Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double compute, or by introducing specialized parameterizations and multi-stage pipelines that fragment optimization. In this paper, we introduce Fixed-Point Distillation (FPD), an end-to-end framework that constructs local correction targets by partially corrupting the student's one-step draft and refining it with a single teacher step. To compute the training objective in a semantically meaningful space, we lift discrete tokens into continuous features and apply a multi-bandwidth drift loss that iteratively accumulates these corrections. To backpropagate through the discrete bottleneck, we employ a straight-through estimator that feeds exact hard-sampled tokens to the teacher and decoder during the forward pass, ensuring that training and inference operate on the same codebook manifold, while routing continuous gradients back to the student logits. This fully differentiable pathway additionally accommodates an optional unconditional adversarial objective to enhance perceptual realism. Evaluations on both class- and text-conditional generation validate the effectiveness of our framework. FPD achieves competitive visual fidelity and structural alignment within a single inference step, narrowing the gap to multi-step teachers while outperforming existing discrete distillation baselines.

Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-world scenarios require external knowledge that is not directly observable in the image to answer correctly. We introduce WikiVQABench, a human-curated knowledge-grounded VQA benchmark constructed by systematically combining Wikipedia images, their associated article captions, and structured knowledge from Wikidata. Our pipeline uses large language models (LLMs) to generate candidate multiple-choice image-question-answer sets. All generated instances are subsequently reviewed and curated by human annotators to ensure factual correctness, visual-text consistency, and that each question requires external knowledge in addition to visual evidence for correct resolution. WikiVQABench comprises a substantial collection of Wikipedia images with curated multiple-choice questions designed to benchmark knowledge-aware vision-language models (VLMs). Evaluation of fifteen VLMs (256M-90B parameters) reveals a wide performance range (24.7%-75.6% accuracy), demonstrating that the benchmark effectively discriminates model capabilities on knowledge-intensive reasoning. The dataset and benchmarking code are publicly available.

Pose-driven full-body avatars built on neural rendering produce high-quality novel views of a captured subject. Yet loose clothing and other dynamic elements deform in ways pose alone cannot explain: the same pose can correspond to many different states, because their motion depends on history, inertia, and contact. Explicit simulation and layered-garment methods can model such dynamics, but they require either a dedicated garment template, which raw multi-view capture does not naturally provide, or a test-time physics simulator with non-trivial runtime cost. A parallel line of work learns data-driven clothing avatars that avoid explicit garment layers. These methods add an auxiliary latent for variation beyond pose; at inference, they fix it, regress it from pose, or retrieve it from training data, without explicitly modeling how the latent evolves with its own dynamics. Additionally, even in everyday motion with loose clothing, existing architectures often struggle to capture fine-grained detail, producing blurry renderings and temporal artifacts. We augment a pose-conditioned 3D Gaussian avatar with a transformer-based decoder and a dynamics residual latent that captures temporal appearance and geometry variation beyond the driving signals. At inference, a learned latent dynamics model evolves the residual latent from a short pose history and the previous latent state. The model decomposes each update into driving, restoring, and dissipative forces, producing temporally coherent, history-dependent rollouts with negligible added cost. Different initial conditions yield diverse yet plausible motion trajectories, and the force decomposition exposes controls such as stiffness. Across nine captured sequences of everyday motion with diverse loose garments, quantitative metrics and a perceptual user study show improved animation quality over recent data-driven baselines.

Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet satisfying editing results. We attribute this limitation to the prevalent data-to-data paradigm, which is less compatible with modern generative models than noise-to-data generation. To address this gap, we revisit video editing from a noise-to-data perspective and propose Streaming-Generation-based Video Editing (StreamGVE), which preserves few-step sampling while seamlessly injecting source-video conditions. Built on pre-trained streaming generation models, StreamGVE introduces dual-branch fast sampling with a self-attention bridge and cross-attention grounding/boosting to satisfy both sampling and conditioning requirements. We further propose source-oriented guidance to improve target-generation quality, and a visual prompting strategy to enhance editing flexibility and practicality. The method is effective, robust, and generalizable across different models. Extensive experiments on diverse video editing tasks show that StreamGVE consistently outperforms existing approaches, even in few-step settings with minimal time cost.

We introduce ProtoPathway, an interpretable-by-design multimodal framework for cancer survival prediction that unifies whole slide imaging and transcriptomics through encoders producing biologically grounded representations on both sides of the fusion. On the histopathology side, $K$ learnable morphological prototypes, trained end-to-end with the survival objective, serve as the slide representation itself: patches flow into prototype tokens via soft assignment, compressing variable-length patch sets into fixed task-adaptive tokens. On the genomic side, a bipartite graph neural network encodes gene expression within the Reactome pathway hierarchy, producing pathway embeddings that reflect both constituent genes and their broader biological context through bidirectional message passing over a shared gene--pathway graph. Cross-modal attention then operates over a compact prototype $\times$ pathway matrix in which prototypes query pathways, modeling the biological direction in which molecular programs give rise to tissue morphology. Because both axes carry stable task-learned identity, the attention matrix is itself an interpretability output, yielding native inference-time attribution across the full biological hierarchy, from genes through pathways and prototypes to spatial tissue maps. We evaluate on five TCGA cancer cohorts, demonstrating competitive or superior survival prediction with substantially improved biological interpretability and reduced computational cost, with interpretability claims validated through fold-stratified rank-based population-level analysis. Our source code, model weights, and Reactome pathways, together with a unified codebase reimplementing all multimodal survival baselines under identical preprocessing and evaluation, are available at: https://github.com/AmayaGS/ProtoPathway.

Vision-language models (VLMs) are increasingly being explored for video game quality assurance, especially gameplay glitch detection. Most existing evaluations, however, treat glitches as static visual anomalies, asking models to detect failures from a single frame. We argue that this framing misses a key distinction: some glitches are spatial and visible in an isolated frame, whereas others are temporal and become evident only through changes across ordered frames. A preliminary study confirms this gap, showing that temporal glitches are substantially harder for VLMs to detect than spatial ones. To enable systematic evaluation of this underexplored setting, we introduce TempGlitch, a controlled gameplay video benchmark for temporal glitch detection. TempGlitch covers five temporal glitch types with balanced per-category samples, together with paired glitch-free videos that enable reliable binary evaluation. We evaluate 12 proprietary and open-weight VLMs across multiple frame-sampling settings. Our results show that current VLMs remain near chance on TempGlitch, often collapsing into either overly conservative behavior that misses most glitches or overly sensitive behavior that flags clean videos as glitchy. Moreover, denser frame sampling and larger model size do not reliably resolve these failures. TempGlitch provides a focused testbed for temporal reasoning, robust gameplay understanding, and automated glitch detection with VLMs. Code and data are available at the project website.

Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing significant challenges to both visual clarity and temporal consistency. Current state-of-the-art methods are based on transformer, 3D architectures and require multi-frame input, but their large computational cost and memory usage limit real-time deployment, especially in resource-constrained scenarios. In this work, we propose ReMATF, a lightweight recurrent framework that restores videos using only two frames at a time while preserving spatial detail and temporal stability. ReMATF combines a multi-scale encoder-decoder with temporal warping and a motion-adaptive temporal fusion module that performs per-pixel fusion between the warped previous output and the current prediction to enhance coherence without enlarging the temporal window. This design reduces flicker, sharpens details, and remains efficient. Experiments on synthetic and real turbulence datasets show consistent improvements in PSNR/SSIM and perceptual quality (LPIPS), along with substantially faster inference than multi-frame transformer baselines, making ReMATF suitable turbulence mitigation in resource-constrained scenarios.

In sixth-generation (6G) ultra-dense networks, aggressive frequency reuse amplifies inter-cell interference (ICI), making multi-cell orthogonal frequency-division multiple access (OFDMA) scheduling and power control strongly coupled across neighboring cells. We study distributed downlink resource management -- joint subcarrier scheduling and power allocation -- under interference coupling and long-term per-user quality-of-service (QoS) minimum-rate constraints. By using virtual-queue deficit weights to enforce long-term QoS, we develop FedCritic, a serverless federated multi-agent actor-critic framework with decentralized execution. Unlike centralized training with decentralized execution (CTDE) approaches that require centralized critic learning and joint trajectory aggregation, FedCritic federates the critic through lightweight gossip-based parameter averaging over the interference graph, enabling stable value estimation without a central coordinator while keeping policies local. Simulations in an interference-rich reuse-1 setting show that FedCritic improves mean signal-to-interference-plus-noise ratio (SINR) and cell-edge rate, increases network-wide average sum-rate and fairness relative to non-coordinated and CTDE baselines, and achieves more stable training with lower coordination overhead.

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-language backbones. However, most existing VLAs rely primarily on 2D visual representations, which limit their ability to reason about fine-grained geometry and spatial grounding - capabilities that are essential for precise and robust manipulation in 3D environments. In this paper, we propose PointACT, a dual-system 3D-aware VLA policy that integrates hierarchical 3D point cloud representations directly into the action decoding process. PointACT employs a multi-scale point-action interaction mechanism with efficient bottleneck window self-attention, enabling evolving action tokens to densely attend to both local geometric detail and global scene structure. We evaluate PointACT on the LIBERO and RLBench benchmarks and systematically compare it against monolithic and dual-system VLA baselines, including variants augmented with point cloud inputs. PointACT achieves consistent improvements across both benchmarks, increasing success rates by 10% on the challenging RLBench-10Tasks suite over state-of-the-art pretrained VLAs, with even larger gains when the vision-language backbone is frozen and the action expert is trained from scratch. Extensive ablation studies demonstrate that tightly coupling hierarchical 3D geometry with pretrained 2D semantic representations is critical for robust and spatially grounded robot control. Our results also highlight the promise of pretrained 3D representations for 3D-aware VLA policies.

Existing video-language models can generate factual descriptions of road events but lack control over how these events are expressed: their tone, urgency, or style. This limits deployment in communication-critical settings where the effectiveness of a message depends on both content and presentation, not just factual accuracy. To mitigate this, we introduce a comprehensive dataset-model-evaluation suite for tone-controllable road video captioning. Our human-validated data generation pipeline expands road-video corpora with diverse tonal annotations and multi-tone captions, yielding the RoadTones-51K dataset. We propose RoadTones-VL-CoT, a controllable video-to-text model that also generates tone-conditioned Chain-of-Thought intermediate drafts for interpretability. We also introduce RoadTones-Eval, a new evaluation suite that jointly measures factual consistency and tone adherence. In addition, we conducted a user study whose results validate caption quality, tone control, and factual consistency. Together, these contributions lay the foundation for context-sensitive tone-controllable video captioning.

Recent advances in Image Restoration (IR) have been largely driven by generative methods such as Diffusion Models and Flow Matching, which excel in synthesizing realistic textures while suffering from slow multi-step inference and compromised pixel fidelity. In contrast, classical regression-based IR methods excel precisely in these aspects, offering single-step efficiency and high pixel-level reconstruction fidelity. To bridge this gap, we propose DiSI, a unified framework that Disentangles the underlying Stochastic Interpolant process into independent generation and regression components. This decoupling endows DiSI with remarkable versatility, enabling a continuous and controllable transition from a pure regression process to a fully generative one. Technically, we instantiate this framework with two specific sampling trajectories, accompanied by a unified sampler for high-quality, few-step inference on arbitrary trajectories. Furthermore, we design a dual-branch U-Net style transformer network in pixel space, using a dedicated branch to enhance conditional guidance while ensuring high throughput. Extensive experiments demonstrate that DiSI efficiently achieves competitive results on various IR tasks, while uniquely offering the inference-time flexibility to control the distortion-perception trade-off within a single model.

Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training with near-infinite synthetic data a promising direction. However, naively incorporating all available synthetic data is inefficient and leads to distribution shifts, and optimizing data mixture under practical training budgets remains a critical yet under-explored problem. In this sense, we claim that the mixture of training data requires clear guidance in terms of scene types and quantities. Particularly in this work, we conceptualize the data mixture approximately as a dynamic optimization process that iteratively adjusts the training data mixture to maximize model performance, guided by closed-loop evaluation feedback, and propose AutoScale, a fully automated closed-loop data engine unifying scene representation, data mixture optimization and retrieval, as well as model training and evaluation. Specifically, we propose Graph Regularized AutoEncoder (Graph-RAE) for driving scene representations, introduce Cluster-aware Gradient Ascent (Cluster-GA) for cluster-wise importance estimation and reweighting, and perform cluster-guided vector retrieval to select high-value samples. Experiments on NavSim demonstrate that AutoScale outperforms vanilla co-training and cross-domain baselines, achieving better performance with fewer synthetic samples under constrained budgets.

Acquiring usable optical imagery in Antarctica is inherently challenging due to prolonged polar nights and frequent cloud cover. Landsat provides the longest and most continuous optical observations and constitutes one of the most important remote sensing data sources for Antarctic studies. However, the scan-line corrector (SLC) failure in 2003 resulted in approximately 22% missing pixels in Landsat 7 ETM+ SLC-off imagery, severely limiting its usability. Unlike many non-polar environments, Antarctic surfaces undergo rapid and substantial changes, which makes it difficult to obtain reliable reference imagery and reduces the applicability of conventional reference-based gap-filling methods. To address this challenge, we propose DiffGF, a non-reference diffusion-based framework for restoring Landsat 7 SLC-off imagery without requiring any external reference data. DiffGF adopts a two-stage design consisting of a latent-space diffusion process and a pixel-space refinement. A dedicated Antarctic dataset, SLCANT, is constructed for training and evaluation. Quantitative and qualitative results demonstrate that DiffGF restores Antarctic SLC-off imagery with high fidelity. Its practical value is further examined through a downstream crevasse segmentation application. The results suggest that DiffGF provides a useful approach for exploiting Landsat 7 SLC-off archives in Antarctica, enabling the extraction of valuable information from historical records and supporting related Antarctic studies.

Recent layout-to-image models have achieved remarkable progress in spatial controllability. However, they still struggle with inter-object occlusion. When bounding boxes overlap, most existing methods lack explicit occlusion information, which makes the generation in intersection regions inherently ambiguous and hinders the determination of complex occlusion relationships. As a result, they often produce entangled textures or physically inconsistent layering in the overlapped areas. To address this issue, we first construct SA-Z, a large-scale dataset enriched with explicit occlusion ordering and pixel-level annotations. Building upon our proposed dataset, we introduce OcclusionFormer, a novel occlusion-aware Diffusion Transformer framework that explicitly models Z-order priority by decoupling instances and compositing them via volume rendering. Furthermore, to ensure fine-grained spatial precision, we introduce a queried alignment loss that explicitly supervises individual instances and enhances semantic consistency. The proposed method effectively reduces ambiguity in overlapping regions, enforces correct occlusion dependencies, and preserves structural integrity, leading to substantial accuracy gains across diverse scenes.

Cooperative perception enabled by Vehicle-to-Everything (V2X) communication enhances autonomous driving safety by creating a unified environmental representation through shared sensory data. While recent works have advanced multi-agent fusion for improved perception, uncertainty quantification in such cooperative frameworks remains largely unexplored. This paper introduces Hyper-V2X, a hypernetwork-based framework for estimating both epistemic and aleatoric uncertainties in V2X-based perception. Specifically, we propose a partial weight generation scheme and V2X context embedding module that conditions a Bayesian hypernetwork on fused multi-agent features to generate weight distributions for stochastic Bird's-Eye-View (BEV) segmentation. Unlike existing deterministic BEV models, Hyper-V2X enables efficient uncertainty estimation with little computation overhead. Our approach is architecture-agnostic, and can be seamlessly integrating with modern cooperative backbones such as CoBEVT. Experiments on the OPV2V benchmark demonstrate that Hyper-V2X provides accurate, well-calibrated uncertainty estimates and improves overall perception reliability. Our code and benchmark are publicly available under an open-source license: https://github.com/abhishekjagtap1/Hyper-V2X

State Space Models (SSMs) have emerged as a powerful and efficient alternative to Transformers, demonstrating linear-time complexity and exceptional sequence modeling capabilities. However, their application to vision tasks remains challenging. First, existing vision SSMs largely depend on manually designed fixed scanning methods to flatten image patches into sequences, which imposes predefined geometric structures and increases the complexity. Second, the broader adoption of vision SSMs is hindered in domains that require query-based interactions between distinct information streams. This is a result of the inherently causal and self-referential nature of SSMs designed for 1D sequence modeling tasks. This fusion mechanism is indispensable for critical perception tasks such as multi-view 3D fusion. To address these limitations, we propose Deformba, a context adaptive method that dynamically augments the spatial structural information while maintaining the linear complexity of SSMs. Deformba also allows multi-modal fusion like cross attention. To demonstrate the effectiveness and general applicability of Deformba, we test its performance on general 2D vision tasks such as image classification, object detection, and segmentation, as well as 3D vision tasks like BEV perception. Extensive experiments show that Deformba achieves strong performance across various visual perception benchmarks.

In biomedical Subgroup Discovery, practitioners are interested in discovering interpretable and homogeneous subgroups within a group of patients. In this paper, assuming that healthy subjects (i.e., controls) share common but irrelevant factors of variation with the patients, we motivate and develop a Contrastive Subgroup Discovery method, entitled Deep UCSL. By contrasting patients with controls, Deep UCSL identifies subgroups driven solely by pathological factors, ignoring common variability shared with healthy subjects. Our framework employs a deep feature extractor to learn a discriminative representation space. Mathematically, we derive a novel loss based on the conditional joint likelihood of latent clusters and patient/control labels, optimized via an Expectation-Maximization strategy alternating between subgroup inference and feature encoder updates. A regularization term further encourages representations to capture disease-specific variability while ignoring variability shared with controls. Compared to previous related works, our approach quantitatively improves the quality of the estimated subgroups, as demonstrated on a MNIST example and four distinct real medical imaging datasets. Code and datasets are available at: https://github.com/rlouiset/deep_ucsl.

Object hallucination is a significant challenge that hinders the application of large vision-language models (LVLMs) in practice. We hypothesize that one possible origin of hallucination is the model's tendency to prioritize text generation over meaningful interaction with images. To explore this, we examine the generation process and categorize text tokens into three groups: image-positive, invariant, and negative, based on their visual dependence on input image tokens. Our analysis reveals that most generated tokens are minimally influenced by the image information. This suggests that during the model's training stage, more emphasis is placed on learning how to follow textual instructions, rather than extracting information from images. Based on this finding, we propose adjusting the training weights of different tokens depending on their visual dependence to control hallucination. Additionally, we remove a portion of the training data that potentially contains more hallucinations as a data filtering strategy. Both methods achieve a reduction in hallucination without compromising response length or introducing additional computational costs during inference. We validate our methods across three LVLM variants, demonstrating the effectiveness and general applicability.

High-fidelity EEG generation is critical for alleviating data scarcity and addressing privacy constraints in large-scale neural modeling. Despite recent progress, most existing approaches formulate EEG generation via discrete denoising objectives, which inadequately reflect the inherently continuous temporal dynamics and spectral structure of neural activity. As a result, these methods often struggle to preserve long-range temporal dependencies and exhibit mismatches in the spectral and temporal structure of the generated signals. In this work, we argue that effective EEG generation requires models that operate directly on the continuous evolution of neural signals. We introduce Just EEG Transformer (JET), a generative framework based on conditional flow matching that models EEG as raw sequences evolving along continuous trajectories. By learning a smooth vector field that transports noise to the EEG data distribution, JET captures temporal continuity and transient dynamics without relying on discretized denoising schemes or domain-specific representations. To ensure that the learned dynamics remain consistent with key properties of EEG signals, we introduce principled constraints that preserve spectral structure, temporal stationarity, and signal-level statistics. Across three large-scale benchmarks, JET consistently achieves state-of-the-art performance, reducing TS-FID by over 40% compared to strong baselines. Extensive analyses show that JET captures key structural properties of neural dynamics, providing a scalable and principled approach to EEG generation. Project page: https://y-research-sbu.github.io/JET/ .

