioned SDF prediction. The temporal encoder captures structural similarity across DO sequence, enabling prior-free stable training. FiLM-based conditioning preserves reconstruction expressivity while reducing network complexity. We evaluate the proposed method against a state-of-the-art DO surface reconstruction baseline on a rubber band manipulation dataset, demonstrating robust and high-fidelity reconstruction under severe occlusions.

Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cost. This limits their widespread deployment for dental screening outside specialist centres, where timely inference, limited hardware, and local handling of patient images are vital for practical, privacy-preserving clinical prescreening. Here we present Pocket-Dentist, an efficiency-aware benchmark for dental multimodal question answering that brings together three datasets spanning approximately 1,159 patients, five task types and seven metrics. Across typical 14 VLMs, our results reveals an interesting observation: compact VLMs (e.g., 2B-parameter models) outperform larger VLMs in accuracy while requiring substantially lower computational costs in dental image understanding. Deployed locally on an iPhone 17 Pro, our finetuned compact VLM Pocket-Dentist-2B processed each sample in 4.31 s, reducing latency by 4.9-fold and memory use by 2.3-fold compared with a 7B baseline.

Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including mathematical reasoning and text-to-image generation. However, their reliance on sample-level rewards introduces a key limitation as uniform credit assignment across all tokens fails to capture fine-grained, token-level contributions. To address this issue, we propose Guidance Contrastive Policy Optimization (GCPO), a novel algorithm that enables per-token credit assignment by contrasting model predictions under positive and negative prompts. Rather than uniformly broadcasting sample-level advantages, GCPO assigns token-level advantages proportional to the difference between these contrastive predictions, allowing more precise and informative learning signals. Empirically, we find that GCPO emphasizes semantically relevant regions such as visual areas aligned with textual prompts in text-to-image generation, and critical keywords within reasoning traces for chain-of-thought tasks. Through extensive experiments, GCPO consistently outperforms GRPO and DAPO baselines on both text-to-image generation and chain-of-thought reasoning benchmarks, demonstrating its effectiveness as a general and scalable optimization strategy for discrete policy learning.

Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where beliefs must be continuously revised from egocentric observations under environmental change. We introduce SpaMEM (Spatial Memory from Action Sequences), a large-scale diagnostic benchmark that isolates the mechanics of spatial belief evolution via action-conditioned scene transformations (spawn, place, remove) over long interaction horizons. SpaMEM is built on a physically grounded dataset with 10,601,392 high-fidelity images across four modalities (RGB, depth, instance, semantic segmentation), collected from 25,000+ interaction sequences in 1,000 procedurally generated houses. We formalize embodied spatial reasoning as a three-level hierarchy with 15 diagnostic tasks: Level 1 measures atomic spatial perception from single observations; Level 2 probes temporal reasoning with oracle textual state histories to factor out perceptual noise; and Level 3 requires end-to-end belief maintenance from raw visual streams under the same task dimensions. We further evaluate both short-term (step-wise) updates and long-term (episodic) reconstruction. Benchmarking representative open-source VLM families reveals a consistent stacked bottleneck: coordinate-consistent grounding remains a hard ceiling, and the sharp collapse from Level 2 to Level 3 exposes a pronounced symbolic scaffolding dependency, where models succeed with text-based bookkeeping but struggle to sustain robust visual memory. SpaMEM provides a granular diagnostic standard and motivates explicit mechanisms for state representation, belief revision, and long-horizon episodic integration. A subset of SpaMEM is publicly available at https://huggingface.co/datasets/mill-ct-liao/SpaMEM.

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, subsequently extending into numerous spatial AI applications. However, most existing 3DGS methods operate in isolation, focusing on specific domains. In this paper, we introduce X-GS, an extensible framework consisting of two major components. The X-GS-Perceiver unifies a broad range of 3DGS techniques to enable real-time online SLAM with semantic distillation. The X-GS-Thinker accommodates multimodal models, enabling them to seamlessly interface with the Perceiver to complete downstream tasks. In our implementation of X-GS, the Perceiver leverages the latest vision foundation models to improve online SLAM performance and employs three key mechanisms to accelerate semantic distillation. The Thinker can be built upon both contrastive and generative vision-language models and utilizes the Perceiver's semantic Gaussian splats to unlock capabilities such as 3D visual grounding and scene captioning. Experimental results on diverse benchmarks demonstrate the efficiency and newly unlocked multimodal capabilities of the X-GS framework.