Training large text-to-image models requires high-quality, curated datasets with diverse content and detailed captions. Yet the cost and complexity of collecting, filtering, deduplicating, and re-captioning such corpora at scale hinders open and reproducible research in the field. We introduce MONET, an open Apache 2.0 dataset of approx. 104.9M image--text pairs collected from 2.9B raw pairs across heterogeneous open sources through successive stages of safety filtering, domain-based filtering, exact and near-duplicate removal, and re-captioning with multiple vision-language models covering short to long-form descriptions, and further augmented with synthetically generated samples. Each image is shipped with pre-computed embeddings and annotations to accelerate downstream use. To validate the effectiveness of MONET, we train a 4B-parameter latent diffusion model exclusively on it and reach competitive GenEval and DPG scores, demonstrating that our dataset lowers the barrier to large-scale, reproducible text-to-image research.

This paper presents CircleID, a large-scale ICDAR 2026 competition on writer identification and pen classification from scanned hand-drawn circles. The primary objective is to investigate how biometric writer characteristics and physical pen features naturally entangle within minimal, static traces. CircleID comprises two distinct tasks: (1) open-set writer identification, requiring models to recognize known writers while explicitly rejecting unknown ones, and (2) cross-writer pen classification, evaluated across both seen and unseen writers. Participants were provided with a new, controlled dataset of 46,155 tightly cropped circle images, digitized at 400 DPI and annotated for writer identity and pen type. The dataset comprises samples from 44 known and 22 unknown writers using eight different pens. Hosted on Kaggle as two separate tracks with public and private leaderboards, the competition provided participants with a ResNet baseline. In total, 389 teams (436 participants) made 3,185 submissions for the pen classification task, and 113 teams (141 participants) made 1,737 submissions for the writer identification track. The best-performing private leaderboard submissions achieved a Top-1 accuracy of 64.801% for writer identification and 92.726% for pen classification. This paper details the dataset, evaluates the winning methodologies, and analyzes the impact of out-of-distribution writers on model generalization and feature disentanglement. In this large-scale competition, CircleID establishes a new baseline for minimal-trace analysis.

Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel Tutor-Student Reinforcement Learning (TSRL) framework to dynamically optimize the training curriculum. Our method models the training process as a Markov Decision Process where a ``Tutor'' agent learns to guide a ``Student'' (the deepfake detector). The Tutor, implemented as a Proximal Policy Optimization (PPO) agent, observes a rich state representation for each training sample, encapsulating not only its visual features but also its historical learning dynamics, such as EMA loss and forgetting counts. Based on this state, the Tutor takes an action by assigning a continuous weight (0-1) to the sample's loss, thereby dynamically re-weighting the training batch. The Tutor is rewarded based on the Student's immediate performance change, specifically rewarding transitions from incorrect to correct predictions. This strategy encourages the Tutor to learn a curriculum that prioritizes high-value samples, such as hard-but-learnable examples, leading to a more efficient and effective training process. We demonstrate that this adaptive curriculum improves the Student's generalization capabilities against unseen manipulation techniques compared to traditional training methods. Code is available at https://github.com/wannac1/TSRL.

We developed a multi-label gastrointestinal video analysis pipeline based on a ResNet-50 frame classifier followed by anatomy-guided temporal event decoding. The system predicts 17 labels, including 5 anatomy classes and 12 pathology classes, from frames resized to 336x336. A major challenge was severe class imbalance, particularly for rare pathology labels. To address this, we used clipped class-wise positive weighting in the training loss, which improved rare-class learning while maintaining stable optimization. At the temporal stage, we found that direct frame-to-event conversion produced fragmented mismatches with the official ground truth. The final submission therefore combined GT-style framewise event composition, anatomy vote smoothing, and anatomy-based pathology gating with a conservative hysteresis decoder. This design improved the final temporal mAP from 0.3801 to 0.4303 on the challenge test set.

Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, however, comparable progress has been more limited. We attribute this gap to graph-specific optimization and representation challenges that undermine the effectiveness of training neural networks with backpropagation and gradient descent. We argue that representing graphs on a fixed-size Euclidean grid, as is common in recently proposed models for supervised graph prediction, may not be the optimal choice in these settings. To support our view, we provide an analysis of neural graph generation methods and identify theoretical challenges that lead to pitfalls when training neural networks to produce graphs as their output. Motivated by this analysis, we introduce \textbf{GRA}ph~\textbf{I}mitation~\textbf{L}earning~(GRAIL), a framework for training neural networks in supervised settings in which the supervision signal is a graph. GRAIL generates graphs sequentially through a Markov decision process over embeddings of partial graphs, thereby avoiding the representation issues associated with fixed-size grid graph representations. We empirically show that GRAIL achieves competitive results on supervised graph prediction across a comprehensive suite of 18 benchmarks, matching or surpassing state-of-the-art methods in several settings.

Video generation has achieved remarkable progress, with generated videos increasingly resembling real ones. However, the rapid advance in generation has outpaced the development of adequate evaluation metrics. Currently, the assessment of talking head generation primarily relies on limited metrics, evaluating general video quality, lip synchronization, and on conducting user studies. Motivated by this, we propose a new evaluation framework comprising 8 metrics related to three dimensions (i) quality, (ii) naturalness, and (iii) synchronization. In selecting the metrics, we place emphasis on efficiency, as well as alignment with human preferences. Based on this considerations, we streamline to analyze fine-grained dynamics of head, mouth, and eyebrows, as well as face quality. Our extensive experiments on 85,000 videos generated by 17 state-of-the-art models suggest that while many algorithms excel in lip synchronization, they face challenges with generating expressiveness and artifact-free details. These videos were generated based on a novel real dataset, that we have curated, in order to mitigate bias of training data. Our proposed benchmark framework is aimed at evaluating the improvement of generative methods. Original code, dataset and leaderboards will be publicly released and regularly updated with new methods, in order to reflect progress in the field.

Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the tidy assumption that every training image is fully annotated along its taxonomy path. Reality is messier: A distant bird may be labeled only bird, while a clear close-up may justify bald eagle. We introduce free-grain training, where labels may appear at any level of the taxonomy and models must learn consistent hierarchical predictions from incomplete, mixed-granularity supervision. We build benchmark datasets with varying label granularity and show that existing hierarchical methods deteriorate sharply in this setting. To make up for missing supervision, we propose two simple solutions: One adds broad text-based supervision that captures visual attributes, and the other treats missing labels at specific taxonomy levels as a semi-supervised learning problem. We also study free-grained inference, where the model chooses how deep to predict, returning a reliable coarse label when a fine-grained one is uncertain. Together, our task, datasets, and methods move hierarchical recognition closer to the way labels arise in the real world.

Efficient and accurate feed-forward multi-view reconstruction has long been an important task in computer vision. Recent transformer-based models like VGGT, $π^3$ and MapAnything have demonstrated remarkable performance with relatively simple architectures. However, their scalability is fundamentally constrained by the quadratic complexity of global attention, which imposes a significant runtime bottleneck when processing large image sets. In this work, we empirically analyze the global attention matrix of these models and observe that the probability mass concentrates on a small subset of patch-patch interactions corresponding to cross-view geometric correspondences. Building on this insight and inspired by recent advances in large language models, we propose a training-free, block-sparse replacement for dense global attention, implemented with highly optimized kernels. Our method accelerates inference by more than $3\times$ while maintaining comparable task performance. Evaluations on a comprehensive suite of multi-view benchmarks demonstrate that our approach seamlessly integrates into existing global attention-based architectures such as VGGT, $π^3$ , and MapAnything, while substantially improving scalability to large image collections.

The human brain receives nutrients and oxygen through an intricate network of blood vessels. Pathology affecting small vessels, at the mesoscopic scale, represents a critical vulnerability within the cerebral blood supply and can lead to severe conditions, such as Cerebral Small Vessel Diseases. The advent of 7 Tesla MRI systems has enabled the acquisition of higher spatial resolution images, making it possible to visualise such vessels in the brain. However, the lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. To address this, the SMILE-UHURA challenge was organised. This challenge, held in conjunction with the ISBI 2023, in Cartagena de Indias, Colombia, aimed to provide a platform for researchers working on related topics. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. This dataset was created through a combination of automated pre-segmentation and extensive manual refinement. In this manuscript, sixteen submitted methods and two baseline methods are compared both quantitatively and qualitatively on two different datasets: held-out test MRAs from the same dataset as the training data (with labels kept secret) and a separate 7T ToF MRA dataset where both input volumes and labels are kept secret. The results demonstrate that most of the submitted deep learning methods, trained on the provided training dataset, achieved reliable segmentation performance. Dice scores reached up to 0.838 $\pm$ 0.066 and 0.716 $\pm$ 0.125 on the respective datasets, with an average performance of up to 0.804 $\pm$ 0.15.

This paper proposes an automatic image correction method for portrait photographs, which promotes consistency of facial skin color by suppressing skin color changes due to background colors. In portrait photographs, skin color is often distorted due to the lighting environment (e.g., light reflected from a colored background wall and over-exposure by a camera strobe), and if the photo is artificially combined with another background color, this color change is emphasized, resulting in an unnatural synthesized result. In our framework, after roughly extracting the face region and rectifying the skin color distribution in a color space, we perform color and brightness correction around the face in the original image to achieve a proper color balance of the facial image, which is not affected by luminance and background colors. Unlike conventional algorithms for color correction, our final result is attained by a color correction process with a guide image. In particular, our guided image filtering for the color correction does not require a perfectly-aligned guide image required in the original guide image filtering method proposed by He et al. Experimental results show that our method generates more natural results than conventional methods on not only headshot photographs but also natural scene photographs. We also show automatic yearbook style photo generation as an another application.

A retinal vessel analysis is a procedure that can be used as an assessment of risks to the eye. This work proposes an unsupervised multimodal approach that improves the response of the Frangi filter, enabling automatic vessel segmentation. We propose a filter that computes pixel-level vessel continuity while introducing a local tolerance heuristic to fill in vessel discontinuities produced by the Frangi response. This proposal, called the local-sensitive connectivity filter (LS-CF), is compared against a naive connectivity filter to the baseline thresholded Frangi filter response and to the naive connectivity filter response in combination with the morphological closing and to the current approaches in the literature. The proposal was able to achieve competitive results in a variety of multimodal datasets. It was robust enough to outperform all the state-of-the-art approaches in the literature for the OSIRIX angiographic dataset in terms of accuracy and 4 out of 5 works in the case of the IOSTAR dataset while also outperforming several works in the case of the DRIVE and STARE datasets and 6 out of 10 in the CHASE-DB dataset. For the CHASE-DB, it also outperformed all the state-of-the-art unsupervised methods.

Super-Resolution (SR) has advanced rapidly in recent years, with diffusion-based models achieving unprecedented fidelity at the cost of introducing new types of visual artifacts. While existing Image Quality Assessment (IQA) methods provide holistic quality scores, they lack interpretability and fail to distinguish between different artifact types arising from modern SR approaches. To address this gap, we introduce SR-Ground, a large-scale dataset specifically designed for fine-grained artifact segmentation in super-resolved images. The dataset comprises images processed by a diverse set of state-of-the-art SR models, with pixel-level annotations for multiple artifact categories. We conduct a large-scale crowdsourcing study involving 1,062 participants to validate and refine automatically generated segmentations, resulting in a high-quality dataset of 63,000 images spanning 6 distinct artifact types. We demonstrate that training IQA models with grounding capabilities on SR-Ground significantly improves performance on downstream tasks. Furthermore, we introduce a fine-tuning pipeline that leverages our grounding model to reduce perceptible artifacts in SR outputs, showcasing the practical utility of our dataset.

Cardiac motion over a cardiac cycle is crucial for quantifying regional function and is strongly affected by cardiovascular diseases. Since temporally dense mesh sequences are difficult to obtain in practice, we focus on leveraging the more accessible end-diastolic frame to infer a full-cycle sequence. Due to strong regional and disease-specific differences, traditional methods often oversmooth the data by relying on generative models that are optimized for global patterns. To address this problem, we propose Region-Aware and Phenotype-Adaptive Bi-Ventricular Cardiac Motion Synthesis (RePCM) for single frame Bi-ventricular mesh motion completion. In Stage I, a reconstruction network learns vertex wise motion descriptors and clustering yields a data driven functional partition, providing an explicit motion derived region structure. In Stage II, a Region-Specific Injection Module enforces masked, synchronized region exchange within a conditional VAE, preserving localized specific dynamics and restricting cross-region mixing. A Phenotype-Adaptive Mixture-of-Experts prior conditioned on ED shape uses anatomy-guided cues to model latent motion trends and capture inter-disease variability. Experiments on three datasets covering different cardiovascular diseases show consistent gains in geometric and functional metrics and improved preservation of region specific dynamics.

The rapid evolution of generative AI, from GANs to modern diffusion models, has resulted in increasingly subtle discriminative clues. These fine-grained signals are often overshadowed by dominant, high-fidelity image content (e.g., the main subject), limiting the reliability of existing detectors that predominantly rely on global representations. To address this challenge, we propose the Peak-Guided Calibration (PGC) framework. PGC introduces a novel strategy that aggregates salient features via a peak-focusing mechanism. Specifically, by employing a peak-sensitive aggregation that accentuates the most discriminative local clues, PGC leverages these critical signals to calibrate the global decision. This approach recovers subtle patterns that would otherwise be submerged in the global context. Furthermore, to better simulate real-world threats, we introduce the CommGen15 dataset, a challenging benchmark comprising samples from 15 commercial models. Extensive experiments demonstrate that PGC achieves state-of-the-art performance. Specifically, it improves mean accuracy by +12.3% on our CommGen15 dataset, and sets new records on standard benchmarks, including GenImage (+2.1%), AIGI (+3.5%), and UniversalFakeDetect (+1.7%). Code is available at https://github.com/xiaoyu6868/PGC.

Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the policy while keeping the VQ decoder frozen. Recent diffusion T2I work, exemplified by REPA-E, has shown that the VAE itself constitutes a key alignment bottleneck, yet no analogous investigation exists for discrete AR models. We show that policy-only optimization induces Latent Covariate Shift: as the policy evolves, the resulting token distribution diverges from the ground-truth distribution on which the decoder was trained, such that reward scores improve while decoded image quality degrades. To address this mismatch, we propose RankE, the first end-to-end post-training framework for discrete T2I generation. Rather than optimizing the policy against a fixed decoder, RankE co-evolves both components through alternating optimization: each module maximizes a ranking-based alignment objective while being regularized by a stability-preserving anchor suited to its parameter space. This co-evolution breaks the fidelity--alignment trade-off that plagues frozen-decoder approaches: on LlamaGen-XL (775M), standard RL improves CLIP but degrades FID, whereas RankE improves both simultaneously (FID 15.21, CLIP 33.76 on MS-COCO 30K). Consistent gains on Janus-Pro (1B) confirm that decoder co-evolution reliably converts reward optimization into pixel-space quality improvements.

Interpretability in object detection provides crucial confidence support for clinical auxiliary diagnosis. However, in tiny bacteria detection, traditional explanation methods often suffer from blurred foreground boundaries and diffuse feature attribution due to the extreme sparsity of target morphological features and severe interference from complex backgrounds. Such limitations hinder the provision of logically coherent morphological evidence. To bridge this gap, we propose a novel eXplainable AI (XAI) framework, SAM-Sode. The framework innovatively transforms initial feature attribution maps into geometry-aware prompts, leveraging the prior knowledge of the foundation model (SAM3) to achieve spatial refinement and morphological reconstruction of the explanatory mappings. Furthermore, we introduce a dual-constraint mechanism based on physical significance and geometric alignment to perform instance-level denoising, generating coherent explanations that better align with human expert intuition. Experimental results on our self-constructed bacteria dataset with complex circuit backgrounds (containing 2,524 images) and other public datasets demonstrate that the proposed method effectively suppresses background redundancy and significantly enhances the decision-making transparency of tiny object detection.

Ternary Vision Transformers offer substantial model compression, however state-of-the-art methods only ternarize the encoder layers, leaving patch embeddings, LayerNorm parameters, and classifier heads in full precision. In compact models targeting resource-constrained processors, such as microcontrollers, these remaining full-precision components determine the total memory footprint, severely limiting deployment efficiency and on-device feasibility. In this work, we introduce a fully ternarized Vision Transformer in which \emph{all} weight matrices and normalization parameters are ternarized (FTerViT). To this end, we introduce two novel operators : TernaryBitConv2d with per-channel scaling for patch embedding and TernaryLayerNorm. FTerViT is trained using knowledge distillation, followed by a lightweight quantization-aware recovery phase. Our ternary W2A8 DeiT-III-S at 384$\times$384 resolution achieves 82.43\% ImageNet-1K top-1 at 6.09\,MB (${\sim}$15$\times$ compression, $-$2.42\,pp vs.\ FP32), outperforming prior ternary ViTs methods up to 8 pp. Finally, we demonstrate the first implementation of ternary vision transformers on a dual cores XTensa LX7 microcontroller inside the ESP32-S3 system-on-chip. By deploying FTerViT-Small (based on DeiT-III-Small at 224$\times$224 resolution, 5.81\,MB), we achieve 79.64\% ImageNet-1K top-1 accuracy.

In modern warfare, drones are becoming an essential part of intelligence gathering and carrying out precise attacks in different kinds of hostile environments. Their ability to operate in real-time and hostile environments from a safe distance makes them invaluable for surveillance and military operations. The KIIT-MiTA dataset is comprised of images of different military scenarios taken from drones, and these provide a foundation for detecting military objects, but it does not take into account the various types of real-world scenarios. With that in mind, to evaluate how the models are performing under varying conditions, four different types of datasets are created: Gray Scale, Thermal Vision, Night Vision, and Obscura Vision. These simulate the real-world environments such as low visibility, heat-based imagery, and nighttime conditions. The YOLOv11-small model is trained and used to detect objects across diverse settings. This research boosts the performance and reliability of drone-based operations by contributing to the development of advanced detection systems in both defensive and offensive missions.

Understanding surgical workflow in real time is fundamental for intelligent surgical embodiment, where AI systems continuously perceive and respond as surgery proceeds. In the operating room, critical decisions depend on subtle, moment-to-moment changes, such as fine instrument movements and evolving tissue states, where even slight perceptual delays can limit assistance or compromise safety. Yet existing methods remain offline or operate at coarse temporal scales, generating descriptions only after processing clips, preventing immediate reaction. We address this by proposing SurgOnAir, a streaming vision-language model that processes frames sequentially without future access and progressively generates narration tokens as visual input arrives. SurgOnAir achieves fine-grained frame-to-token generation, enabling instant responsiveness to evolving surgical dynamics. Built upon our curated hierarchical dataset SurgOnAir-11k spanning action-, step-, and phase-level supervision, the model is trained to produce multi-level textual responses that reflect the inherent hierarchy of surgical procedures. Furthermore, special transition tokens are generated to explicitly mark state changes, allowing SurgOnAir to capture and signal key workflow transitions as they occur. Experiments show that SurgOnAir enables real-time understanding through a single vision-language model that unifies streaming across multiple hierarchies of the surgical workflow, generating superior and hierarchy-aware narrations. Code and dataset will be public.

Recent feed-forward models have significantly advanced geometry perception for inferring dense 3D structure from sensor observations. However, its essential capabilities remain fragmented across multiple incompatible paradigms, including online perception, offline reconstruction, multi-modal integration, long-horizon scalability, and metric-scale estimation. We present UniT, a unified model built upon a novel Group Autoregressive Transformer, which reformulates these seemingly disparate capabilities within a single framework. The key idea is to treat groups of sensor observations as the basic autoregressive units and predict the corresponding point maps in an anchor-free and scale-adaptive manner. More specifically, diverse view configurations in both online and offline settings are naturally unified within a single group autoregression process. By varying the group size, online mode operates over multiple autoregressive steps with single-frame groups, whereas offline mode aggregates a multi-frame group in a single forward pass. Meanwhile, a queue-style KV caching mechanism ensures bounded autoregressive memory over long horizons. This is enabled by reducing long-range dependencies on early frames through anchor-free relational modeling, thereby allowing outdated memory to be discarded on the fly. To improve metric-scale generalization across scenes, a scale-adaptive geometry loss is further introduced within this framework. It couples relative geometric constraints with a partial absolute scale term, implicitly regularizing global scale and inducing a progressive transition from scale-invariant geometry to metric-scale solutions. Together with a dedicated modal attention module for integrating auxiliary modalities, UniT achieves state-of-the-art performance in unified geometry perception, as validated on ten benchmarks spanning seven representative tasks.

Large Multimodal Models (LMMs) have shown promise for video quality assessment, but most methods still predict an absolute score for each video. Such pointwise supervision often mixes perceptual quality with dataset-specific calibration, including annotation protocols, rating habits, and score distributions. As a result, the learned scoring rule may work well within a benchmark but transfer poorly across unseen domains. We argue that relative comparisons alleviate the absolute-scale calibration bias by focusing purely on perceptual differences rather than dataset-specific rating habits. Consequently, we propose \textbf{VersusQ}, a pairwise margin reasoning framework driven entirely by direct comparisons. Specifically, VersusQ performs LMM-based comparison between two videos, reasons about their visual and temporal quality differences, and predicts a signed continuous margin that captures both the preferred choice and the degree of difference. Furthermore, to align interpretable comparison rationales with fine-grained numerical differences, we introduce Margin-Coupled GRPO, which jointly optimizes rollout-based relational reasoning and continuous margin regression. Extensive experiments on multiple public VQA benchmarks demonstrate that VersusQ achieves state-of-the-art performance, strong cross-domain generalization, and reliable fine-grained ranking under heterogeneous evaluation scenarios.

Direct Preference Optimization (DPO) is successful for alignment in LLMs but still faces challenges in text-to-image generation. Existing studies are confined to denoising diffusion models while overlooking flow-matching, and suffer from an objective mismatch when applying discrete NLP-based DPO to regression-based generative tasks.\ In this paper, we derive a generalized DPO objective that covers both diffusion and flow-matching via a unified reverse-time SDE framework, and point out from a gradient perspective that the standard DPO objective is suboptimal for text-to-image generation. Consequently, we propose Linear-DPO, which replaces the aggressive sigmoid-based utility function with a sustained linear utility and incorporates an EMA-updated reference model. Qualitative and quantitative experiments on diffusion models (SD1.5, SDXL) and flow-matching model (SD3-Medium) demonstrate the superiority of our approach over existing baselines.

Single-image-to-3D generative models can now produce high-quality geometry, yet conditioning on a single view inevitably introduces ambiguity about unseen regions. Multi-view conditioning can reduce this ambiguity, but existing methods either require fixed canonical viewpoints or rely on external reconstruction modules that impose heavy training costs and limit generation quality. We observe that pretrained single-view models already possess strong 2D-to-3D grounding that can be reused for multi-view conditioning. However, a closer analysis reveals that their conditioning mechanism entangles orientation control with geometry transfer, two functions that conflict when images from different viewpoints are naively combined. Based on this analysis, we propose ROAR-3D, a lightweight method that upgrades a pretrained single-view model to accept an arbitrary number of unposed images. A token-wise view router assigns each 3D latent token to its most relevant view, implicitly establishing 2D-to-3D correspondences without explicit pose input. A dual-stream attention design preserves the pretrained primary-view behavior while routing auxiliary views through a separate path dedicated to geometric enrichment. An orientation perturbation strategy ensures the auxiliary path learns orientation-independent geometry transfer. These components introduce minimal trainable parameters and add negligible inference overhead relative to the single-view baseline. ROAR-3D achieves state-of-the-art multi-view 3D generation quality and supports test-time view scaling from 1 to 12+ views with consistent improvements.

4D automotive radar is indispensable for autonomous driving due to its low cost and robustness, yet its point cloud sparsity challenges 3D object detection. Existing 4D radar-camera fusion methods focus on complex fusion strategies, trading inference speed for marginal gains. This trade-off hinders real-time deployment due to heavy computation on dense feature maps. In contrast, feature extraction from sparse radar points is less time-consuming but remains under-explored. This work uncovers that simply enhancing radar feature extraction can achieve comparable or even higher performance than elaborate fusion modules, while maintaining real-time performance. Based on this finding, we propose RCGDet3D, which centers on radar feature encoding and simplifies multi-modal fusion. Its encoder inherits from the efficient Gaussian Splatting-based Point Gaussian Encoder (PGE) in RadarGaussianDet3D with two key improvements. First, the Ray-centric PGE (R-PGE) predicts Gaussian attributes in ray-aligned coordinate systems before unifying them to Bird's-Eye View (BEV) space, significantly improving geometric consistency and reducing learning difficulty by decoupling the coordinate transformation from representation learning. Second, a Semantic Injection (SI) module incorporates visual cues from images, producing more geometrically accurate and semantically enriched radar features. Experiments on View-of-Delft (VoD) and TJ4DRadSet show that RCGDet3D outperforms state-of-the-art methods in both accuracy and speed, setting a new benchmark for real-time deployment.

Accurate estimation of the Angle of Progression (AoP) from intrapartum transperineal ultrasound is critical for objective assessment of labor progression, yet remains highly sensitive to imaging noise, boundary ambiguities, and the geometric amplification of local segmentation errors. We propose R2AoP, a reliable and robust AoP estimation framework that integrates structurally informed segmentation and confidence-guided geometric modeling to achieve stable and reproducible measurements. A three-branch local-structure-enhanced backbone improves the delineation of the pubic symphysis (PS) and fetal head (FH), while confidence-weighted contour fitting explicitly suppresses the influence of unreliable boundary points in AoP computation. To further improve performance under heterogeneous acquisition conditions, we introduce a lightweight geometry-reliable test-time adaptation strategy as an auxiliary component, enabling stable inference without target annotations. Extensive evaluations on multi-center benchmarks demonstrate consistent reductions in AoP error and boundary metrics compared with state-of-the-art AoP methods. Our source code is available at https://github.com/baiyou1234/R2AoP.

Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editing remains challenging, as it requires models to precisely modify textual content while preserving visual realism and non-target regions. Current open-source models still lag behind proprietary systems, largely due to the scarcity of high-quality training data and the lack of standardized benchmarks tailored to text editing. To address these challenges, we present TextSculptor, a comprehensive framework for data construction and evaluation of scene text editing. We first develop an automated data construction pipeline that combines text-aware image synthesis with programmatic text rendering and compositing. Based on this pipeline, we build TextSculpt-Data, a large-scale dataset containing 3.2M training samples, including 1.2M OCR-verified text-to-image samples and 2M paired text editing samples with naturally aligned source-target images and strong background consistency. We further introduce TextSculpt-Bench, a benchmark covering four fundamental text editing tasks: text addition, text replacement, text removal, and hybrid editing. To support reliable evaluation, we design a tailored protocol that measures text accuracy, visual quality, and background preservation through OCR-based text alignment, multimodal judgment, and background-region similarity. Extensive experiments show that TextSculptor improves open-source text editing performance and narrows the gap to proprietary models. The data and benchmark are available at https://github.com/linyiheng123/TextSculptor.

Earth observation (EO) foundation models (FMs) are increasingly trained on multisensor data, spanning multispectral imagery (MSI), synthetic aperture radar (SAR), and derived geospatial layers, but hyperspectral imagery (HSI) remains underrepresented. Conversely, existing hyperspectral FMs are trained on HSI alone, leaving joint pretraining and fusion of HSI with co-located EO sensors unexplored. We introduce SpectralEarth-FM, a hierarchical transformer for multisensor EO input with heterogeneous spectral dimensionality. The architecture combines spectral tokenization for hyperspectral inputs, sensor-specific encoders, a cross-sensor fusion module, and a shared hierarchical encoder, enabling joint processing of HSI and lower-channel observations. To pretrain SpectralEarth-FM, we curate SpectralEarth-MM, a dataset that co-locates HSI from three spaceborne sensors (EnMAP, EMIT, DESIS) with Sentinel-2, Landsat-8/9 optical imagery, Landsat land surface temperature (LST), and Sentinel-1 SAR, over common geographic footprints. It comprises approximately 2M globally distributed locations, 25M georeferenced patches, and over 40TB of data. Pretraining uses a Joint-Embedding Predictive Architecture (JEPA)-style objective that matches representations between global views and single-sensor local views from the same location. We evaluate SpectralEarth-FM on hyperspectral downstream tasks and standard EO benchmarks following the PANGAEA protocol, achieving state-of-the-art results across both evaluation settings.

Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming video generation, paving the way for real-time interactive video generation and world modeling. Despite their potential, the substantial inference cost of ARVDs remains a major obstacle to practical deployment, making model quantization a natural direction for improving efficiency. However, quantization for ARVDs remains largely unexplored. Our empirical analysis shows that directly applying existing quantization schemes developed for standard diffusion transformers to ARVDs leads to suboptimal performance, revealing quantization behaviors that differ from those observed in bidirectional diffusion models. In this paper, we identify two critical challenges in quantizing ARVDs: (C1) Highly unbalanced frame-wise quantization sensitivity. Error accumulation during autoregressive generation can induce severely skewed quantization sensitivity across frames, following an exponential-like decay pattern. (C2) Prominent and heterogeneous outlier patterns in weights. Weight distributions exhibit pronounced outlier channels, whose patterns vary substantially across layer types and block depths. To address these issues, we propose Q-ARVD, a novel framework for accurate ARVD quantization. (S1) To tackle the highly unbalanced frame-wise sensitivity, Q-ARVD incorporates a final-quality aware frame-weighting mechanism into the quantization objective. (S2) To prevent heterogeneous outliers from degrading performance, Q-ARVD introduces an outlier-aware adaptive dual-scale quantization, which automatically detects the presence and quantity of outlier channels for an arbitrary layer, and isolates them to protect normal channels. Extensive experiments demonstrate the superiority of Q-ARVD.

Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task formulation. We show that trajectory recovery, when viewed through the lens of inverse kinematics, requires both a current and a future visual state as boundary conditions; existing VLAs supply only the former, which encourages the model to shortcut through ego status and text commands alone. To address this, we re-design Driving VLA in the style of an inverse kinematics solver. First, a next visual state prediction objective that requires the LLM to predict the future visual scene provides dense visual supervision and suppresses shortcut paths. Second, a separate Inverse Kinematics Network (a cross-attention-based conditional diffusion model) that takes only the current and future visual states as input is designed to suppress reliance on ego status and textual shortcuts during trajectory decoding. With this simple prescription alone, our 0.5B-scale model recovers visual grounding and reaches trajectory planning performance comparable to 7B--8B VLAs more than an order of magnitude larger, on both the closed-loop NAVSIM-v2 and the nuScenes benchmarks. Extensive analysis further shows that this improvement stems from a recovered ability to exploit visual features, with the effect being most pronounced in dynamic driving situations such as turning.

Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human effort to construct multi-way aligned datasets and thereby limiting scalability across domains. In this work, we explore training MLLMs by only leveraging multiple paired modalities as a surrogate for the full joint multimodal distribution. Specifically, we first provide a theoretical analysis of the conditions under which the representations are identifiable with only observing pairwise modalities. Building on this analysis, we propose a representation learning framework for aligning latent representations across modalities using only pairwise data. The framework consists of two stages: latent representation alignment and cross-modal recomposition. Specifically, in the first stage, we learn the shared latent space across modalities by both self-modal reconstruction and pair-wise contrastive learning. We also incorporate an inductive bias in the contrastive learning process by partially aligning and minimal latent specification. In stage two, we integrate the encoder of newly introduced modalities with the decoders of the pre-trained modalities to facilitate cross-modal transfer and generation. We evaluate our method by newly adding 3D point clouds and tactile modalities into pre-trained MLLMs with three modality pairs and show that, by learning an aligned latent representation space, our model achieves strong cross-modal performance.

Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive resolution sampling has emerged as a promising acceleration approach by reducing latent resolution in early stages. However, scaling this idea to video generation remains challenging, as the additional temporal dimension introduces diverse spatio-temporal demands across different videos, and compressing only a single dimension often leads to limited acceleration or degraded quality. Therefore, we propose DVG, a Dynamic Video Generation framework that jointly allocates computation across time and space, automatically selecting content-aware acceleration strategies without manual tuning or retraining. DVG achieves near-lossless acceleration across models and tasks, reaching up to 7 times speedup on HunyuanVideo and HunyuanVideo-1.5, and 18 times when combined with distillation, demonstrating its potential as a key component in today's large-scale efficient video generation systems. Our code is in supplementary material and will be released on Github.

High-fidelity street scene reconstruction is pivotal for end-to-end autonomous driving simulation, where novel-view synthesis (NVS) and time-varying information modeling are two fundamental capabilities to facilitate closed-loop training. However, existing 3DGS methods and their 4D extensions fail to simultaneously achieve both. To bridge this gap, we establish an information-geometric diagnostic framework, revealing that this limitation stems from a credit assignment dilemma between spatial and temporal parameters. Specifically, the deterministic coupling between viewpoint and time in single-source observation creates a low-rank structure that induces massive null-space ambiguity between static view-dependent and dynamic time-varying components. Temporal information overshadows spatial cues, causing the estimation variance of spatial parameters to diverge. To address this issue, we propose Orthogonal Projected Gradient (OPG), a hierarchical training method designed to restore spatial identifiability. OPG prioritizes the integrity of spatial representations by securing them in an initial stage, then restricts temporal updates to the spatial null space, enabling proactive credit assignment. While OPG isolates temporal updates algebraically, Temporal Regularization Strategy is proposed to further refine the temporal solution space by imposing a smoothness constraint based on the physical prior of consistent appearance evolution, ensuring that the reconstructed scene remains physically consistent in closed-loop simulation. Extensive experiments demonstrate that our method not only maintains stable NVS capabilities but also demonstrates superior performance in traditional observation-reproducing metrics, which indirectly reflect the capability of modeling temporal dynamics.

Generative artificial intelligence now synthesizes photorealistic imagery, audio, and video at a cost that defeats traditional forensic intuition. The legal consequences span three regimes studied so far in isolation: international operational law, domestic procedure, and product regulation. This article presents a unified evidentiary framework that maps cryptographic content provenance, robust statistical watermarking, and zero knowledge attestation to the proof requirements of each regime. We define a five tier threat model spanning naive regeneration, adversarial laundering, cross model regeneration, active watermark removal, and insider provenance forgery. We release a public benchmark of 12000 generated items across image, audio, and video modalities under six laundering pipelines for 72000 evaluation samples. We evaluate four representative schemes and report true positive rate at fixed false positive rate, robustness area under the curve, computational overhead, and a regime conditioned legal sufficiency score. We translate empirical detection bounds into legal sufficiency thresholds for command decisions under the law of armed conflict, for criminal and civil admissibility under domestic procedure, and for persistence audits under the European Union Artificial Intelligence Act and analogous regimes. The result is a reproducible reference pipeline, a public benchmark, and model annexes that lawyers, engineers, and operators can deploy together.

Existing 3D clothed avatar reconstruction methods achieve high visual fidelity but ignore geometric structure and physical plausibility. They either model clothed humans as a single deformable surface or attempt garment disentanglement without enforcing geometric constraints, resulting in ambiguous garment boundaries and no control over stacking or layer ordering. To address these limitations, we introduce DAMA (Disentangled body-Anchored Gaussians for Controllable Multi-layered Avatars), a 3D avatar reconstruction method that produces physically plausible clothed avatars through a dedicated representation and reconstruction method. At the representation level, we bind Gaussians to SMPL-X faces using barycentric in-plane coordinates and a positive normal offset. Based on this parameterization, the reconstruction method lifts 2D segmentations to body-anchored Gaussians, refines layers using topology-guided correction, and jointly optimizes geometry and appearance. DAMA is the first Gaussian avatar reconstruction method from multi-view images to achieve physically plausible layering, clean garment separation, and explicit stacking control. On the full 4D-DRESS dataset (82 scans), it achieves state-of-the-art performance in geometry reconstruction, garment separation, penetration rate, and penetration depth. The representation further supports user-defined garment reordering and fast conversion of body-conforming garments to simulation-ready meshes. Project Page: https://danieleskandar.github.io/dama/

Integrating machine learning (ML) with physical models (PM) has emerged as a promising way of retrieving geophysical parameters from remote sensing data. In this context, a ML model for estimating forest height from TanDEM-X interferometric coherence measurements has recently been proposed, that constrains the learning process through a PM. While the features used for training and inversion where selected to ensure the physical consistency of the solutions, they could not resolve all height / structure and baseline / terrain slope ambiguities in the data. To improve this, the extension of the feature space with optical Landsat data is proposed able to provide complementary information on forest type or structure. The extended model is applied and validated on several TanDEM-X acquisitions over the Gabonese Lopé national park site and assessed against airborne LiDAR measurements. Results show a 13.5% reduction in RMSE and a 16.6% reduction in MAE compared to the original hybrid model, confirming the added value of multispectral inputs.

The effectiveness of rock support in underground mines depends on the interaction between installed rock bolts and the structural fabric of the surrounding rock mass. However, discontinuity characterisation and rock bolt identification are commonly treated as separate tasks, limiting their value for integrated support assessment. This study presents an automated framework for integrated rock support visualisation using 3D point clouds of underground mine excavations. The framework integrates structure mapping, rock bolt identification, discontinuity plane fitting, and bolt orientation estimation into a unified workflow optimised for accuracy and computational efficiency. The outputs are used to generate an integrated 3D visualisation of fitted discontinuity planes and bolt vectors, enabling direct assessment of their spatial intersections and geometric relationships. A complementary stereographic analysis of discontinuity poles and bolt orientations is also performed to evaluate overall bolting geometric effectiveness relative to the mapped structural fabric. Additionally, bolt-level quality metrics, including exposed protrusion length and deviation from the local roof normal, are visualised to support assessment of installation quality. The proposed framework is demonstrated on real underground metal mine scans, producing accurate structure mapping and rock bolt identification results in medium-scale point clouds. Overall, the study provides a practical step towards automated, integrated geotechnical assessment of rock support effectiveness without requiring manual measurements or additional in-situ data acquisition.