Understanding the multi-dimensional attributes and intensity nuances of image-evoked emotions is pivotal for advancing machine empathy and empowering diverse human-computer interaction applications. However, existing models are still limited to coarse-grained emotion perception or deficient reasoning capabilities. To bridge this gap, we introduce \textbf{EEmoDB}, the largest image-{\ul e}voked {\ul emo}tion understanding {\ul d}ataset to date. It features $5$ analysis dimensions spanning $5$ distinct task categories, facilitating comprehensive interpretation. Specifically, we compile $1.2M$ question-answering (QA) pairs (EEmoDB-QA) from $125K$ images via automated generation, alongside a $36K$ dataset (EEmoDB-Assess) curated from $25K$ images for fine-grained assessment. Furthermore, we propose \textbf{EEmo-Logic}, an \textbf{all-in-one} multimodal large language model (MLLM) developed via instruction fine-tuning and task-customized group relative preference optimization (GRPO) with novel reward design. Extensive experiments demonstrate that EEmo-Logic achieves robust performance in in-domain and cross-domain datasets, excelling in emotion QA and fine-grained assessment. The dataset and code are available at https://github.com/workerred/EEmo-Logic.

Visual and acoustic events in the physical world are inherently coupled, yet existing video editing methods typically adopt decoupled pipelines, lacking bidirectional modality interaction. This results in two key limitations: (i) audio-visual desynchronization and (ii) contextual conflicts between generated audio and preserved content. To address these, we propose SpongeBob, the first end-to-end audio-visual joint editing framework featuring bidirectional cross-modal interaction. For synchronization, a Sync-Aware Mechanism aligns visual edits with sound events via bidirectional attention, temporal alignment, and spatial constraints. For contextual consistency, a Context-Aware Module leverages acoustic and visual context attention to prevent semantic clashes. Additionally, we introduce Sync-Preserving Training and Guidance (SPTG) to enhance alignment without degrading quality. Due to the scarcity of paired data, we construct a scalable data pipeline and a large-scale subject-level dataset. We also propose SpongeBob-Bench for systematic evaluation. Experiments show SpongeBob significantly outperforms existing baselines, improving Sync-C by 30% and Ctx-F1 by 12.5%. Our project page is available at: https://hy-spongebob.github.io/.

Composed Image Retrieval (CIR) requires both preserving the visual continuity of the reference image and faithfully executing the semantic variables specified in the modification text, which constitute the core challenge of the task. Existing methods often suffer from Perception Myopia in a single space, or fall into Logic Drift in iterative collaboration due to the perception ceiling of the underlying retriever. To address this issue, we propose a one-stop hierarchical Perception-to-Deliberation Framework (PDF), which, to the best of our knowledge, is the first to introduce experience self-evolution and Test-Time Scaling Laws (TTS) into CIR. Relying on a hierarchical multi-agent architecture, PDF first utilizes an Intent Routing Manager to dynamically dispatch multi-view Worker perception signals based on modification intents to construct a high-recall candidate pool. Subsequently, the Decision Manager combines a Training-free Reasoning Policy Distillation mechanism with a Tournament-style TTS (T-TTS) strategy to achieve self-evolving fine-grained reasoning, yielding the final retrieval results. Experimental results demonstrate that PDF achieves SOTA performance on three benchmark datasets: CIRR, CIRCO, and FashionIQ. This study indicates that experience-driven self-evolution and TTS represent a highly promising and scalable path for achieving zero-shot fine-grained multimedia retrieval. The code will be made publicly available upon acceptance.

We ask whether everyday open-world monocular videos can be turned into reusable 4D interaction primitives: articulated hand motion, object shape with 6D pose over time, and the when/where of contact. Such a capability would enable scalable mining of real interactions and, beyond reconstruction, support scene-aware synthesis and planning. However, reconstructing hand-object interaction (HOI) from challenging monocular videos remains difficult: methods often assume known objects or curated scenes, and separately estimated hands and objects easily become misaligned under clutter, occlusion, and unseen object geometries. Targeting this setting, we present CHOIR, a Contact-aware HOI Reconstruction framework for a monocular camera, using contact as an explicit coupling signal between hands and objects. CHOIR first initializes a coarse, contact-agnostic 4D HOI sequence from open-world visual priors. It then introduces a generative HOI spatial rectification module to predict ray-depth corrections and rectify hand-object relative placement, then derive initial per-frame contact correspondences on the rectified geometry. Last, a contact-aware joint optimization with dynamically updated contact constraints enforces geometric, temporal, and contact consistency. Experiments on controlled and challenging videos show that CHOIR improves object reconstruction, physical plausibility, and temporal consistency over state-of-the-art methods.