The growing sophistication of GAN-based image manipulation presents significant challenges for digital forensics. This study compares the performance of four pretrained CNN architectures including VGG16, ResNet50, EfficientNetB0, and XceptionNet for fake image detection using a unified preprocessing and training pipeline. A dataset of real and manipulated images was processed through resizing, normalization, and augmentation to address class imbalance and improve generalization. Models were evaluated using Accuracy, Precision, Recall, F1-score, and ROC-AUC. VGG16 achieved the highest accuracy at 91%, with XceptionNet, ResNet50, and EfficientNetB0 each reaching 90%. EfficientNetB0 showed stronger sensitivity to fake images but reduced reliability on real samples, reflecting imbalance-driven bias. Limitations include dataset imbalance, overfitting, and limited interpretability, which affect cross-domain robustness. The study provides a reproducible baseline and underscores the need for balanced datasets, advanced augmentation, and fairness-aware training to develop reliable fake image detection systems.

Large Vision-Language Models (LVLMs) have shown remarkable performance on a wide range of vision-language tasks. Despite this progress, they are still prone to hallucination, generating responses that are inconsistent with visual content. In this work, we find that LVLMs tend to hallucinate when they pay insufficient attention to the correct visual evidence and gradually forget it during the generation process. We empirically find that although LVLMs overall attend insufficiently to visual evidence, they exhibit sensitivity to the correct visual evidence in specific layers, with notable inter-layer discrepancy. Motivated by this observation, we propose a novel hallucination mitigation method that enhances visual evidence based on Inter-Layer Visual Attention Discrepancy (ILVAD). Specifically, we obtain the attention weights from early generated tokens to visual tokens across layers and identify the tokens that are repeatedly activated as visual evidence, forming a saliency map. We then enhance attention to visual evidence during generation through the saliency map to reduce visual forgetting. In addition, we leverage the saliency map to obtain attention scores of generated text to visual evidence, in order to select and emphasize text tokens that are strongly grounded in visual evidence. Our method is training-free and plug-and-play. Multiple benchmark evaluations conducted on five recently released models show that our method can consistently mitigate hallucinations in different LVLMs over various architectures. Code is available at https://github.com/ytx-ML/ILVAD.

The proliferation of unmanned aerial vehicles (UAVs) has created urgent demand for precise UAV monitoring. Existing RGB-based systems rely on spatial cues that degrade at small scales, particularly with high inter-type similarity, target-clutter ambiguity, and low contrast. Multispectral imaging (MSI) encodes material-aware spectral signatures, yet MSI-based fine-grained small-UAV detection remains underexplored due to lack of dedicated datasets. We introduce UAVNet-MS, the first multispectral dataset for fine-grained small-UAV detection, comprising 15,618 temporally synchronized RGB-MSI data cubes (1440x1080) with bounding box annotations. The dataset features challenging small objects (93.7% <= 32^2 pixels, average 18^2 pixels, ~0.02% image area) under low contrast. We propose MFDNet, a dual-stream baseline addressing array-induced parallax and spatial-spectral fusion. Extensive evaluation under RGB-only, MSI-only, and RGB+MSI protocols against 20 detectors shows MFDNet achieves +6.2% AP50 improvement over best RGB-only methods, demonstrating spectral cues provide complementary material evidence beyond spatial cues. This work provides foundational dataset, strong baseline, and benchmark for multispectral UAV monitoring research.

Existing 4D-driven video diffusion models primarily target plausible generation, but faithful 4D editing requires preserving source-observed regions while synthesizing disoccluded or out-of-view content. We identify Evidence-Role Mismatch: reliable source-backed evidence, unreliable rendered cues, and unsupported regions are entangled in a single conditioning signal, causing preservation drift, ghosting, and unstable extrapolation. We propose PREX (Preserve, Reveal, Expand), a region-aware framework that decomposes the target spatiotemporal volume into Preserve, Reveal, and Expand roles according to observation support and scene extent. PREX builds observation-backed appearance cues with calibrated confidence and injects them into a frozen video diffusion backbone through a region-aware adapter, trained with proxy tasks without requiring paired edited videos. We further introduce PREBench, a diagnostic benchmark with curated edits, region-role masks, and human-aligned metrics that complement global video-quality and 4D-control evaluations. Experiments show that PREX reduces region-structured failures while maintaining strong visual quality and 4D edit control capability. Project Page: https://ricepastem.github.io/PREX-Open

Text-to-motion generation, which translates textual descriptions into human motions, faces the challenge that users often struggle to precisely convey their intended motions through text alone. To address this issue, this paper introduces DrawMotion, an efficient diffusion-based framework designed for multi-condition scenarios. DrawMotion generates motions based on both a conventional text condition and a novel hand-drawing condition, which provide semantic and spatial control over the generated motions, respectively. Specifically, we tackle the fine-grained motion generation task from three perspectives: 1) freehand drawing condition. To accurately capture users' intended motions without requiring tedious textual input, we develop an algorithm to automatically generate hand-drawn stickman sketches across different dataset formats; 2) multi-condition fusion. We propose a Multi-Condition Module (MCM) that is integrated into the diffusion process, enabling the model to exploit all possible condition combinations while reducing computational complexity compared to conventional approaches; and 3) training-free guidance. Notably, the MCM in DrawMotion ensures that its intermediate features lie in a continuous space, allowing classifier-guidance gradients to update the features and thereby aligning the generated motions with user intentions while preserving fidelity. Quantitative experiments and user studies demonstrate that the freehand drawing approach reduces user time by approximately 46.7% when generating motions aligned with their imagination. The code, demos, and relevant data are publicly available at https://github.com/InvertedForest/DrawMotion.

Structured road understanding of lane geometry, topology, and traffic element relationships is foundational to safe autonomous driving. While vision-language models (VLMs) offer promising semantic flexibility, they lack the geometric and relational grounding required for precise road reasoning. Conversely, traditional modular systems, e.g., HD maps and topological road graphs, provide structural precision but remain semantically rigid. To bridge this gap, we introduce the Combined Road Substrate (CRS), a graph-grounded framework that makes geometric road structure and open-vocabulary semantics jointly executable in a single representation. CRS enables the automatic generation of compositionally complex and linguistically varied question-answer pairs via recursive graph queries, augmented with a "grounding for free" mechanism that ensures logical traceability to specific map elements, and procedurally extracted chain-of-thought supervision traces. We demonstrate that state-of-the-art VLMs - including large, closed-source models - struggle significantly with structured road reasoning, yet training a small 2- or 4-billion-parameter model with as few as 20 to 80 CRS-enriched scenes yields stable gains in compositional reasoning tasks of varying depth. Analysis of model behavior via verifiable reasoning traces reveals a systematic shift in failure modes: whereas baseline models fail at relational scene understanding, CRS-trained models reduce failures to attribute recognition, suggesting that the primary bottleneck in road understanding is not model scale, but the absence of structured supervision.

We present PaintCopilot, a co-creative neural painting assistant that models painting as an open-ended autoregressive artistic behavior conditioned on evolving canvas states and prior brushstroke history, without requiring a target image. Unlike existing neural painting methods that frame painting as pixel reconstruction toward a predefined reference, PaintCopilot predicts future strokes directly from learned artistic dynamics, analogous to how large language models continue text sequences from prior context. The framework proposes three complementary models: a ViT-based Target Predictor that infers artist intent from partial canvas observations, an autoregressive Next Stroke Predictor that generates temporally coherent brushstrokes via flow matching, and a VAE-based Region Sampler that synthesizes semantically localized stroke sequences on demand. Built on three differentiable brush representations (Hard Round, Brush Tip, and 2D Gaussian), the system supports four interactive workflows: Optimize History, Stroke Completion, Region Inpainting, and Dynamic Brush. Through case studies with professional artists, we demonstrate that PaintCopilot enables fluid co-creative painting workflows in which artists and AI continuously alternate control throughout the creative process.

Accurate estimation of wheat spike volume is important for yield component analysis and stress resilience assessment, yet field-based measurement remains challenging. Active 3D sensing methods such as Light Detection and Ranging (LiDAR) or time-of-flight (ToF) are sensitive to plant motion or poorly suited to outdoor conditions, while 3D reconstructions are computationally expensive. Direct 2D image processing would offer computational advantages, but image-based models lack explicit geometric information. We therefore propose a hybrid 2D-3D approach with knowledge distillation during training while enabling efficient image-only inference. First, we train a rigid-invariant point cloud network using distance-based histogram features to obtain pose-robust geometric representations. We then combine the 3D model with a proposed multi-view image-based regulated Transformer (RT) in an ensemble architecture. Finally, we distill the ensemble knowledge into a purely image-based student model using either feature-based or label-based distillation. The two distilled RTs reduce the mean absolute error (MAE) from 654.31 mm$^3$ of the non-distilled RT to 639.93 mm$^3$ and 644.62 mm$^3$, and increase correlation from 0.76 to 0.77 and 0.82, respectively. At the same time, inference time is reduced from 160 ms to 1.4 ms per spike. Distillation further mitigates volume-dependent bias and reshapes the latent representation of the image model toward a geometry-aware shape. Our results demonstrate that 3D-informed training of a 2D Transformer allows for scalable and efficient spike volume estimation for high-throughput field phenotyping.

Oscillations and synchronization are widely believed to play a fundamental role in representation and computation. However, existing machine learning approaches based on synchronization dynamics have largely been confined to specialized settings such as object discovery, with limited evidence of scalability to standard vision benchmarks or logic reasoning tasks. We propose the Winfree Oscillatory Neural Network (WONN), a dynamical neural architecture based on generalized Winfree dynamics. WONN evolves representations on the torus $(S^1)^d$ through structured oscillatory interactions, combining phase-based inductive biases with flexible and hierarchical interaction mechanisms instantiated as either fixed trigonometric mappings or learnable neural networks. We evaluate WONN on image recognition and complex reasoning tasks, including CIFAR, ImageNet, Maze-hard, and Sudoku. Across these domains, WONN achieves competitive or superior performance with strong parameter efficiency. In particular, WONN is, to our knowledge, the first synchronization-based oscillatory architecture to scale competitively to ImageNet-1K. Furthermore, on Maze-hard, WONN achieves 80.1% accuracy using only 1% of the parameters of prior state-of-the-art models. These results suggest that structured oscillatory dynamics provide a scalable and parameter-efficient alternative to conventional neural architectures.

Extending the generation horizon of video diffusion models to long sequences remains a long-standing and important challenge. Existing training-free approaches fall into two categories: extensions of bidirectional models, which are tightly coupled to specific architectures and suffer from quality degradation over long horizons, and autoregressive models, which accumulate drift errors due to exposure bias and tend to produce repetitive motion patterns. To address these issues, we propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training. Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via \emph{Tweedie matching} to enforce both \textbf{manifold constraint and temporal consistency} across overlap regions. \emph{Stochastic early-phase sampling} then synchronizes per-window trajectories by injecting fresh noise after each Tweedie matching correction in the high-noise phase, before transitioning to deterministic ODE sampling to preserve fine-grained visual fidelity. Applied to various video generation models, our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any fine-tuning.

Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task performance but little transparency. Prior work has explored hybrid formulations that integrate concepts and additional representations to improve accuracy, often at the cost of human interventions. We introduce the \emph{Synergy Concept-Based Model (SynCB)} framework, that combines a CB branch with a complementary neural branch, and a trainable routing module that dynamically selects which branch to use for each input. Unlike prior models, which fuse residual and concept-based predictions, SynCB keeps the two branches distinct and coordinates them through the routing module. Moreover, both branches are learned jointly, allowing information sharing between the complementary neural branch and CB branches through their common backbone. To improve responsiveness to interventions, we further introduce a test-time intervention policy and a corresponding loss. Across five datasets and CB benchmarks, SynCB consistently achieves higher task accuracy while remaining more responsive to human interventions, surpassing the full neural baseline by up to 3.9 percentage points and exceeding the strongest competitor in intervention performance by up to 6.43 percentage points.

We propose JFAA, a JEPA-based Future Action Anticipation method for the EPIC-KITCHENS-100 (EK-100) Action Anticipation task. Inspired by the representation learning and future prediction ability of V-JEPA 2.1, JFAA uses a frozen encoder and predictor to extract observed context features and near-future latent tokens. A lightweight attentive probe is then trained to predict verb, noun, and action logits with separate task queries. To improve robustness, we further build a field-aware ensemble over selected epoch-level predictions, allowing each output field to benefit from its most reliable candidates. Experimental results on the official challenge server show that JFAA achieves first place in the EgoVis 2026 EK-100 Action Anticipation Challenge. Our code will be released at https://github.com/CorrineQiu/JFAA.

We propose VISTA, a V-JEPA Integrated StillFast Temporal Anticipator for the Ego4D Short-Term Object Interaction Anticipation (STA) Challenge at EgoVis 2026. Given an egocentric video timestamp, the task requires anticipating the next human-object interaction, including the future active object's bounding box, noun category, verb category, time-to-contact, and confidence score. VISTA follows a StillFast-style design that combines object-centric spatial detection with short-horizon temporal context. Specifically, a COCO-pretrained Faster R-CNN ResNet-50 FPN detector generates object proposals from the last observed high-resolution frame, while a frozen V-JEPA 2.1 temporal branch extracts clip-level egocentric context from the observed video. The temporal representation is injected into the detection pathway through feature modulation and ROI-level context fusion. The fused proposal features are then passed to multi-head STA predictors for box refinement, noun classification, verb classification, time-to-contact regression, and interaction confidence estimation. For the final submission, we further ensemble complementary predictions to improve robustness. Experimental results on the official challenge server show that VISTA achieves first place in the EgoVis 2026 Ego4D STA Challenge. Our code will be released at https://github.com/CorrineQiu/VISTA.

Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-quality datasets and the high visual similarity between classes. To address these challenges, we first constructed a comprehensive dataset comprising 306 fruit categories with 116,233 samples. Moreover, we propose FruitEnsemble, a practical two-stage dynamic inference framework designed to overcome the generalization limitations of static single-model architectures. In the first stage, FruitEnsemble employs a validation-calibrated weighted ensemble of heterogeneous backbones to generate a robust Top-3 candidate pool. To tackle difficult samples, we introduce an expert arbitration mechanism: when ensemble confidence falls below 0.6, a multimodal large language model (MLLM) is triggered to perform rigorous visual verification by integrating external botanical descriptions using Chain-of-Thought (CoT) reasoning. Furthermore, we optimized the training pipeline with a hard sample-aware joint loss. Extensive experiments demonstrate that FruitEnsemble achieves a classification accuracy of 70.49\% and outperforms existing state-of-the-art models. Our framework provides an efficient, deployment-oriented solution for real-world agricultural visual sorting and quality inspection tasks.

Multimodal survival prediction, a crucial yet challenging task, demands the integration of multimodal medical data (\eg Whole Slide Images (WSIs) and Genomic Profiles) to achieve accurate prognostic modeling. Given the inherent heterogeneity across modalities, the feature decoupling-fusion paradigm has emerged as a dominant approach. However, these methods have the following shortcomings: (1) fail to reduce the redundant information of modality features before decoupling, which negatively affects the feature decoupling and fusion effect;(2) lack the ability to model the fine-grained relationships of the features and capture the local information interactions between intra- and inter-modality features. To address these issues, we propose a \underline{H}ierarchical \underline{D}ecoupling-Fusion \underline{M}ixture-\underline{o}f-\underline{E}xperts (HDMoE) framework with two levels of MoE and \underline{R}andom \underline{F}eature \underline{R}eorganization (RFR) modules.In the first-level MoE, shared experts and routed experts are employed to remove redundant information and extract fine-grained specific features within each modality, while the second-level MoE facilitates fine-grained inter-modality feature decoupling. Besides, we design two RFR modules following each level of MoE to finely fuse intra- and inter-modality features, which can help the model capture more fine-grained relationships between modalities. Extensive experimental results on our private Liver Cancer (LC) and three TCGA public datasets confirm the effectiveness of our proposed method. Codes are available at https://github.com/ZJUMAI/HDMoE.

Monocular egocentric human pose estimation is essential for ubiquitous activity monitoring. However, understanding the user's absolute location within the environment remains a challenge. Existing methods primarily focus on relative motion from an initial position, and tend not to account for the wearer's absolute location within an environment. Furthermore, inherent scale ambiguity in monocular vision leads to severe translational drift, limiting long-term tracking without specialized multi-sensor hardware. To address this, we propose MapMonoEgo, a novel framework achieving globally consistent human pose estimation solely from a monocular camera by leveraging a pre-scanned 3D point cloud. We also introduce AIST-Living dataset, a new dataset pairing egocentric video with ground-truth motion in a scanned environment. Experiments demonstrate that our approach significantly outperforms the state-of-the-art baseline, proving its utility for practical monitoring tasks without specialized hardware.

Multimodal sarcasm detection requires reasoning over cross-modal incongruities between literal expression and intended meaning, yet the specific analytical perspectives needed vary across samples due to the diversity of sarcastic mechanisms. While recent methods make this analytical process explicit, they still rely on fixed, predefined perspectives that operate independently under hand-crafted routing rules. We argue that multimodal sarcasm detection instead calls for self-elicited multi-perspective reasoning, where a model autonomously generates the perspectives needed for each sample and progressively integrates them into a coherent analysis. To realize this goal, we propose ProCrit, a Proposal-Critic two-agent framework with a proposal agent for multi-perspective reasoning and a critic agent for external evaluation and targeted revision guidance. First, to overcome the lack of process-level supervision in existing sarcasm datasets, ProCrit synthesizes process-level reasoning annotations through a dynamic-role agentic rollout: a strong vision-language model sequentially spawns analytical roles within a shared context, and the resulting multi-role trajectories are flattened into sequences that preserve cross-perspective dependencies while enabling efficient autoregressive generation. Second, to improve reasoning reliability, ProCrit adopts a draft-critique-revise paradigm in which an independent critic identifies reasoning deficiencies and provides targeted natural-language feedback for directed revision. Finally, we develop a mutual-refinement training framework that jointly optimizes proposal drafting and feedback-guided revision via dual-stage reinforcement learning, while refining the critic agent according to the actual effectiveness of its feedback. Experiments on three widely used benchmarks demonstrate the effectiveness of ProCrit.

Modern vision backbones treat pointwise activations (e.g., ReLU, GELU) and exponential softmax as essential sources of nonlinearity, but we demonstrate they are not required within MetaFormer-style vision backbones. We design activation-free polynomial alternatives for three core primitives (MLPs, convolutions, and attention), where Hadamard products replace standard nonlinearities to yield polynomial functions of the input. These modules integrate seamlessly into existing architectures: instantiated within MetaFormer, a modular framework for vision backbones, our PolyNeXt models match or exceed activation-based counterparts across model scales on ImageNet classification, ADE20K semantic segmentation, and out-of-distribution robustness. We also substantially outperform prior polynomial networks at reduced computational cost, showing that polynomial variants of standard modules beat complex custom architectures.

Several large-scale video datasets have been published these years and have advanced the area of video understanding. However, the newly emerged user-generated short-form videos have rarely been studied. This paper presents USV, the User-generated Short-form Video dataset for high-level semantic video understanding. The dataset contains around 224K videos collected from UGC platforms by label queries without extra manual verification and trimming. Although video understanding has achieved plausible improvement these years, most works focus on instance-level recognition, which is not sufficient for learning the representation of the high-level semantic information of videos. Therefore, we further establish two tasks: topic recognition and video-text retrieval on USV. We propose two unified and effective baseline methods Multi-Modality Fusion Network (MMF-Net) and Video-Text Contrastive Learning (VTCL), to tackle the topic recognition task and video-text retrieval respectively, and carry out comprehensive benchmarks to facilitate future research. Our project page is https://usvdataset.github.io.

Architectural spatial intelligence, the ability to recognize and infer architectural space, is fundamental to tasks such as robot navigation, embodied interaction, and 3D scene understanding and generation. Although extensive research has evaluated the basic spatial skills of Vision-Language Models (VLMs) such as relative orientation, distance comparison, and object counting, these tasks cover only the most elementary levels of spatial cognition and largely overlook higher-level cognition of architectural space, including layout understanding, circulation patterns, and functional zoning. In this work, we present ArchSIBench, a Benchmark for Architectural Spatial Intelligence based on the perspectives from architecture, cognitive science, and psychology. ArchSIBench covers five core dimensions: perception, reasoning, navigation, transformation, and configuration, comprising 17 fine-grained subtasks. Through careful manual annotation by experts with architectural backgrounds, we construct 3,000 question-answer pairs to enable comprehensive evaluation of architectural spatial intelligence. Based on ArchSIBench, we evaluate various VLMs and find that the architectural spatial intelligence of most models shows significant differences from human baselines; additionally, models exhibit substantial variability across capability dimensions. Some state-of-the-art models can approach the level of human evaluators without architectural training. However, a clear gap remains compared to human evaluators with architectural training, particularly in spatial transformation and configuration reasoning. We believe that ArchSIBench will provide important insights and systematic resources for measuring and advancing the architectural spatial intelligence of VLMs. The dataset and code are available at https://huggingface.co/datasets/ArchSIBench/ArchSIBench.

Panoramic radiograph (PR) is fundamentally used in routine dental care, but it inherently provides only a two-dimensional (2D) projection of complex three-dimensional (3D) craniofacial anatomy. Most existing learning-based methods attempt to computationally recover this 3D information by directly regressing native cone-beam computed tomography (CBCT) volumes from PR. However, this direct mapping requires the model to simultaneously learn common anatomical structures and patient-specific morphological variations. This entangled formulation makes the ill-posed 2D-to-3D inverse problem highly ambiguous, often producing over-smoothed reconstructions with blurred anatomical boundaries. To address this, we propose HyDAR-Pano3D, a two-stage framework that reformulates PR-to-CBCT reconstruction as a disentangled anatomical recovery problem. In Stage 1, a dual-encoder network integrates radiographic features with SAM-derived semantic priors to reconstruct an arch-normalized canonical volume. In Stage 2, an Anatomical Restoration Network predicts a prior-constrained structured deformation field to map this canonical volume back to the native space, restoring individual morphological variations. Experiments on three large-scale datasets show that HyDAR-Pano3D significantly outperforms baseline methods ($p < 0.05$), achieving a 25.76 dB PSNR, 85.70\% SSIM, and an 83.83\% overall anatomical Dice score. The synthesized volumes successfully support downstream segmentation of whole teeth (82.4\% Dice) and the inferior alveolar canal (72.2\% Dice), demonstrating that our disentangled approach preserves clinically relevant structures to enable robust anatomy-aware assessment when CBCT data is unavailable.

In this work, we address the challenge of Scene Change Detection (SCD), where the goal is to identify variations between two images of the same location captured at different times. Existing SCD models often overlook the varying importance of features across layers, employ single-step decoders that confine refinement, and provide limited insight into encoder pretraining strategies. We propose TERDNet, a Transformer Encoder-Recurrent Decoder Network designed to overcome these limitations. TERDNet consists of a transformer-based encoder that extracts multi-level representations, a feature fusion module that integrates correlation volumes with these features, a recurrent 3-gate-GRU decoder that performs iterative refinement, and a combined convolution-interpolation upsampler that restores fine-grained resolution. Extensive experiments on four public benchmarks show that TERDNet consistently outperforms prior approaches and produces more accurate and detailed change masks. Ablation studies confirm the benefit of segmentation-based pretraining and the effectiveness of our fusion design. In addition, robustness tests under viewpoint misalignment confirm TERDNet's potential for deployment in real-world robotic systems, where reliable perception is critical. Our code is available at https://github.com/AutoCompSysLab/TERDNet.

Detecting what has changed in an environment is essential for long-term autonomy, yet most change detection settings assume fixed viewpoints, mild misalignment, or only a few changed objects. We introduce Video-based Scene Change Detection (VSCD), which predicts a pixel-wise change mask for each query frame, given a reference and a query RGB video of the same indoor space recorded at different times under unconstrained camera motion. The two videos are not temporally synchronized, and many object instances may appear or disappear. To study this setting, we build a large-scale benchmark with over 1.1 million frames annotated with pixel-accurate change masks, together with a real-world test set for evaluating transfer beyond simulation. We propose a query-centric multi-reference model that learns temporal matching implicitly from change-mask supervision, aligns candidate reference features to the query via local patch correspondence, and fuses per-candidate change features using frame-level and patch-level confidence before decoding a high-resolution mask once per frame. Our approach achieves state-of-the-art performance against strong image- and video-based baselines, and we validate its real-world impact by deploying it on a mobile robot for two downstream applications -- visual surveillance and object incremental learning.

2D Gaussian splatting provides an efficient explicit representation for image reconstruction, but existing methods still require costly per-image iterative optimization or rely on handcrafted priors for primitive allocation. We present AIR, a self-supervised feed-forward framework that amortizes iterative Gaussian fitting into a single network pass, eliminating per-image test-time optimization. AIR adopts a stage-wise residual architecture that progressively predicts additional Gaussian primitives from reconstruction residuals, together with an explicit Stage Control mechanism that activates new primitives only in under-reconstructed regions. A Predict--Optimize--Distill training strategy stabilizes multi-stage prediction by distilling short-horizon optimized Gaussian increments back into the predictor. The stabilized predictor is then jointly finetuned across stages and equipped with an image-adaptive quantizer for compact Gaussian storage. Experiments on Kodak and DIV2K show that AIR achieves better reconstruction quality than representative Gaussian-based baselines while reducing encoding time to 160--300\,ms. Code: https://github.com/whoiszzj/AIR.git

In this report, we present our champion solutions for the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge at CVPR 2026. Both tracks require accurately localizing temporal segments from long untrimmed egocentric videos. To address these tasks, we propose a reranking-based framework that effectively leverages the strong video-language reasoning capability of multimodal large language model (MLLM) while preserving the efficiency and candidate recall of conventional localization pipelines. Specifically, we first obtain a set of candidate segments from existing localization model OSGNet, and then employ MLLM to select the segment that best matches the given query, thereby refining the final prediction. Ultimately, our method achieved first place in both the Natural Language Queries and GoalStep tracks. Our code can be found at https://github.com/iLearn-Lab/CVPR25-OSGNet.

Modern ultra-high-resolution image synthesis relies heavily on the robust generative capacity of large-scale pre-trained Latent Diffusion Models (LDMs). While recent representation alignment methods have proven effective by distilling visual priors from foundation models (e.g., SAM or DINO) into generative latent features, scaling these approaches to pre-trained LDMs at extreme resolutions exposes a critical learnability-fidelity conflict. Specifically, forcing direct patch-wise feature distillation inherently perturbs the pre-trained latent manifold, ultimately leading to generation degradation. To address this bottleneck, we propose Spatial Gram Alignment (SGA), a novel framework that explicitly leverages the representation priors of vision foundation models while preserving the native generative capacity of LDMs. Moving beyond restrictive direct alignment, SGA imposes a non-invasive spatial constraint by aligning the internal self-similarities of the generative features with those of the foundation priors. This spatial constraint effectively establishes macroscopic structural coherence, while the native generative objectives retain the microscopic pixel-level fidelity inherent to the original LDMs. Notably, this versatile strategy integrates seamlessly across both intermediate diffusion features and VAE latents within pre-trained LDMs. Extensive experiments demonstrate that SGA achieves state-of-the-art performance for ultra-high-resolution text-to-image synthesis, yielding an effective reconciliation between global structural integrity and fine-grained visual details. Code is available at https://github.com/zhang0jhon/SGA.

Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under substantial edits. We propose a two-stage framework that decouples structure from appearance by first predicting a Canny map and then rendering the final image conditioned on both the source appearance and the predicted structure. To improve text handling, we further introduce a fully automatic pipeline that constructs a 100k-pair text-aware dataset with cross-view textual consistency. Experiments, including GPT-4.1-based evaluation and a knowledge distillation study, show clear gains over selected baselines and suggest that intermediate structural prediction is an effective route for high-fidelity subject-driven generation. Our dataset and code will be made publicly available.

We present a set of improvements to the OlmoEarth family. These improvements allow us to cut compute costs during training ($1.7 \times$ reduction in GPU hours required to train our Base models) and inference ($2.9\times$ reductions in MACs on Sentinel-2 tasks), while maintaining the models' overall performance. All training code is available at github.com/allenai/olmoearth_pretrain.

Physics-informed diffusion models typically enforce PDE constraints only on final outputs, leaving intermediate representations unconstrained and prone to shortcut learning under shifted boundary conditions. We introduce **REPA-P**, a teacher-free, architecture-agnostic framework that aligns intermediate features with physical states using first-principles residuals. REPA-P attaches lightweight $1{\times}1$ projection heads to selected layers, decodes hidden activations into physical quantities, and applies PDE residual losses during training. These heads are discarded at inference, introducing **zero overhead**. Across four PDE tasks, including Darcy flow, topology optimization, electrostatic potential, and turbulent channel flow, REPA-P accelerates convergence by up to $2{\times}$, reduces physics residuals by up to $66.4\%$, and improves out-of-distribution robustness by up to $49.3\%$, with consistent gains on both U-Net and Diffusion Transformer backbones. Ablations show that supervising a small set of intermediate layers captures most benefits and complements output-level physics losses. Code is available at [https://github.com/Hxxxz0/REPA-P](https://github.com/Hxxxz0/REPA-P).

Visual storytelling with diffusion models has made impressive strides in maintaining character consistency across narrative scenes. However, a critical gap remains: while these methods ensure a character remains consistent across scenes, they provide no systematic method to ensure if fine-grained attributes such as color and textures of clothing, accessories are faithfully rendered in the generated images. Towards this goal, we introduce AttriStory, a benchmark enabling attribute realization in visual storytelling. We curate 200 multi-scene stories across 10 distinct artistic styles using Large Language Model. Each scene is constructed with detailed attribute specifications to enable rich visual narratives. Further, to address attribute realization, we propose a plug-and-play latent optimization module that operates during early denoising steps, when the model establishes structural and semantic content. We achieve this through AttriLoss objective designed to maximize alignment between the cross-attention maps for desired attribute-object pairs while suppressing spurious associations, guiding models to localize attributes correctly. This approach operates orthogonally to existing consistency mechanisms, integrating seamlessly with current story generation pipelines without requiring architectural modifications. Our experiments demonstrate consistent improvements on incorporating AttriLoss across all baselines. This work positions attribute realization as a distinct, complementary dimension of visual storytelling, alongside character consistency, advancing the field toward fine-grained attribute-controlled story generation. Project-page:https://manogna-s.github.io/attristory/

Point supervision has become a scalable solution to address dense annotation for infrared small target detection, but its performance is limited by two coupled bottlenecks: unstable pseudo-label evolution in cluttered, low-contrast infrared imagery and severe sample-distribution imbalance. In this paper, we present a more adaptive and stable framework to address these issues. Leveraging the intrinsic consistency between thermal radiation patterns and heat diffusion, we propose a physics-induced annotation strategy that expands single-point labels into reliable pseudo-masks. To further enhance supervision and alleviate sample imbalance, we develop a bi-level dual-update framework that jointly optimizes detector weights, sample weights, and diffusion parameters. A meta-classifier dynamically predicts sample-wise loss weights, while a differentiable diffusion module refines pseudo-labels with detection feedback, enabling adaptive interaction between training and hyperparameter optimization. Extensive experiments across multiple datasets demonstrate five-fold annotation acceleration, superior detection accuracy, and comparable performance with 30% of the training data, validating the efficiency and practicality of our approach. Our code is available at https://github.com/yuanhang-yao/diffuse-to-detect.

Automated segmentation of the vertebral column in Computed Tomography (CT) scans is a prerequisite for pathological assessment and surgical planning. However, state-of-the-art methods, particularly those based on Transformers or large-scale ensembles, demand substantial GPU resources, creating a barrier for clinical adoption in resource-constrained environments or on edge devices. To address this, we introduce SpineContextResUNet, a computationally efficient 3D Residual U-Net designed for rapid spinal localization. Our architecture integrates a lightweight Context Block that employs parallel multi-dilated convolutions to capture long-range anatomical dependencies without the high latency of Recurrent Neural Networks (RNNs) or the memory overhead of Self-Attention mechanisms. Extensive validation on two public benchmarks, VerSe2020 and CTSpine1K, demonstrates that our model achieves a Dice score of 88.17% and 88.13% respectively. To evaluate performance under strict hardware constraints, we compared our model against a bottlenecked SwinUNETR scaled to match our ~1.7M hardware footprint. While the constrained Transformer suffers severe performance degradation due to a lack of spatial inductive biases in a limited-data regime, our CNN-based approach successfully maintains high accuracy. Crucially, heavy baselines like TotalSegmentator fail due to memory exhaustion on commodity hardware (Intel Core i5, 8GB RAM), our model performs robust inference, making it a viable solution for point-of-care diagnostics and deployment on edge platforms like the Nvidia Jetson Orin Nano.

Inference-time guided sampling steers state-of-the-art diffusion and flow models without fine-tuning by interpreting the generation process as a controllable trajectory. This provides a simple and flexible way to inject external constraints (e.g., cost functions or pre-trained verifiers) for controlled generation. However, existing methods often fail when composing multiple constraints simultaneously, which leads to deviations from the true data manifold. In this work, we identify root causes of this off-manifold drift and find that the approximation error scales severely with gradient misalignment. Building on these findings, we propose Conflict-Aware Additive Guidance ($g^\text{car}$), a lightweight and learnable method, which actively rectifies off-manifold drift by dynamically detecting and resolving gradient conflicts. We validate $g^\text{car}$ across diverse domains, ranging from synthetic datasets and image editing to generative decision-making for planning and control. Our results demonstrate that $g^\text{car}$ effectively rectifies off-manifold drift, surpassing baselines in generation fidelity while using light compute. Code is available at https://github.com/yuxuehui/CAR-guidance.

Vision-language models solve geometry problems with rising accuracy, yet their intermediate states remain latent and unverifiable: a relation expressed in textual reasoning or drawing code carries no guarantee that a constraint-satisfying configuration realizes it. We observe that existing externalization methods based on rendered pixels or one-shot scripts fail to provide exact, per-action geometric guarantees. Enforcing geometric relations by algebraic definition closes this gap: the workspace becomes a constraint-checked evolving canvas. We present Draw2Think, a framework that recasts geometric reasoning from latent spatial inference into agentic interaction with the GeoGebra constraint engine. In a Propose-Draw-Verify loop, Draw2Think externalizes hypotheses onto an executable canvas, measures exact geometric quantities, and feeds structured observations back to the model, so subsequent reasoning proceeds from checked canvas state grounded by the shared workspace. This externalization makes two properties separately auditable: model-level Construction Fidelity (whether the canvas realizes the intended configuration) and engine-level Measurement Faithfulness (exact values and relations from canvas constraints). Across construction, outcome, and rendering evaluations, Draw2Think builds canvases that pass 95.9% predicate-level and 84.0% strict problem-level construction checks on GeoGoal, improves outcome accuracy by up to 4.1%/16.4% on planar/solid benchmarks, and attains 68.2%/90.5% strict/relaxed rendering scores on GenExam-math. Project page is available at https://draw2think.github.io/

Remote sensing imagery typically arrives in the form of continuous data streams. Traditional detectors often forget previously learned categories when learning new ones; therefore, research on Remote Sensing Incremental Object Detection (RS-IOD) is of great significance. However, existing methods largely overlook the intra-class scale variations prevalent in remote sensing scenes, which undermines the effectiveness of knowledge transfer and old knowledge preservation. Moreover, RS-IOD also suffers from missing annotations, which cause the model to misclassify old-class instances as background. To address these challenges, we propose a novel framework, STAR-IOD. First, we introduce a Subspace-decoupled Topology Distillation (STD) module to transfer structural knowledge, explicitly aligning inter-class topological relationships and mitigating intra-class representation discrepancies induced by scale shifts. Furthermore, we introduce the Clustering-driven Pseudo-label Generator (CPG), a plug-and-play module that leverages K-Means clustering to dynamically identify class-specific thresholds, thereby guaranteeing an accurate distinction between true positive targets and background noise and alleviating the issue of missing annotations for old classes. We also constructed two Remote Sensing Incremental Object Detection datasets, DIOR-IOD and DOTA-IOD to facilitate research on RS-IOD. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches by 1.7% and 2.1% mAP on DIOR-IOD and DOTA-IOD, respectively, effectively alleviating catastrophic forgetting while preserving strong detection performance on both base and novel classes. The code and dataset are released at: https://github.com/zyt95579/STAR-IOD.

Existing approaches for unsupervised 3D point cloud segmentation predominantly rely on a purely visual similarity-based learning-by-clustering paradigm, which suffers from a fundamental limitation: long-tail ambiguity. In such a paradigm, features of minor classes are consistently absorbed by dominant clusters, leading to severely imbalanced predictions. To address this issue, we propose LangTail, a language-guided hierarchical learning framework that leverages the balanced world knowledge encoded in language models to mitigate long-tail ambiguity in unsupervised 3D segmentation. The key idea is to establish multi-level associations between language-derived semantic priors and visually underrepresented minor classes, thereby compensating for the biased attention of purely visual clustering toward dominant classes. Specifically, LangTail first constructs an entity-level semantic prior from language models, capturing balanced and fine-grained world knowledge across categories. These priors are injected into a hierarchical clustering framework via contrastive alignment. This guides multi-granularity semantic structure formation and prevents minor classes from being absorbed by dominant clusters, yielding more discriminative representations for underrepresented categories. Extensive experiments on ScanNet-v2, S3DIS, and nuScenes demonstrate that LangTail consistently outperforms existing methods by significant margins, \ie, +13.5, +12.9, and +8.9 mIoU, respectively. These results demonstrate the effectiveness of language priors in improving the representation of minority classes in 3D point clouds. The code will be released at: https://github.com/Whisky0129/langtail_official.

Converting hand-drawn sketches into structured 3D geometries remains challenging due to the difficulty of representing non-Euclidean surfaces and maintaining topological consistency. Existing generative models such as GANs, NeRFs, and diffusion architectures often fail to produce editable manifolds directly usable in downstream design workflows. We present Sketch2MinSurf, a hybrid vision-language and geometric optimization framework that integrates vision-language guidance with minimal-surface theory to generate smooth and editable 3D surfaces from hand-drawn sketches. The core of our approach is a spatial-topological encoding that represents geometry as tuples of node coordinates and real/virtual edge skeletons, enabling stable topological control during generation. We further introduce the Sketch2MinSurf Structural Loss (S2MS-Loss), a reward-modulated objective that jointly constrains geometric reconstruction and topological coherence. On a test set of 100 sketches, Sketch2MinSurf achieves a topological similarity score of 0.844, outperforming existing sketch-to-shape baselines. The generated manifolds are directly editable and free from non-manifold artifacts. A public art installation at a university showcases the method's potential for human-intent-driven 3D form generation. The dataset and code are available at https://anonymous.4open.science/r/Sketch2MinSurf/.