Road segmentation is a fundamental perception task for autonomous driving and intelligent robotic systems, requiring both high accuracy and real-time inference, especially for deployment on resource-constrained edge devices. Existing multi-modal road segmentation methods often rely on heavy transformer-based encoders to achieve state-of-the-art performance, but their enormous computational cost prohibits real-time deployment on embedded platforms. To address this dilemma, we propose LiteViLNet, a lightweight multi-modal network that fuses RGB texture information and LiDAR geometric information for efficient road segmentation. Specifically, we design a dual-stream lightweight encoder and depth-wise separable convolutions to extract hierarchical features from both modalities with minimal parameters. We further propose a Multi-Scale Feature Fusion Module (MSFM) to facilitate cross-modal interaction at different levels, and a large-kernel-bridge module to capture long-range dependencies with linear complexity. Extensive experiments on the KITTI Road dataset and real-world applications demonstrate that LiteViLNet achieves a promising balance between accuracy and efficiency. Notably, with only 14.04M parameters, our model attains a 96.36% MaxF score, ranking the best among all CNN-based methods and being comparable to larger transformer-based models, and runs at 163.79 FPS in model-only inference on RTX 4060 Ti (22.18 FPS on Jetson Orin NX). It outperforms numerous heavy-weight methods in inference speed while maintaining highly competitive accuracy, fully validating the potential of LiteViLNet for real-time embedded deployment in autonomous driving and intelligent robotics.

Open-Vocabulary Object Detection (OVD) models break the limitations of closed-set detection, enabling the identification of unseen categories through natural language prompts. However, they exhibit notable limitations in fine-grained detection tasks involving attributes like color, material, and texture. We attribute this performance bottleneck in OVD models to a core issue: when category signals dominate, OVD models tend to marginalize attribute information during inference. This leads to incorrect binding between attributes and target objects. To address this, we propose the Dual-Stage Attribute Activation (DSAA) framework, which enhances fine-grained detection capabilities by strengthening attribute semantics at two critical stages. In the text embedding stage, we employ Attribute Prefix Adapter (APA) module to generate attribute prefixes that inject explicit attribute priors. To further amplify the influence of these attributes, our Key/Value (K/V) Modulator module then intervenes during the BERT encoding phase, selectively enhancing the Key and Value vectors of the corresponding attribute tokens. In addition, we introduce an attribute-aware contrastive loss to improve discrimination among same-category instances with different attributes during training. Experimental results on the FG-OVD benchmark demonstrate the effectiveness of our method across various mainstream open-vocabulary models.

Polarimetric synthetic aperture radar (PolSAR) images encompass valuable information that can facilitate extensive land cover interpretation and generate diverse output products. Extracting meaningful features from PolSAR data poses challenges distinct from those encountered in optical imagery. Deep learning (DL) methods offer effective solutions for overcoming these challenges in PolSAR feature extraction. Convolutional neural networks (CNNs) play a crucial role in capturing PolSAR image characteristics by leveraging kernel capabilities to consider local information and the complex-valued nature of PolSAR data. In this study, a novel three-branch fusion of complex-valued CNN, named the Shallow to Deep Feature Fusion Network (SDF2Net), is proposed for PolSAR image classification. To validate the performance of the proposed method, classification results are compared against multiple state-of-the-art approaches using the airborne synthetic aperture radar (AIRSAR) datasets of Flevoland and San Francisco, as well as the ESAR Oberpfaffenhofen dataset. The results indicate that the proposed approach demonstrates improvements in overallaccuracy, with a 1.3% and 0.8% enhancement for the AIRSAR datasets and a 0.5% improvement for the ESAR dataset. Analyses conducted on the Flevoland data underscore the effectiveness of the SDF2Net model, revealing a promising overall accuracy of 96.01% even with only a 1% sampling ratio.

Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios. We identify a critical pathology in current training paradigms where goal-driven data collection creates a dataset bias. In such datasets, language instructions are highly predictable from visual observations alone, causing the conditional mutual information between instructions and actions to vanish, a phenomenon we term Information Collapse. Consequently, models degenerate into vision-only policies that ignore language constraints and fail in out-of-distribution (OOD) settings. To address this, we propose LangForce, a novel framework that enforces instruction following via Bayesian decomposition. By introducing learnable Latent Action Queries, we construct a dual-branch architecture to estimate both a vision-only prior $p(a \mid v)$ and a language-conditioned posterior $π(a \mid v, \ell)$. We then optimize the policy to maximize the conditional Pointwise Mutual Information (PMI) between actions and instructions. This objective effectively penalizes the vision shortcut and rewards actions that explicitly explain the language command. Without requiring new data, LangForce significantly improves generalization. Extensive experiments across on SimplerEnv and RoboCasa demonstrate substantial gains, including an 11.3% improvement on the challenging OOD SimplerEnv benchmark, validating the ability of our approach to robustly ground language in action.

Hyperspectral image (HSI) classification typically involves large-scale data and computationally intensive training, which limits the practical deployment of deep learning models in real-world remote sensing tasks. This study introduces SpectralTrain, a universal, architecture-agnostic training framework that enhances learning efficiency by integrating curriculum learning (CL) with principal component analysis (PCA)-based spectral downsampling. By gradually introducing spectral complexity while preserving essential information, SpectralTrain enables efficient learning of spectral -- spatial patterns at significantly reduced computational costs. The framework is independent of specific architectures, optimizers, or loss functions and is compatible with both classical and state-of-the-art (SOTA) models. Extensive experiments on three benchmark datasets -- Indian Pines, Salinas-A, and the newly introduced CloudPatch-7 -- demonstrate strong generalization across spatial scales, spectral characteristics, and application domains. The results indicate consistent reductions in training time by 2-7x speedups with small-to-moderate accuracy deltas depending on backbone. Its application to cloud classification further reveals potential in climate-related remote sensing, emphasizing training strategy optimization as an effective complement to architectural design in HSI models. Code is available at https://github.com/mh-zhou/SpectralTrain.

Recent advances in visual generative models have highlighted the promise of learning generative world models. However, most existing approaches frame world modeling as novel-view synthesis or future-frame prediction, emphasizing visual realism rather than the structured uncertainty required by embodied agents acting under partial observability. In this work, we propose a different perspective: world modeling as embodied belief inference in 3D space. From this view, a world model should not merely render what may be seen, but maintain and update an agent's belief about the unobserved 3D world as new observations are acquired. We identify several key capabilities for such models, including spatially consistent scene memory, multi-hypothesis belief sampling, sequential belief updating, and semantically informed prediction of unseen regions. We instantiate these ideas in 3D-Belief, a generative 3D world model that infers explicit, actionable 3D beliefs from partial observations and updates them online over time. Unlike prior visual prediction models, 3D-Belief represents uncertainty directly in 3D, enabling embodied agents to imagine plausible scene completions and reason over partially observed environments. We evaluate 3D-Belief on 2D visual quality for scene memory and unobserved-scene imagination, object- and scene-level 3D imagination using our proposed 3D-CORE benchmark, and challenging object navigation tasks in both simulation and the real world. Experiments show that 3D-Belief improves 2D and 3D imagination quality and downstream embodied task performance compared to state-of-the-art methods.

Recent advancements in image animation have utilized diffusion models to breathe life into static images. However, existing controllable frameworks typically rely on Lagrangian motion guidance, where optical flow is estimated relative to the initial frame. This paper revisits the same optical-flow primitive through a more local supervision design: we use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop. This shift enables parallelized training and provides bounded-error supervision throughout the generation process. To mitigate the drift artifacts common in adjacent frame generation, we introduce a Bidirectional Geometric Consistency mechanism, which computes a forward-backward cycle check to mathematically identify and mask occluded regions, preventing the model from learning incorrect warping objectives. Extensive experiments demonstrate that our approach accelerates training, preserves temporal coherence, and reduces dynamic artifacts compared to reference-based baselines.