Convolutional Neural Networks (CNNs) often exploit spurious correlations in datasets, learning superficially predictive yet causally irrelevant features, leading to poor generalization and fairness issues. Deep Feature Reweighting (DFR) is a post-hoc technique that reduces a trained model's reliance on spurious correlations by retraining its classification head on a target dataset. However, we show that DFR is fundamentally constrained by operating on entangled features, limiting its ability to amplify the core features while simultaneously suppressing the spurious ones. We trace this entanglement to the ubiquitous Global Average Pooling (GAP) layer, which indiscriminately collapses spatially distinct core and spurious features into a single representation. To address this, we propose Deep Attention Reweighting (DAR), a post-hoc attention-based aggregation module that replaces GAP and is retrained jointly with the classification head. DAR computes an adaptive weighting of spatial locations across feature maps, enabling selective suppression of spurious features before the collapse into entangled features. Across various datasets, metrics, and ablations, DAR consistently outperforms DFR, demonstrating that our attention-based aggregation mitigates GAP-induced entanglement and reduces spurious reliance.

Post-hoc OOD detectors score logits or features after training, so their success depends on the geometry already encoded in the representation. We revisit this assumption through a band-wise MMD^2 analysis across CE, SimCLR, SupCon, and the OOD-oriented representation method PALM. In our diagnostic, low-frequency input bands induce weaker ID/OOD feature discrepancy, whereas higher-frequency bands tend to provide stronger separability. This observation motivates EIHF, an input-side intervention that exposes high-frequency evidence before the first convolution without changing the training objective. EIHF is strongest for geometry-sensitive OOD detection: under matched training and scoring settings, it reshapes class-conditional feature geometry and reduces ID/OOD Mahalanobis score overlap. Experiments on CIFAR-100 and ImageNet-100 show gains on CIFAR-100 and the best average FPR95 with second-best average AUROC on ImageNet-100, while also revealing a limitation on the scene-centric Places shift. Code is available at https://anonymous.4open.science/r/EIHF.

Deep neural networks (DNNs) experience significant performance degradation when processing noisy labels, primarily due to overfitting on mislabeled data. Current mainstream approaches attempt to mitigate this issue by passively filtering clean samples during training. However, simple sample filtering within feature spaces degraded by noise struggles to distinguish between challenging samples and noisy samples, creating a bottleneck for model performance. We highlight for the first time the fundamental importance of actively reshaping feature space geometry for learning from noisy data. We propose a novel Geometry-aware Manifold Regularization Paradigm whose core idea is to explicitly construct energy barriers between data manifolds by actively synthesizing virtual outlier samples. By imposing geometric constraints that promote intra-class compactness and inter-class separation, this approach enhances the discriminability between hard and noisy samples, leading to the learning of more robust representations. Our regularization mechanism exhibits high universality, with effectiveness independent of any prior assumptions about noise patterns. It can be integrated as a standalone mechanism into existing sample selection frameworks, providing stronger robustness against diverse noisy environments. Experiments demonstrate that our paradigm achieves performance surpassing current state-of-the-art (SOTA) methods on multiple benchmarks, including CIFAR-10, with particularly pronounced advantages under more challenging asymmetric noise conditions. Furthermore, this paradigm significantly enhances the model's capability in Out-of-Distribution (OOD) detection, ensuring superior reliability and safety for deployment in open-world scenarios.

Learning with noisy labels in multimedia classification often combines external annotations and model predictions into a single reliability weight, even though the two sources can fail for different reasons. We instead estimate disentangled reliabilities: bilevel meta-learning produces two batch-normalized scalars per sample, alpha for the given label and beta for the pseudo-label, without constraining them to sum to one. Holistic Reliability Propagation (HRP) then routes them to different objectives, using reliability-aware Mixup with global gating on the input branch and beta-gated pseudo-label positives on the contrastive branch. On synthetic and real-world benchmarks, HRP improves average accuracy over strong baselines and remains competitive at the highest noise rates.

This work presents E-ReCON, a 16 Kb energy and resource-efficient digital compute-in-memory (DCIM) macro based on a compact 3T1R ReRAM bitcell for edge-AI inference. The proposed bitcell occupies only 0.85 um^2 and supports reliable AND-based in-memory multiplication for both conventional convolutional neural network (CNN) and spiking neural network (SNN) workloads. To reduce accumulation overhead, a novel interleaved 10T/28T adder tree is introduced, reducing transistor count and power consumption by 37% and 28%, respectively, compared to a conventional 28T RCA-based design. Implemented in 65 nm CMOS at 1.2 V, the proposed macro achieves a minimum latency of 0.48 ns, throughput of 2.31-3.1 TOPS, and energy efficiency of up to 419 TOPS/W. When evaluated on LeNet-5, AlexNet, and CNN-8 models, the macro achieves 97.81%, 93.23%, and 96.51% accuracy on MNIST/A-Z, CIFAR10, and SVHN datasets, respectively. In addition, 40% pruning preserves nearly 99.8% of the original accuracy while reducing MAC operations and computation cycles. For SNN-oriented workloads, the proposed AND-type bitcell efficiently supports spike-weight multiplication with low switching activity, where the 2A2W configuration achieves accuracy close to the FP32 baseline across VGG-8, VGG-16, and ResNet-18 networks on CIFAR-10, CIFAR-100, and ImageNet-1K datasets. Compared to prior ADC-based ReRAM-CIM designs, the proposed architecture improves latency and energy efficiency by nearly 30-40% while maintaining robust operation under full PVT and ReRAM variability. Overall, E-ReCON provides a scalable, low-latency, and energy-efficient nvCIM platform for next-generation edge-AI, IoT, biomedical sensing, and neuromorphic applications.

Multimodal IE in social media is difficult because a post may attach multiple images that are weakly related, redundant, or even misleading with respect to the text. In this setting, always-on multimodal fusion wastes computation and can amplify spurious visual cues. The core challenge is to decide, for each candidate span or marked entity pair, whether vision should be consulted at all and, if so, which small subset of images provides trustworthy evidence. We propose SAVER, a selective vision-as-needed framework for multimodal named entity recognition and multimodal relation extraction. SAVER uses a Conformal Groundability Gate (CGG) to estimate span-level visual groundability in MNER, derive pair-level activation in MRE from the two marked entities, and calibrate the activation threshold on a held-out split via a conformal-style procedure with Clopper--Pearson upper bounds. When activated, a submodular relevance--diversity selector chooses a compact evidence subset across images, which is then aggregated by a Set Transformer. An energy-inspired joint scoring head combines text, optional visual evidence, text--image consistency, and sparse routing for entity typing or relation classification. Experiments show that SAVER consistently improves F1 over strong text-only and always-on multimodal baselines, while reducing AURC, increasing activation coverage at a fixed risk level, and lowering FLOPs and P90 latency.

Multimodal large language models (MLLMs) have shown remarkable capability in bridging visual perception and textual reasoning, enabling zero-shot understanding across diverse industrial scenarios. However, their performance in open-vocabulary industrial anomaly detection (IAD) is often limited by domain-misaligned reasoning and hallucinated structural inferences. To address these challenges, we propose \textbf{IndusAgent}, a tool-augmented agentic framework for open-vocabulary IAD. Specifically, we first construct \textbf{Indus-CoT}, a structured dataset that integrates global visual observations, high-resolution local patches, and expert normalcy priors, providing supervision for fine-tuning the model on rigorous industrial inspection trajectories. Building on this, IndusAgent dynamically orchestrates a set of external tools, including dynamic region cropping, high-frequency feature enhancement, and prior retrieval, thus enabling the agent to actively resolve visual ambiguities and disentangle subtle anomalies. Furthermore, we introduce a gated reinforcement learning objective that jointly optimizes anomaly classification, localization accuracy, anomaly type reasoning, and efficient tool usage, ensuring that tool invocation occurs only when beneficial. Extensive evaluations on five industrial anomaly benchmarks, including MVTec-AD, VisA, MPDD, DTD, and SDD, demonstrate that IndusAgent achieves state-of-the-art zero-shot performance among all existing methods, validating our robustness and generalization capacity.

Human Action Recognition (HAR) is a fundamental computer vision task with diverse real-world applications. Practical deployments often involve low-light environments and unconstrained 6-DoF camera motion, conditions that degrade visual quality, disrupt temporal coherence, and compromise reliability of existing methods. Event cameras, with high low-light sensitivity and microsecond-level temporal resolution, paired with an inertial measurement unit (IMU), present a promising solution. However, current research faces two key challenges: absence of a benchmark integrating low-light conditions, 6-DoF motion, and synchronized IMU data; and lack of effective motion compensation techniques. To address these, we propose Event-IMU Stabilized HAR (EIS-HAR), with two modules. The first is an EIS module that reduces motion blur via a non-linear warping function to reconstruct a motion-compensated input. The second is a HAR module with a four-stage hybrid architecture to efficiently extract spatiotemporal features for accurate action recognition. To alleviate data scarcity, we introduce DarkShake-DVS, the first large-scale event-based HAR benchmark that includes 18,041 realworld clips captured in low light and intense 6-DoF motion, supplemented by synchronized IMU data. Extensive experiments on three datasets demonstrate consistent superiority of EIS-HAR over state-of-the-art methods.

Establishing a clear link between model predictions and the visual evidence that supports them is critical for transparency and reliability in multimodal reasoning, yet current multimodal large language model (MLLM) evaluations do not explicitly enforce this alignment. Existing benchmarks assess either textual answer correctness or pixel-level localization in isolation, leaving the coupling of reasoning and grounding an open challenge. We introduce VISTAQA, a comprehensive benchmark for joint evaluation of free-form answer correctness and pixel-level evidence grounding in visual question answering. VISTAQA comprises 1,157 expert-curated samples spanning six task types and six visual domains, ranging from direct perception to compositional and relational reasoning. VISTAQA requires models to not only answer correctly, but to also provide precise segmentation masks that support their answers. It also includes hallucination-aware examples where no valid visual evidence exists. To support this enhanced evaluation, we introduce GROVE, a unified evaluation metric that enforces joint correctness by combining textual accuracy and grounding quality via a per-sample geometric mean, ensuring neither dimension can compensate for deficiencies in the other. Comprehensive experiments across grounding-aware models and hybrid pipelines with general-purpose MLLMs reveal that even the strongest systems achieve limited performance under GROVE, highlighting a substantial gap between answer accuracy and visual evidence alignment.

X-ray security inspection requires accurate real-time detection of prohibited items, but existing models often struggle to balance the challenges of severe occlusion, complex clutter, and strict speed requirements. To overcome these challenges, this paper proposes GSA-YOLO, a novel lightweight framework built upon the YOLOv8n architecture, specifically engineered to enhance detection robustness and inference efficiency. GSA-YOLO strategically integrates structured sparsity and adaptive knowledge transfer through three core components: Group Lasso (GL) applied to the network neck for robust feature extraction; Sparse Structure Selection (SSS) applied to the detection head for significant model slimming; and an Adaptive Knowledge Distillation (Ada-KD) mechanism for comprehensive accuracy recovery. This integrated approach synergistically enhances feature representation while pruning redundant channels, maximizing model efficiency without sacrificing performance. Rigorous evaluations on the HiXray and PIDray datasets confirm GSA-YOLO's comprehensive capability, achieving a leading inference speed of 189.62 FPS, accompanied by a reduction in computational cost from 8.7G to 8.0G. Crucially, GSA-YOLO secures mAP50:95 results of 0.531 and 0.679 on HiXray and PIDray, demonstrating 2.4% and 1.8% improvements over the baseline, respectively. Compared to other models, GSA-YOLO exhibits enhanced accuracy while maintaining computational efficiency, making it a promising solution for practical X-ray security inspection.

Detecting small unmanned aerial vehicles from RGB-infrared remote-sensing pairs remains challenging due to tiny target scale, cluttered backgrounds, and spatial misalignment between heterogeneous sensors. Existing bimodal detectors often align or fuse features without assessing the reliability of local cross-sensor correspondence, allowing mismatch artifacts to propagate into the detection head. To address this issue, we propose LER-YOLO, a reliability-aware sparse mixture-of-experts framework for misaligned RGB-infrared UAV detection. LER-YOLO first introduces an Uncertainty-Aware Target Alignment module that resamples visible features toward the infrared reference and estimates a spatial reliability map. This reliability prior is then used by a Reliability-Guided Sparse MoE Fusion module to adaptively select k experts from RGB-dominant, infrared-dominant, and interactive fusion experts, enabling trustworthy cross-modal interaction while suppressing unreliable fusion. Experiments on the public MBU benchmark under a YOLOv5s-family protocol show that LER-YOLO achieves 89.7+/-0.2% AP50 over three independent seeds, with a best result of 89.9%. Extensive ablations, parameter-matched comparisons, synthetic-shift evaluations, and complexity analysis demonstrate that the gains mainly come from reliability-guided expert routing rather than increased model capacity.

Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, yet their $\mathcal{O}(L^2)$ attention complexity poses a formidable bottleneck for long-sequence synthesis. While recent sparse-linear attention hybrids aim to mitigate this, their performance severely degrades at extreme sparsity due to the "RoPE Dilemma": standard linear attention fails to preserve the orthogonal relative-position structure of 3D Rotary Position Embeddings (RoPE), neutralizing vital distance awareness. To address this, we propose \textbf{RoPeSLR}, a 3D RoPE-guided Sparse-LowRank attention framework. We establish that under empirically validated assumptions, the DiT attention manifold admits a decoupling into a high-frequency semantic spike set (bounded by $\mathcal{O}(L^{3/2})$ sparsity) and an extreme low-rank ($\mathcal{O}(d_h \log L)$) background continuum. Guided by this structural prior, RoPeSLR eschews standard linear attention for a head-wise low-rank parameterization equipped with a learnable 3D Absolute Positional Embedding (PE) injection, seamlessly synthesizing long-range relative distance decay. By guaranteeing sub-quadratic sparsity and sub-linear rank growth, RoPeSLR is exceptionally suited for scaling to ultra-long video inference. Extensive evaluations validate this scalable superiority: at 90\% sparsity, RoPeSLR achieves up to $10\times$ fewer FLOPs on Wan2.1-1.3B and delivers a $2.26\times$ end-to-end inference speedup on the ultra-long 100K+ token sequences of HunyuanVideo-13B, all while maintaining near-lossless generation fidelity (less than 1.3\% average VBench degradation).

Existing deep learning frameworks for Optical Coherence Tomography Angiography (OCTA) vessel segmentation are largely derived from the U-Net architecture, which serves as the foundation for most current designs. However, most of these methods focus only on holistic representation, struggling to address the problem of low local contrast unique to OCTA, which leads to vessel discontinuities and loss of detail. To address these problems, we propose LSENet, which builds upon the U-Net architecture by introducing three core innovative modules: To address vessel discontinuities, we introduce the Patch Information Enhance module (PIE), which replaces standard skip connections to execute patch-wise attention. To mitigate detail loss, the Multiscale Feature Fusion module (MFF) is proposed to feed the PIE module rich, multi-scale information by extracting visually interpretable features from both the original input and preceding layers. Finally, the Connectivity Refinement Decoder (CRD) is designed to refine features from all levels and utilize a large kernel in the final convolutional layer to reduce fragmentation. Experiments on three public datasets (OCTA-500, ROSE-1, and ROSSA) demonstrate that our proposed LSENet achieves state-of-the-art performance while requiring fewer parameters.

Foggy conditions are commonly encountered in real-world applications; however, existing action recognition approaches typically assume favorable weather and high-quality video inputs. On foggy days, unpredictable visibility degradation and reduced contrast obstruct the extraction of semantic cues, posing significant challenges for current action recognition methods. In this paper, we mitigate the issues faced in action recognition under foggy conditions by employing two strategies. First, we present FogAct, the first benchmark dataset for foggy action recognition, consisting of paired clean and foggy videos captured with a stereo camera system. The dataset spans 10 scenes and 55 action categories, comprising nearly 10,000 video clips. Second, we propose FogNet, a two-stream CLIP model that discovers fog-invariant semantic information hidden behind the degraded videos. FogNet learns robust representations of foggy videos with guidance from clean videos, effectively capturing shared structural and motion cues between clean and foggy videos. Extensive experiments on FogAct and three other popular datasets demonstrate that our method achieves competitive performance compared with state-of-the-art (SOTA) approaches. Our FogAct and FogNet are given in our project page.

Text-to-image diffusion models often face a severe trilemma in human portrait generation: text-image alignment, photorealism, and human-perceived aesthetics inherently inhibit one another. Supervised Fine-Tuning (SFT) is an effective method for enhancing the photorealism of image generation. However, it often leads to overfitting to the training dataset, corrupts pre-trained image priors, and degrades alignment or aesthetics. To break this bottleneck, we propose a feature supervision paradigm for Multimodal Diffusion Transformers (MM-DiT). Specifically, we introduce a lightweight cross-modal alignment mechanism that implicitly extracts multi-granularity vision-aligned text representations from SigLIP 2 and applies supervision to the image branch of MM-DiT during the training stage, with zero extra inference overhead. Our method injects vision-aligned text guidance while preserving the base model's original generalization, avoiding degradation caused by SFT. Furthermore, our method directly mines implicit multi-granularity aesthetic signals from pre-trained vision foundation models to optimize human-perceived aesthetics. Extensive experiments on MM-DiTs show that our method pushes the Pareto frontier and achieves synergistic improvements across text-image alignment, photorealism, and human-perceived aesthetics.

We present the University of Florida Gators submission to the AmericasNLP 2026 shared task on cultural image captioning for Indigenous languages. Our two-stage pipeline generates a Spanish intermediate caption with Qwen2.5-VL, then produces the target-language caption using retrieval-augmented many-shot prompting with Gemini 2.5 Flash. We achieve 164.1%, 131.7%, and 122.6% improvements over the shared task baseline for Bribri, Guaraní, and Orizaba Nahuatl captioning, respectively, in our dev set evaluation and maintain >150% improvements for the Bribri and Orizaba Nahuatl languages in the test set evaluation. We find retrieval is highly language-dependent, beneficial only for large, in-domain corpora, and that synthetic data augmentation accounts for around 28 chrF++ of the dev set Guaraní performance gain. Our submission is the overall winner of the shared task, placing second out of five finalist submissions in human evaluations of target-language captions.

Diffusion models provide powerful priors for zero-shot video inverse problems, but their real-time deployment is hindered by two inefficiencies: high initial latency caused by holistic video restoration, and low throughput resulting from multiple VAE passes to enforce measurement consistency in pixel space. To overcome these limitations, we propose Autoregressive Video Inverse problem Solver (AVIS). The AVIS framework leverages autoregressive video diffusion models to restore videos in a streaming manner, naturally eliminating latency bottlenecks. Specifically, AVIS initializes reverse diffusion with a measurement-consistent estimate, reducing the required sampling steps. Compared to leading non-autoregressive solvers, AVIS drastically reduces initial latency from 114s to 4s and increases throughput from 0.71 to 1.18 FPS while achieving superior restoration quality. We further introduce a highly accelerated variant, dubbed AVIS Flash, that enforces measurement consistency solely on the first chunk. AVIS Flash substantially boosts throughput to 5.91 FPS on a single RTX 4090 GPU while maintaining competitive performance and achieving a favorable efficiency-performance trade-off, paving the way toward real-time deployment.