Current vision language models face hallucination and robustness issues against ambiguous or corrupted modalities. We hypothesize that these issues can be addressed by exploiting the shared information between modalities to compensate for the impaired one. To this end, we analyze multimodal interactions -- redundant (shared), unique (exclusive), and synergistic (emergent) task-relevant information provided by the modalities -- to determine their impacts on model reliability. Specifically, amplifying redundant interactions would increase this exploitable shared information to resolve these issues; yet, modern instruction datasets often eliminate redundancies to prioritize visual grounding. We bridge this gap through a self-captioning workflow featuring a \textsc{Multimodal Interaction Gate}: a mechanism to convert unique interactions into redundant interactions. Our findings suggest that increasing redundancy can reduce visual induced errors by 38.3\% and improve consistency by 16.8\%.

In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy both reconstruction and generation, Prologue generates a small set of prologue tokens prepended to the visual token sequence. These prologue tokens are trained exclusively with the AR cross-entropy (CE) loss, while visual tokens remain dedicated to reconstruction. This decoupled design lets us optimize generation through the AR model's true distribution without affecting reconstruction quality, which we further formalize from an ELBO perspective. On ImageNet 256x256, Prologue-Base reduces gFID from 21.01 to 10.75 without classifier-free guidance while keeping reconstruction almost unchanged; Prologue-Large reaches a competitive rFID of 0.99 and gFID of 1.46 using a standard AR model without auxiliary semantic supervision. Interestingly, driven only by AR gradients, prologue tokens exhibit emergent semantic structure: linear probing on 16 prologue tokens reaches 35.88% Top-1, far above the 23.71% of the first 16 tokens from a standard tokenizer; resampling with fixed prologue tokens preserves a similar high-level semantic layout. Our results suggest a new direction: generation quality can be improved by introducing a separate learned generative representation while leaving the original representation intact.

Modern scene reconstruction methods, such as 3D Gaussian Splatting, deliver photo-realistic novel view synthesis at real-time speeds, yet their adoption in interactive graphics applications has been limited. A major bottleneck is the difficulty of interacting with these representations compared to traditional, human-authored 3D assets. While previous research has attempted to impose semantic decomposition on these models, significant challenges remain regarding segmentation quality and consistency. To address this, we introduce Semantic Foam, extending the recently proposed Radiant Foam representations to semantic decomposition tasks. Our approach integrates the natural spatial volumetric decomposition of Radiant Foam's Voronoi mesh with an explicit semantic feature field parameterized at the cell level. This explicit structure enables direct spatial regularization, which prevents artifacts caused by occlusion or inconsistent supervision across views - common pitfalls for other point-based representations. Experimental results show that our method achieves comparable or superior object-level segmentation performance compared to state-of-the-art methods like Gaussian Grouping and SAGA.

With the widespread application of Unmanned Aerial Vehicles (UAVs) in bridge structural health monitoring, deep learning-based automatic crack detection has become a major research focus. However, practical UAV inspections still face four key challenges: weak crack features, degraded imaging conditions, severe class imbalance, and limited computational resources for practical UAV inspection workflows. To address these issues, this paper proposes a unified lightweight convolutional neural network framework composed of four synergistic components: a lightweight backbone network, a Convolutional Block Attention Module (CBAM) for channel and spatial enhancement, a directed robust augmentation strategy based on inspection-scene priors, and Focal Loss for hard-sample learning under class imbalance. Experiments on the SDNET2018 bridge deck dataset show that the proposed method achieves an inference speed of 825 FPS with only 11.21M parameters and 1.82G FLOPs. Compared with the baseline model, the complete framework improves the F1-score by 2.51% and recall by 3.95%. In addition, Grad-CAM visualizations indicate that the introduced attention module shifts the model's focus from scattered regions to precise tracking along crack trajectories. Overall, this study achieves a strong balance among accuracy, speed, and robustness, providing a practical solution for ground-station assisted real-time deployment in UAV bridge inspections. The source code is available at: https://github.com/skylynf/AttXNet .