Mixture-of-Experts (MoE) models are often interpreted by analysing which categories are routed to which experts. However, routing alone does not reveal what each expert actually encodes. We train sparsely-gated convolutional MoE models with a contrastive objective on natural images and characterise expert specialisation using tools from visual neuroscience. Extending from gating-level to expert-level analyses, we measure per-expert category separability, and per-expert tuning using the most exciting inputs. Extending from category-level to feature-level explanations, we interpret tuning via semantic dimensions derived from a dataset of human behavioural judgements (THINGS). Finally, we use tuning and representational similarity analysis to assess the stability of expertise-allocation across independent initialisations. We find that an animate-inanimate distinction dominates expert partitioning, apparent from gating through to expert readout, and is stable across independently trained models. Although routing statistics suggest relatively sparse, categorical preferences, expert analyses reveal broader tuning to continuous visual and semantic dimensions that extend beyond category boundaries. Experts exhibit similar category-separability to one another, despite distinct feature tuning, demonstrating the explanatory benefits of moving beyond category-level analyses. Together, these results show that expert specialisation in vision MoEs extends well beyond category routing and is better understood by probing fine-grained expert-level tuning and representational structure.

EASA's learning-assurance guidance requires data-driven aviation systems to build and monitor their own situation representation, yet for neural networks the technical means to provide such evidence remain an open problem. We address this gap for a vision-based aircraft landing system: we propose that a minimally assurable model must at least be shown to separate content from style in its own situation representation. Showing that the model's predictions then rely largely on the contentful representation components leads to a concrete assurance path. To demonstrate this assurance path on a concrete model we train a vision transformer model for runway keypoint regression on the LARDv2 dataset. The model, which acts as the subject for our assurance demonstration, produces per-patch embeddings that we decompose into interpretable atoms via K-SVD sparse dictionary learning. A qualitative visualization confirms that contentful atoms track task-relevant runway structure and stylistic atoms track domain-specific appearance, and the regression head is shown to place almost all of its linear weight on contentful atoms. We further build on the content/style separation and define out-of-model-scope (OOMS) detection, a novel runtime assurance approach directly monitoring the model's situation representation. OOMS monitoring is complementary to operational design domain and output-space out-of-distribution monitoring and addresses concrete requirements of the recent EASA guidance. By directly analyzing a model's situation representation both at test time and runtime, this work delivers the first concrete piece of the representation-level evidence that EASA learning-assurance guidance demands, and points to mechanistic interpretability as a practical building block of future aviation safety cases.

Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching previously generated visual tokens. Recent research has shown that retaining only a few lines of cache tokens can maintain high-quality images while significantly reducing memory usage and improving throughput. However, these methods allocate a fixed budget to each attention head, overlooking the heterogeneity among attention heads, leading to suboptimal memory allocation. In this paper, we observe that attention heads across different layers exhibit diverse attention patterns, where some heads focus on local neighborhoods while others capture broader contextual dependencies. Based on this insight, we propose a novel head-aware key-value (KV) cache compression framework for autoregressive image generation, called HeadKV, which assigns smaller budgets to locality-biased heads and larger budgets to heads with broader attention. A key challenge lies in identifying the type of each attention head to guide cache compression. We further observe that, within the same layer, each head exhibits consistent attention patterns across token positions, \emph{i.e.}, a head's behavior for early tokens remains consistent with that for later tokens. This insight suggests that head types can be identified during the early stage and reused for KV compression throughout generation. Its advantage is that it requires no additional training or dataset-level statistics and generalizes seamlessly across different inputs. Moreover, we design a Stratified Token Eviction strategy to effectively preserve long-range information. Extensive experiments demonstrate its effectiveness across multiple autoregressive image generation models.

The field of sign language translation has witnessed significant progress in the translation between sign and spoken languages, but the translation between sign languages remains largely unexplored and out of reach. The latter can help 1.5 billion deaf and hard-of-hearing (DHH) people worldwide communicate across language barriers without relying on hearing interpreters or written-language fluency. The cascade approach composing separate sign-to-text, text-to-text, and text-to-sign systems suffers from error propagation and extra latency as well as the loss of information unique in the visual modality. We aim to develop direct sign-to-sign translation. However, a large-scale open-domain parallel corpus has not been curated between sign languages. To enable direct translation between sign language utterances, we use back-translation to produce synthetic sign-sign pairs from unaligned individual language utterance-sign corpora. Using this data, we jointly train a single MBART-based model for both text->sign (T2S) and sign->sign (S2S). On synthetically generated paired sets between American Sign Language (ASL), Chinese Sign Language (CSL), and German Sign Language (DGS), our direct S2S method outperforms the cascaded baseline on geometric sign error metrics (20% lower DTW-aligned MPJPE) and language matching metrics after predicted sign utterances are translated back to sentences (50% high BLEU-4) while achieving a roughly 2.3* speedup. On a small set of pre-existing cross-lingual sign data, we find similar improvements for our proposed method.

Mobile app marketplaces require developers to disclose standardized content rating descriptors (CRDs) to inform users about potentially sensitive or restricted content. Ensuring the accuracy and consistency of these disclosures remains challenging due to the multimodal nature of app content, which spans textual descriptions and visual interfaces. In this paper, we present QwenSafe, a Vision-Language Model (VLM) designed to automatically identify the presence of Apple-defined CRDs by jointly reasoning over app metadata and screenshots. To enable scalable training for this task, we introduce metadata2CRD, a data-construction pipeline that synthesizes descriptor-aligned question-answer pairs by combining app descriptions, screenshots, and formal descriptor definitions. We adapt Qwen3-VL-8B using supervised fine-tuning followed by Direct Preference Optimization (DPO) to align model predictions with descriptor-specific evidence and explanations across visual and textual modalities. We evaluate QwenSafe on 12 Apple-defined content rating descriptors and compare it against state-of-the-art vision-language models, including Qwen3-VL, LLaVA-1.6, and Gemini-2.5-Flash. QwenSafe consistently outperforms all baselines in binary CRD classification, achieving improvements in positive-class recall of 111.8%, 36.1%, and 2.1%, respectively. Our results demonstrate that descriptor-aware multimodal alignment substantially improves automated content classification and highlights the potential of vision-language models to support scalable and consistent content rating in mobile app marketplaces.

Inferring rigid-body physical states and properties from monocular videos is a fundamental step toward physics-based perception and simulation. Existing approaches assume specific underlying physical systems, object types, and camera poses, making them unable to generalize to complex real-world settings. We introduce $Δ$YNAMICS, a vision-language framework that uses language as a unified representation of rigid-body dynamics. Instead of directly predicting parameters, $Δ$YNAMICS generates scene configurations in a structured text format for physics simulation. We enhance the model's generalization by integrating natural language motion reasoning and leveraging optical flow as a semantic-agnostic input. On the CLEVRER dataset, $Δ$YNAMICS achieves a segmentation IoU of 0.30, a 7x improvement over leading VLMs (InternVL3-8B, Qwen2.5-VL-7B and Claude-4-Sonnet). Additionally, test-time sampling and evolutionary search further boost performance by 27% and 120% in segmentation IoU, respectively. Finally, we demonstrate strong transfer to a new dataset of 235 real-world rigid-body videos, highlighting the potential of language-driven physics inference for bridging perception and simulation.

Hyperspectral imagery encodes rich material properties that can improve tracking robustness under appearance ambiguity, illumination change, and background clutter. However, due to the limited availability of hyperspectral video data, many existing methods adapt pretrained RGB trackers via spatial or channel fusion strategies, largely neglecting the intrinsic material information in hyperspectral imagery. Moreover, the few material-aware approaches typically rely on external spectral unmixing pipelines that are decoupled from the tracking objective, limiting effective optimization of material representations for target localization. To address these limitations, we formulate hyperspectral object tracking as a joint optimization problem of material decomposition and target localization, coupling the two tasks via a weighted target-oriented unmixing loss that explicitly aligns material representations with localization accuracy. Specifically, we propose a material representation decomposition module for deep learning-based spectral unmixing with adaptive frequency decomposition. Building on the decomposed material representations, we further introduce a dual-branch wavelet-enhanced material prompt module that learns low- and high-frequency material prompts through efficient spatial-material interactions in the frequency domain. The framework is model-agnostic and can be seamlessly generalized to different unmixing backbones. Extensive experiments on standard hyperspectral tracking benchmarks demonstrate state-of-the-art performance and validate the effectiveness of the proposed end-to-end material-aware tracking framework. Code is available at https://github.com/han030927/E2EMPT.

Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art methods employ Vision Transformers (ViTs) as backbone foundation models to extract patch-level features that are robust to viewpoint, illumination, and seasonal variations, which are then aggregated into a compact global descriptor for retrieval. Most existing aggregation methods uniformly pool patch tokens into learned clusters, despite the fact that different clusters often encode distinct spatial or semantic patterns and contribute unequally to VPR performance. To address this limitation, we propose Weighted Aggregated Descriptor (WeiAD), which assigns weights to clusters during aggregation, producing more discriminative global representations. Beyond accuracy, retrieval latency is a critical concern for large-scale deployments and resource-constrained edge devices. Prior work mainly reduces latency by compressing global descriptors, while overlooking the cost of feature extraction, an issue exacerbated by ViT-based backbones. We therefore introduce WeiToP, a VPR-oriented token pruning framework that reduces feature extraction cost via self-distillation, where aggregation-induced token importance supervises a lightweight pruning module attached to an early transformer layer, enabling inference-time token pruning. After a single joint training phase, WeiToP enables plug-and-play token pruning at inference time, allowing flexible and on-demand control over the accuracy-efficiency trade-off without additional training. Moreover, WeiToP outperforms existing token pruning methods adapted from general vision tasks.

Modern vision models achieve strong performance on standard benchmarks, yet their aggregate accuracy reveals little about which scene properties drive their predictions. Existing robustness benchmarks provide important stress tests, but typically manipulate global 2D image properties, rely on entangled real-world variation, or cover only a limited set of 3D objects and scene parameters. We introduce MAPS (Manifolds of Artificial Parametric Scenes), a scalable instrument for controlled attribution of vision model behavior to scene parameters. MAPS comprises 2,618 curated photorealistic 3D meshes validated for recognizability across 560 ImageNet classes and provides a Blender-based rendering pipeline for on-demand image generation under continuous variation of nine independent scene-factors spanning background, camera, and lighting, extensible to other factors. To showcase its applicability, we use MAPS to evaluate 20 convolutional and transformer-based models by quantifying their reliance on these scene factors through regression-based sensitivity analysis. We find a near-universal failure axis across all tested architectures: camera distance and elevation consistently dominate recognition failure regardless of ImageNet accuracy. However, the full sensitivity structure reveals that modern CNNs and transformers cluster together, distinct from older architectures, suggesting that fine-grained architectural design choices, rather than the coarse CNN-versus-transformer distinction, are the stronger determinant of sensitivity profiles.

Vision-language models (VLMs) are used as high-level planners for embodied agents, translating natural language instructions and visual observations into action plans. While prior work has studied abstention in LLMs, existing benchmarks are largely text-only and do not capture the perceptual grounding and physical constraints inherent to embodied robotics environments. In such settings, abstention requires recognizing when instructions are ambiguous, physically infeasible, based on false premises, or otherwise unresolvable given the available sensory modalities and context. To address this gap, we introduce a taxonomy to categorize abstention in the context of embodied robotics and present RoboAbstention, a scalable and auditable framework for generating abstention instructions grounded in images gathered from five robotics datasets. RoboAbstention instantiates the taxonomy through a three-phase pipeline: (1) structured visual grounding, (2) deterministic constraint derivation, and (3) controlled instruction generation via category-specific templates. This enables the construction of a diverse dataset with verifiable abstention conditions. We evaluate several frontier VLMs and find that all models exhibit significant weaknesses in abstention, including those with advanced reasoning capabilities. The best-performing model, Gemini 2.5 Flash, abstains on only 39.0% of our 6,069 benchmark instructions, while the embodied planner Gemini Robotics ER 1.6 Preview abstains on just 16.5%. We further explore methods for improving abstention in VLM planners, such as defensive prompting and in-context learning, and find that these interventions substantially improve performance, reaching 93.6% abstention rate for Gemini Robotics ER 1.6 Preview and 88.6% for GPT 5.4 Mini, yet no approach fully solves the problem. We open-source RoboAbstention at https://purseclab.github.io/RoboAbstention/.

Accurate vessel segmentation is essential for medical image analysis, yet remains challenging due to complex vascular patterns and imaging ambiguity. Most deep models rely on single-pass prediction, limiting their ability to refine uncertain or disconnected regions during inference. To address this limitation, we propose Uncertainty-Guided Conservative Propagation (UGCP), a general plug-in module for vessel segmentation. Instead of directly using a one-shot output as the final prediction, UGCP performs a small number of logit-space update steps to refine the segmentation through local predictions interaction. Predictive uncertainty guides reliable regions to support ambiguous regions, while structure-aware modulation and source-based stabilization reduce unreliable propagation and excessive drift. The module is differentiable and can be trained end-to-end with different segmentation networks. We evaluate UGCP on four public vessel segmentation datasets covering 2D and 3D tasks, including retinal vessel, coronary artery, and cerebral vessel segmentation. Experiments with convolutional neural network-based and Transformer-based backbones show consistent improvements in Dice similarity coefficient, centerline Dice, and 95th percentile Hausdorff distance. Further analysis demonstrates that UGCP reduces vessel disconnections and improves structural consistency with limited additional computation. The code will be made available at https://github.com/chenzhao2023/UGC_PR.

Existing Gaussian avatar methods typically parameterize geometry on a body-template surface, which entangles the avatar's representation space with the template's deformation space and limits the capture of layered, off-body, and non-rigid clothing geometry. We present PiG-Avatar, which addresses this limitation by using the parametric body model solely for kinematic transport, while representing the avatar as Gaussians anchored in a volumetric canonical space governed by a continuous neural field. This decouples representation from template topology, avoiding the geometric constraints of surface-based parameterizations. Kinematic coherence is maintained through 3D barycentric anchor transport, which guides motion without constraining geometry and allows anchors to deviate freely from the template surface, yielding dense, stable temporal surface correspondences by construction. To make this unconstrained formulation tractable, we introduce dual-level spatially coherent optimization, combining Sobolev-preconditioned neural-field updates with a novel KNN-based preconditioning of canonical anchor geometry. Together, these mechanisms induce an emergent self-organization of anchor density: anchors migrate toward regions of high curvature, appearance variation, and non-coherent motion without explicit heuristics. As a result, complex clothing geometry and layered surfaces emerge as natural, high-fidelity outputs. This single representation further supports hierarchical reconstruction across multiple levels of detail, with coarse-level supervision propagating to finer levels through the shared field and coupled anchor graph. On established benchmarks featuring subjects with complex clothing and challenging non-rigid motion, PiG-Avatar achieves state-of-the-art rendering quality, generalizes robustly to imperfect body model initialization, and renders in real time across all detail levels.

Pairwise preferences and pointwise ratings are the two dominant annotation protocols in image aesthetic assessment (IAA), yet existing benchmarks adopt only one, leaving their complementarity unmeasured under controlled conditions. We introduce PPaint, a matched dual-protocol benchmark in which 15 domain experts, 5 per category, annotate 150 Chinese paintings under both protocols across five aesthetic dimensions, collecting 45,900 pairwise expert judgments through a locally dense preference design alongside the matched ratings. The matched design reveals complementary strengths: preferences yield more consistent ordinal rankings, while ratings anchor the absolute score scale. Fusing both signals via two independent preference-to-score methods yields a fused expert ground truth on which the two constructions converge to nearly identical scores. The same preference-to-score principle extends to label-free VLM training. PSDistill converts VLM pairwise judgments into calibrated pseudo-scores via an Elo reference pool, and trains the same VLM with confidence-weighted ranking optimization to produce a single-pass aesthetic scorer. Trained on a single painting category, the distilled Qwen3-VL-8B improves mean SRCC from 0.504 to 0.709 across all three categories, outperforming all open-source baselines including the dedicated aesthetic model ArtiMuse and matching closed-source Gemini-3.1-Pro within 0.04 SRCC at single-pass inference cost, with cross-domain transfer further validated on APDDv2. We will release the full PPaint dataset and training code.

Spacecraft pose estimation networks require tens of thousands of CAD-rendered images to be trained. This reliance on synthetic CAD data (i) limits applicability to targets with reliable geometry prior, excluding uncooperative or poorly documented spacecraft, and (ii) causes poor generalization to real on-orbit conditions due to unrealistic illumination and material appearance. This paper introduces a NeRF-based image augmentation method that enables the learning of spacecraft pose estimators from only a few tens to a few hundreds of images. The method learns a Neural Radiance Field of the target and generates a large, diverse dataset through geometrically-consistent viewpoint and appearance augmentation. This augmented dataset enables the training of accurate target-specific pose estimators without requiring a CAD model or large synthetic datasets. Experiments show that our approach supports the training of accurate pose estimators from only 25 to 400 realistic images, even under severe illumination variations. When applied on large CAD-based synthetic datasets, the NeRF-based augmentation also enhances out-of-domain generalization, yielding improved robustness to real on-orbit conditions.

For camera-based satellite visual sensing, Sim2Real data construction requires images that approach real-domain sensor appearance while retaining the annotations inherited from simulation. Real sensor images of satellite targets with reliable pose labels and component-level masks are difficult to acquire at scale, whereas synthetic rendering provides exact geometric annotations but suffers from a visible appearance gap. This paper presents a component-aware structure-preserving style transfer framework for satellite visual synthetic-to-real data construction. The method builds weakly paired real--synthetic samples from calibrated real acquisition, ArUco-based camera-pose measurement, CAD rendering, and component masks. It then extracts part-wise real-domain style codes from unlabeled real images and injects them into corresponding synthetic satellite regions through mask-aligned modulation. To keep the generated images usable for downstream sensor-data supervision, adversarial training is combined with local contrastive consistency, self-regularization, and edge-preserving constraints. Experiments are conducted on 5,000 rendered satellite images and 100 real images captured in a calibrated setup. The real images provide target-domain appearance references and final evaluation images, while the downstream GDRNet pose estimator is trained only on synthetic or translated synthetic images. Compared with representative image-translation baselines, the proposed method achieves the lowest image distribution discrepancy, with an FID of 54.32 and a KID of 0.048. When the translated data are used to train GDRNet in this target-domain adaptation setting, the ADD pass rate improves to 0.260 and the AUC improves to 0.611. These results indicate that component-level appearance transfer can improve annotation-preserving satellite visual Sim2Real data generation in the considered calibrated setup.

Overparameterized neural networks often contain many removable neurons, yet what makes a neuron redundant remains poorly understood. Existing pruning criteria commonly rely on local quantities such as weight magnitude, activation strength, or gradient sensitivity, but these measures provide limited insight into the structural role of a neuron in the transformation performed by a layer. Here we show that neuronal redundancy can be characterized by weak participation in the spectral structural distortion induced by layer-wise representation transformations. For each hidden layer of a trained network, we record pre-activation and post-activation hidden states, model neurons as graph nodes, and construct input-side and output-side graphs that describe neuron-level relational structure before and after the layer transformation. We then define a spectral structural importance score that measures the contribution of each neuron to the dominant graph-spectral distortion between these two relational structures. Low-participation neurons are treated as structurally redundant and removed through an iterative pruning process in which scores are recomputed after each structural change. No parameter updates are performed during intermediate pruning rounds; after the target parameter reduction is reached, a single recovery fine-tuning stage is applied to the compact model. Direct ablation analysis and experiments across conventional neural networks, encoder-only Transformers, and decoder-only language models show that this graph-spectral criterion identifies removable neurons and Transformer units while preserving task performance after compression. These results suggest that neural redundancy is not merely a consequence of small weights or weak activations, but can be understood through weak participation in the spectral distortion of layer-wise relational structure.