Open-vocabulary 3D instance segmentation is a core capability for robotics and AR/VR, but prior methods trade one bottleneck for another: multi-stage 2D+3D pipelines aggregate foundation-model outputs at hundreds of seconds per scene, while pseudo-labeled end-to-end approaches rely on fragmented masks and external region proposals. We present SpaCeFormer, a proposal-free space-curve transformer that runs in 0.12--0.30 seconds per scene across standard benchmarks, 2--3 orders of magnitude faster than multi-stage 2D+3D pipelines. We pair it with SpaCeFormer-3M, the largest open-vocabulary 3D instance segmentation dataset (3.0M multi-view-consistent captions over 604K instances from 7.4K scenes) built through multi-view mask clustering and multi-view VLM captioning; it reaches 21$\times$ higher mask recall than prior single-view pipelines (54.3% vs 2.5% at IoU$>$0.5). SpaCeFormer combines spatial window attention with Morton-curve serialization for spatially coherent features, and uses a RoPE-enhanced decoder to predict instance masks directly from learned queries without external proposals. On ScanNet200 we achieve 11.1 zero-shot mAP, a 2.8$\times$ improvement over the prior best proposal-free method; on ScanNet++ and Replica, we reach 22.9 and 24.1 mAP, surpassing all prior methods including those using multi-view 2D inputs.

Recovering camera parameters from images and rendering scenes from novel viewpoints have been treated as separate tasks in computer vision and graphics. This separation breaks down when image coverage is sparse or poses are ambiguous, since each task depends on what the other produces. We propose Rays as Pixels, a Video Diffusion Model (VDM) that learns a joint distribution over videos and camera trajectories. To our knowledge, this is the first model to predict camera poses and do camera-controlled video generation within a single framework. We represent each camera as dense ray pixels (raxels), a pixel-aligned encoding that lives in the same latent space as video frames, and denoise the two jointly through a Decoupled Self-Cross Attention mechanism. A single trained model handles three tasks: predicting camera trajectories from video, generating video from input images along a pre-defined trajectory, and jointly synthesizing video and trajectory from input images. We evaluate on pose estimation and camera-controlled video generation, and introduce a closed-loop self-consistency test showing that the model's predicted poses and its renderings conditioned on those poses agree. Ablations against Plücker embeddings confirm that representing cameras in a shared latent space with video is subtantially more effective.

6D object pose estimation in cluttered scenes remains challenging due to severe occlusion and sensor noise. We propose MAPRPose, a two-stage framework that leverages mask-aware correspondences for pose proposal and amodal-driven Region-of-Interest (ROI) prediction for robust refinement. In the Mask-Aware Pose Proposal (MAPP) stage, we lift 2D correspondences into 3D space to establish reliable keypoint matches and generate geometrically consistent pose hypotheses based on correspondence-level scoring, from which the top-$K$ candidates are selected. In the refinement stage, we introduce a tensorized render-and-compare pipeline integrated with an Amodal Mask Prediction and ROI Re-Alignment (AMPR) module. By reconstructing complete object geometry and dynamically adjusting the ROI, AMPR mitigates localization errors and spatial misalignment under heavy occlusion. Furthermore, our GPU-accelerated RGB-XYZ reprojection enables simultaneous refinement of all $N \times B$ pose hypotheses in a single forward pass. Evaluated on the BOP benchmark, MAPRPose achieves a state-of-the-art Average Recall (AR) of 76.5%, outperforming FoundationPose by 3.1% AR while delivering a 43x speedup in multi-object inference.

Accurate distance estimation from monocular cameras is essential for intelligent monitoring systems. In many deployments, image coordinates are mapped to ground positions using planar homographies initialized by manual selection of corresponding regions. Small inaccuracies in this initialization propagate into systematic distance distortions. This paper derives an explicit relationship between homography perturbations and the resulting distance error, showing that the error grows approximately quadratically with the true distance from the camera. Based on this model, two simple correction strategies are evaluated: regression-based estimation of the quadratic error function and direct optimization of the homography via coordinate-based gradient descent. A large-scale simulation study with more than 19 million test samples demonstrates that regression achieves higher peak accuracy when the model is reliably fitted, whereas gradient descent provides greater robustness against poor initial calibration. This suggests that improving geometric calibration may yield greater performance gains than increasing model complexity in many practical systems.

By combining complementary benefits of short- and long-exposure images, Dual-Exposure Imaging (DEI) enhances image quality in low-light scenarios. However, existing DEI approaches inevitably suffer from producing artifacts due to spatial displacement from scene motion and image feature discrepancies from different exposure times. To tackle this problem, we propose a novel Event-based DEI (E-DEI) algorithm, which reconstructs high-quality images from dual-exposure image pairs and events, leveraging high temporal resolution of event cameras to provide accurate inter-/intra-frame dynamic information. Specifically, we decompose this complex task into an integration of two sub-tasks, i.e., event-based motion deblurring and low-light image enhancement tasks, which guides us to design E-DEI network as a dual-path parallel feature propagation architecture. We propose a Dual-path Feature Alignment and Fusion (DFAF) module to effectively align and fuse features extracted from dual-exposure images with assistance of events. Furthermore, we build a real-world Dataset containing Paired low-/normal-light Images and Events (PIED). Experiments on multiple datasets show the superiority of our method. The code and dataset are available at github.

Convolutional neural networks (CNNs) achieve state-of-the-art performance in medical image analysis yet remain opaque, limiting adoption in high-stakes clinical settings. Existing approaches face a fundamental trade-off: post-hoc methods provide unfaithful approximate explanations, while inherently interpretable architectures are faithful but often sacrifice predictive performance. We introduce TTE-CAM, a test-time framework that bridges this gap by converting pretrained black-box CNNs into self-explainable models via a convolution-based replacement of their classification head, initialized from the original weights. The resulting model preserves black-box predictive performance while delivering built-in faithful explanations competitive with post-hoc methods, both qualitatively and quantitatively. The code is available at https://github.com/kdjoumessi/Test-Time-Explainability

Performance gains of Vision Language Models (VLMs) obtained by fine-tuning are generally based on ad hoc data collection and annotation of real-world scenes. Despite the improvements, this process is often prone to biases, errors, and distribution imbalance, resulting in overfitting and imbalanced performance. Although a few studies have explored synthetic data generation, they typically lack control over data distribution and annotation quality. In this work, we re-evaluate the potential of model fine-tuning by exploring a fully controlled data generation and annotation pipeline, obtaining bias-free data with balanced distribution and clean annotations. Using the spatial reasoning task of identifying the absolute position of an object as a use case, we fine-tune state-of-the-art VLMs and conduct exhaustive evaluations on both synthetic and real-world benchmarks, including transferability to real-world scenes. Our experiments reveal two key findings: 1) fine-tuning on balanced data yields uniform performance across the visual scene and mitigates common biases with as few as 130 samples; and 2) fine-tuning on synthetic stimuli improves performance by 13% on real-world data (COCO), outperforming models fine-tuned on the full COCO train set.

Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individual modality encoders are applied to inherently intra-modal tasks like image-to-image retrieval, their performance suffers from the intra-modal misalignment. In this paper we study intra-modal misalignment in CLIP with a focus on the role of the projectors that map pre-projection image and text embeddings into the shared embedding space. By analyzing the form of the cosine similarity applied to projected features, and its interaction with the contrastive CLIP loss, we show that there is an inter-modal operator responsible for aligning the two modalities during training, and a second, intra-modal operator that only enforces intra-modal normalization but does nothing to promote intra-modal alignment. Via spectral analysis of the inter-modal operator, we identify an approximately isotropic subspace in which the two modalities are well-aligned, as well as anisotropic directions specific to each modality. We demonstrate that this aligned subspace can be directly obtained from the projector weights and that removing the anisotropic directions improves intra-modal alignment. Our experiments on intra-modal retrieval and classification benchmarks show that our training-free method reduces intra-modal misalignment, greatly lowers latency, and outperforms existing approaches across multiple pre-trained CLIP-like models. The code is publicly available at: https://github.com/simomagi/IsoCLIP.

In this work, we present and investigate the novel blind inverse problem of position-blind ptychography, i.e., ptychographic phase retrieval without any knowledge of scan positions, which then must be recovered jointly with the image. The motivation for this problem comes from single-particle diffractive X-ray imaging, where particles in random orientations are illuminated and a set of diffraction patterns is collected. If one uses a highly focused X-ray beam, the measurements would also become sensitive to the beam positions relative to each particle and therefore ptychographic, but these positions are also unknown. We investigate the viability of image reconstruction in a simulated, simplified 2-D variant of this difficult problem, using variational inference with modern data-driven image priors in the form of score-based diffusion models. We find that, with the right illumination structure and a strong prior, one can achieve reliable and successful image reconstructions even under measurement noise, in all except the most difficult evaluated imaging scenario.

World Models (WMs) offer a promising mechanism for post-training Vision-Language-Action (VLA) policies by providing dynamics priors that improve generalization under task and scene variation. However, most WM-based post-training methods rely on pixel-space supervision, making policies sensitive to visual artifacts introduced by imperfect WM rollouts. We present World2Act, a latent-space post-training framework that transfers WM dynamics to the VLA policy without pixel-space supervision. World2Act operates in two stages: 1) it induces a shared video-action latent space by contrastively aligning WM-dynamics latents with action embeddings, and 2) it post-trains the VLA by guiding policy action representations toward WM-imagined dynamics rather than decoded pixels. Built on GR00T-N1.6, World2Act delivers absolute success-rate gains of up to +2.5% on simulation benchmarks (RoboCasa, LIBERO, Bridge-SIMPLER) and +6.7% on a real robot over finetuned VLA baselines. Notably, it outperforms pixel-space WM supervision by up to +6.0%, including on LIBERO where pixel supervision degrades the baseline, suggesting that latent WM dynamics offer a more stable WM-based post-training alternative to pixel-space transfer.

Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically by estimating a simplified causal structure of the model. In existing work, this causal structure often includes relationships where the presence of a concept is associated with a strong activation of a neuron. For example, attribution methods primarily identify input pixels that contribute most to a prediction, and feature visualization methods reveal inputs that cause high activation of a target neuron - the former implicitly assuming that the relevant information resides in the input, and the latter that neurons encode the presence of concepts. However, a largely overlooked type of causal relationship is that of encoded absences, where the absence of a concept increases neural activation. In this work, we show that such missing but relevant concepts are common and that mainstream XAI methods struggle to reveal them when applied in their standard form. To address this, we propose two simple extensions to attribution and feature visualization techniques that uncover encoded absences. Across experiments, we show how mainstream XAI methods can be used to reveal and explain encoded absences, how ImageNet models exploit them, and that debiasing can be improved when considering them.

Brain tumors result in 20 years of lost life on average. Standard therapies induce complex structural changes in the brain that are monitored through MRI. Recent developments in artificial intelligence (AI) enable conditional multimodal image generation from clinical data. In this study, we investigate AI-driven generation of follow-up MRI in patients with intracranial tumors through conditional image generation. This approach enables realistic modeling of post-radiotherapy changes, allowing for treatment optimization. The public SAILOR dataset of 25 patients was used to create a 2D rectified flow model conditioned on axial slices of pre-treatment MRI and RT dose maps. Cross-attention conditioning was used to incorporate temporal and chemotherapy data. The resulting images were validated with structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), Dice scores and Jacobian determinants. The resulting model generates realistic follow-up MRI for any time point, while integrating treatment information. Comparing real versus predicted images, SSIM is 0.88, and PSNR is 22.82. Tissue segmentations from real versus predicted MRI result in a mean Dice-Sørensen coefficient (DSC) of 0.91. The rectified flow (RF) model enables up to 250x faster inference than Denoising Diffusion Probabilistic Models (DDPM). The proposed model generates realistic follow-up MRI in real-time, preserving both semantic and visual fidelity as confirmed by image quality metrics and tissue segmentations. Conditional generation allows counterfactual simulations by varying treatment parameters, producing predicted morphological changes. This capability has potential to support adaptive treatment dose planning and personalized outcome prediction for patients with intracranial tumors. Code will be available upon peer-reviewed publication at: https://github.com/SelenaIHuisman/RF-GlioPREDICT

Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical ``spatial intelligence gap,'' where models fail to construct coherent 3D mental representations from 2D observations. We uncover this gap via diagnostic analyses showing the bottleneck is a missing view-consistent spatial interface rather than insufficient visual features or weak reasoning. To bridge this, we introduce \textbf{3ViewSense}, a framework that grounds spatial reasoning in Orthographic Views. Drawing on engineering cognition, we propose a ``Simulate-and-Reason'' mechanism that decomposes complex scenes into canonical orthographic projections to resolve geometric ambiguities. By aligning egocentric perceptions with these allocentric references, our method facilitates explicit mental rotation and reconstruction. Empirical results on spatial reasoning benchmarks demonstrate that our method significantly outperforms existing baselines, with consistent gains on occlusion-heavy counting and view-consistent spatial reasoning. The framework also improves the stability and consistency of spatial descriptions, offering a scalable path toward stronger spatial intelligence in multimodal systems.~\footnote{https://github.com/Jasaxion/3ViewSense}