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later timesteps. This structure offers a natural opportunity for efficient generation, as high-resolution computation on noise-dominated frequencies is largely redundant. We propose Spectral Progressive Diffusion, a general framework that progressively grows resolution along the denoising trajectory of pretrained diffusion models. To this end, we develop a spectral noise expansion mechanism and derive an optimal resolution schedule from the model's power spectrum. Our framework supports training-free acceleration and a novel fine-tuning recipe that further improves efficiency and quality. We demonstrate significant speedups on state-of-the-art pretrained image and video generation models while preserving visual quality.

We present Lance, a lightweight native unified model supporting multimodal understanding, generation, and editing for both images and videos. Rather than relying on model capacity scaling or text-image-dominant designs, Lance explores a practical paradigm for unified multimodal modeling via collaborative multi-task training. It is grounded in two core principles: unified context modeling and decoupled capability pathways. Specifically, Lance is trained from scratch and employs a dual-stream mixture-of-experts architecture on shared interleaved multimodal sequences, enabling joint context learning while decoupling the pathways for understanding and generation. We further introduce modality-aware rotary positional encoding to mitigate interference among heterogeneous visual tokens and boost cross-task alignment. During training, Lance adopts a staged multi-task training paradigm with capability-oriented objectives and adaptive data scheduling to strengthen both semantic comprehension and visual generation performance. Experimental results demonstrate that Lance substantially outperforms existing open-source unified models in image and video generation, while retaining strong multimodal understanding capabilities. The homepage is available at https://lance-project.github.io.

Autonomous rendezvous and proximity operations around uncooperative, unknown spacecraft are critical for active debris removal and on-orbit servicing missions. A key component of such operations is the offline reconstruction of a 3D model of the target from a set of 2D images. This task is challenging due to two main factors. First, in-orbit illumination conditions exhibit considerable variability, and change rapidly over time. Second, the inaccuracy of pose information in the images, results in 3D reconstruction uncertainty. To overcome these challenges, we propose to extend Neural Radiance Fields with per-image degrees of freedom: a learnable appearance embedding that captures the illumination conditions specific to each image, and an image-specific pose correction term that refines its noisy pose label to increase 3D consistency across images. These parameters add minimal complexity, as they are learned jointly with the NeRF, yet they substantially improve robustness to illumination variability and pose inaccuracies. We validate our approach on three image sets representative of in-orbit operations, demonstrating its effectiveness for offline reconstruction and highlighting its suitability for online reconstruction, an open problem in the field.

Multimodal large language models are increasingly used as agent backbones that understand multimodal inputs, plan retrieval actions, invoke external tools, and reason over retrieved information. Yet existing benchmarks rarely evaluate this ability in short-video applications, where a paused frame is often visually ambiguous and answering requires vertical, long-tail, and fast-evolving domain knowledge. We introduce SVFSearch, the first open benchmark for short-video frame search in the Chinese gaming domain. SVFSearch contains 5,000 four-choice test examples and 4,198 auxiliary training examples, each centered on a paused game scene from a real short-video clip. To support fair and reproducible evaluation, SVFSearch provides a frozen offline retrieval environment with a game-domain text corpus, a topic-linked image gallery, and text, image, and multimodal retrieval interfaces, avoiding reliance on uncontrolled web search APIs. We evaluate representative paradigms ranging from direct QA and RAG workflow to Plan-Act-Replan agents and learned search models. Results reveal a large gap between model-only answering, practical agentic search, and oracle knowledge: the best open-source direct-QA model reaches 66.4%, the best practical agent achieves 79.1%, and oracle knowledge reaches 95.4%. Further analysis exposes bottlenecks in visual grounding, retrieval quality, evidence-grounded reasoning, and tool-use behavior, including over-search, answer-only shortcuts, and retrieval-induced misleading.

Pre-trained vision foundation models (VFMs) provide strong semantic representations, yet their patch-level features are inherently coarse, limiting their effectiveness on tasks requiring fine-grained localization, dense prediction, and point-wise correspondence. In this work, we revisit feature upsampling for VFMs from the perspective of \textbf{\textit{inverse problem}} and propose Weighted Reverse Convolution (WRC), a spatially adaptive inverse operator for densifying high-level visual descriptors. Specifically, we formulate feature upsampling as a weighted Tikhonov-regularized least-squares problem, where spatially varying weights modulate both data fidelity and prior strength at each spatial location. This allows WRC to adapt the reconstruction to spatially varying feature characteristics, thereby preserving critical structures while mitigating over-smoothing. Moreover, WRC retains an efficient, fully differentiable closed-form FFT solution, making it a practical drop-in upsampling operator. Integrated into a lightweight self-supervised densification framework, WRC consistently improves dense feature quality across various downstream benchmarks, including segmentation, depth estimation, video object segmentation, object discovery, and keypoint correspondence, while maintaining high computational efficiency.

Existing vision-language forgery detection and grounding methods operate under a closed-world paradigm, assuming verification can be completed by the model alone. However, self-contained MLLMs are constrained by finite parametric knowledge, static training corpora, and limited perceptual resolution, creating a practical ceiling in dynamic open-world forensics -- particularly for real-time event verification requiring external clues and forgery segmentation demanding fine-grained scrutiny of local manipulations. To address these limitations, we shift from scaling up the self-contained model toward reaching beyond it. We propose \textbf{OmniVL-Guard Pro}, a tool-augmented agent that extends unified forensics from closed-world prediction to open-world clues-driven reasoning. OmniVL-Guard Pro integrates a tool environment spanning real-time event search, local cropping and zooming, edge-anomaly screening, face detection, video frame extraction, and SAM3-based segmentation. To generate high-quality tool-reasoning trajectories, we introduce \textbf{Tree-Structured Self-Evolving Tool Trajectory Generation}, which produces diverse trajectories through seed guidance, guider-free self-evolution, and weakly-hinted hard sample synthesis, yielding the Full-Spectrum Tool Reasoning (FSTR) dataset for training. We further propose \textbf{Checker-Guided Agentic Reinforcement Learning} (CGARL), which provides process-level supervision to penalize cases where the answer is correct but the reasoning is distorted. Extensive experiments demonstrate that OmniVL-Guard Pro achieves state-of-the-art performance across various tasks, and exhibits strong zero-shot generalization. The FSTR dataset and code for OmniVL-Guard Pro will be publicly released at https://github.com/shen8424/OmniVL-Guard-Pro.

Realistic surgical simulation plays a crucial role in training novice surgeons and in the development of autonomous agents. World models can scale such simulation environments to realistic and diverse procedures by predicting future patient states conditioned on current observations and surgical actions. However, current state-of-the-art approaches often fail to satisfy key criteria required for clinical applicability, including visual realism, physically grounded interactions, and the ability to simulate scenarios beyond the training distribution. Hence, we introduce SWoMo, a neuro-symbolic world model for cataract surgery simulation that decouples motion generation from visual realism. The symbolic component, consisting of a rule-based simulator and scene graph representations, models motion dynamics and tool-tissue interactions, while a diffusion model produces realistic visual appearance, including textures and tissue deformations. We propose an inverse pairing strategy that reconstructs real surgical videos in the simulator to obtain paired simulated and real videos, which are then used to train our video diffusion model for the reverse objective of sim-to-real translation. Our experiments show both qualitative and quantitative improvements over prior work. We demonstrate that our simulator further satisfies the key criteria, including generalisation to unseen interaction geometries, improvements in downstream phase detection, and unsupervised video style transfer. The code, data, and model weights are available at: https://ssharvienkumar.github.io/SWoMo/

Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and prevents the recovery of dense geometry. Prior methods either distill geometry from external vision models, introducing error accumulation, or enable direct prediction with inefficient per-pixel query or coarse token-level outputs. In this paper, we propose DepthVLM, a simple yet effective framework that transforms a single VLM into a native dense geometry predictor while preserving its multimodal capability. By attaching a lightweight depth head to the LLM backbone and training under a unified vision-text supervision paradigm with a two-stage schedule, DepthVLM generates full-resolution depth maps alongside language outputs in a single forward pass. We further introduce a unified indoor-outdoor metric depth benchmark in a VLM-compatible format. Experiments show that DepthVLM significantly outperforms existing VLMs with higher inference efficiency, surpasses leading pure vision models, and improves complex 3D spatial reasoning, moving toward a truly unified multimodal foundation model. The project page is available at https://depthvlm.github.io/

Natural language is an intuitive interface for humanoid robots, yet streaming whole-body control requires control representations that are executable now and anticipatory of future physical transitions. Existing language-conditioned humanoid systems typically generate kinematic references that a low-level tracker must repair reactively, or use latent/action policies whose outputs do not explicitly encode upcoming contact changes, support transfers, and balance preparation. We propose \textbf{DAJI} (\emph{Dynamics-Aligned Joint Intent}), a hierarchical framework that learns an anticipatory joint-intent interface between language generation and closed-loop control. DAJI-Act distills a future-aware teacher into a deployable diffusion action policy through student-driven rollouts, while DAJI-Flow autoregressively generates future intent chunks from language and intent history. Experiments show that DAJI achieves strong results in anticipatory latent learning, single-instruction generation, and streaming instruction following, reaching 94.42\% rollout success on HumanML3D-style generation and 0.152 subsequence FID on BABEL.

Interactive real-time autoregressive video generation is essential for applications such as content creation and world modeling, where visual content must adapt to dynamically evolving event conditions. A fundamental challenge lies in balancing reactivity and stability: models must respond promptly to new events while maintaining temporal coherence over long horizons. Existing approaches distill bidirectional models into autoregressive generators and further adapt them via streaming long tuning, yet often exhibit persistent drift after condition changes. We identify the cause as conditional bias, where the teacher may provide condition-aligned but trajectory-agnostic guidance, biasing generation toward locally valid yet globally inconsistent modes. Inspired by Trust Region Policy Optimization, we propose Delta Forcing, a simple yet effective framework that constrains unreliable teacher supervision within an adaptive trust region. Specifically, Delta Forcing estimates transition consistency from the latent delta between teacher and generator trajectories, and uses it to balance teacher supervision with a monotonic continuity objective. This suppress unreliable teacher-induced shifts while preserving responsiveness to new events. Extensive experiments demonstrate that Delta Forcing significantly improves consistency while maintaining event reactivity.

Vision-language-action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings due to being trained under traditional imitation learning framework. Existing closed-loop supervision approaches lack scalability and fail to completely model a reactive environment. We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model. The ego vehicle and nearby traffic agents are independently controlled over multi-step horizons, while being reactive to other agents in the scene, enabling closed-loop training. MAPLE consists of two training stages: (1) supervised fine-tuning on the latent rollouts based on ground-truth trajectories, followed by (2) reinforcement learning with global and agent -specific rewards that encourage safety, progress, and interaction realism. We further propose diversity rewards that encourage the model to generate planning behaviors that may not be present in logged driving data. Notably, our closed-loop training framework is scalable and does not require external simulators, which can be computationally expensive to run and have limited visual fidelity to the real-world. MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.

Federated Learning (FL) enables collaborative training of distributed clients while protecting privacy. To enhance generalization capability in FL, prototype-based FL is in the spotlight, since shared global prototypes offer semantic anchors for aligning client-specific local prototypes. However, existing methods update global prototypes at the prototype-level via averaging local prototypes or refining global anchors, which often leads to semantic drift across clients and subsequently yields a misaligned global signal. To alleviate this issue, we introduce hyper-prototypes, defined by a set of learnable global class-wise prototypes to preserve underlying semantic knowledge across clients. The hyper-prototypes are optimized via gradient matching to align with class-relevant characteristics distilled directly from clients' real samples, rather than prototype-level descriptors. We further propose FedHPro, a Federated Hyper-Prototype Learning framework, to leverage hyper-prototypes to promote inter-class separability via mutual-contrastive learning with client-specific margin, while encouraging intra-class uniformity through a consistency penalty. Comprehensive experiments under diverse heterogeneous scenarios confirm that 1) hyper-prototypes produce a more semantically consistent global signal, and 2) FedHPro achieves state-of-the-art performance on several benchmark datasets. Code is available at \href{https://github.com/mala-lab/FedHPro}{https://github.com/mala-lab/FedHPro}.

Missing modalities are prevalent in real-world Alzheimer's disease (AD) assessment and pose a significant challenge to multimodal learning, particularly when the distribution of observed modality subsets differs between training and deployment. Such missingness pattern mismatch induces a conditional representation shift across modality subsets. Existing approaches that rely on implicit imputation or modality synthesis often fail to explicitly model modality availability and uncertainty, leading to overconfident dependence on synthesized features, reduced robustness, and miscalibrated uncertainty estimates. To address these limitations, we propose PRA-PoE, an incomplete multimodal learning framework that is equipped with Prototype-anchored Representation Alignment (PRA) and an Uncertainty-aware Product of Experts (UA-PoE) fusion mechanism. First, PRA uses learnable global prototypes and availability-conditioned tokens to encode modality availability, distinguish observed from missing modalities, re-synthesize features for missing modalities, and adaptively refine observed representations to align latent spaces across modality subsets, with the goal of reducing representation shift under varying missingness patterns. Second, UA-PoE models each modality as a Gaussian expert and performs closed-form Product of Experts fusion, where experts with higher uncertainty are automatically down-weighted via lower precision, improving uncertainty reliability. We evaluate PRA-PoE under a clinically realistic protocol by training with naturally missing data and testing on all non-empty modality combinations. PRA-PoE consistently outperforms the state-of-the-art across datasets, achieving a 5.4% relative improvement in average accuracy on ADNI and a 10.9% relative gain in average F1 on OASIS-3 over the strongest baseline across all non-empty modality subsets.

The remarkable achievements of both generative models of 2D images and neural field representations for 3D scenes present a compelling opportunity to integrate the strengths of both approaches. In this work, we propose a methodology that combines a NeRF-based representation of 3D scenes with probabilistic modeling and reasoning using diffusion models. We view 3D reconstruction as a perception problem with inherent uncertainty that can thereby benefit from probabilistic inference methods. The core idea is to represent the 3D scene as a stochastic latent variable for which we can learn a prior and use it to perform posterior inference given a set of observations. We formulate posterior sampling using the score-based inference method of diffusion models in conjunction with a likelihood term computed from a reconstruction model that includes volumetric rendering. We train the model using a two-stage process: first we train the reconstruction model while auto-decoding the latent representations for a dataset of 3D scenes, and then we train the prior over the latents using a diffusion model. By using the model to generate samples from the posterior we demonstrate that various 3D reconstruction tasks can be performed, differing by the type of observation used as inputs. We showcase reconstruction from single-view, multi-view, noisy images, sparse pixels, and sparse depth data. These observations vary in the amount of information they provide for the scene and we show that our method can model the varying levels of inherent uncertainty associated with each task. Our experiments illustrate that this approach yields a comprehensive method capable of accurately predicting 3D structure from diverse types of observations.

Despite strong zero-shot performance, SAM is unreliable under domain shift due to Mask-level Confidence Confusion (MCC), where a single IoU-based mask score fails to reflect pixel-wise reliability near boundaries. Motivated by the contrast between texture-biased shortcuts in neural networks and shape-centric processing in human vision, we model out-of-domain variation as appearance shifts and non-rigid deformations that jointly stress calibration. We propose Segment Anything with Robust Uncertainty-Accuracy Correlation (RUAC) for robust pixel-wise uncertainty estimation under appearance and deformation shifts. RUAC adds a lightweight uncertainty head, trains it with a collaborative style-deformation attack that jointly perturbs texture and geometry, and applies Uncertainty-Accuracy Alignment to ensure uncertainty consistently highlights erroneous pixels even under adversarial perturbations. Across 23 zero-shot domains, RUAC improves segmentation quality and yields more faithful uncertainty with stronger uncertainty-accuracy correlation. Project page: https://hongyouzhou.github.io/ruac/.

Out-of-distribution (OOD) detection is essential for building reliable AI systems, as models that produce outputs for invalid inputs cannot be trusted. Although deep learning (DL) is often assumed to outperform traditional machine learning (ML), medical imaging data are typically acquired under standardized protocols, leading to relatively constrained image variability in OOD detection tasks. This motivates a direct comparison between ML and DL approaches in this setting. The two approaches are evaluated on open datasets comprising over 60,000 fundus and non-fundus images across multiple resolutions. Both approaches achieved an AUROC of 1.000 and accuracies between 0.999 and 1.000 on internal and external validation sets, showing comparable detection performance. The ML approach, however, exhibited substantially lower end-to-end latency while maintaining equivalent accuracy, indicating greater computational efficiency. These results suggest that for OOD detection tasks of limited visual complexity, lightweight ML approaches can achieve DL-level performance with significantly reduced computational cost, supporting practical real-world deployment.

Noisy labels are common in large-scale medical imaging datasets due to inter-observer variability and ambiguous cases. We propose a statistically grounded and task-agnostic framework, Standardized Loss Aggregation (SLA), for detecting noisy labels at the sample level. SLA quantifies label reliability by aggregating standardized fold-level validation losses across repeated cross-validation runs. This formulation generalizes discrete hard-counting schemes into a continuous estimator that captures both the frequency and magnitude of performance deviations, yielding interpretable and statistically stable noisiness scores. Experiments on a public fundus dataset demonstrate that SLA consistently outperforms the hard-counting baseline across all noise levels and converges substantially faster, especially under low noise ratios where subtle loss variations are informative. Samples with high SLA scores indicate potentially ambiguous or mislabeled cases, guiding efficient re-annotation and improving dataset reliability for any classification task.

World models for deformable objects should recover not only geometry and appearance, but also underlying physical dynamics, interaction grounding, and material behavior. Learning such a model from real videos is challenging because deformable linear, planar, and volumetric objects evolve under high-dimensional deformation, noisy interactions, and complex material response. The model must therefore infer a physical state from visual observations, roll it forward under new interactions, and render the resulting dynamics with high visual fidelity. We present DeformMaster, a video-derived interactive physics-neural world model that turns real interaction videos into an online interactive model of deformable objects within a unified dynamics-and-appearance framework. DeformMaster preserves structured physical rollout while using a neural residual to compensate for unmodeled effects, grounds sparse hand motion as distributed compliant actuator for hand-continuum interaction, represents material response with spatially varying constitutive experts, and drives high-fidelity 4D appearance from the predicted physical evolution. Experiments on real-world deformable-object sequences demonstrate DeformMaster's ability to roll out future dynamics and render dynamic appearance, outperforming state-of-the-art baselines while supporting novel action rollout, material-parameter variation, and dynamic novel-view synthesis. Project page: https://can-lee.github.io/deformmaster-web/

Ante-hoc interpretability methods based on prototypes provide highly accurate explanations by utilizing the intuitive "this looks like that" reasoning paradigm. On the other hand, post-hoc models can explain predictions for a single image without relying on an underlying dataset or requiring costly neural network retraining. Recent approaches successfully solve the retraining problem for prototype-based networks. However, they still face a fundamental limitation: they require access to a subset of data (e.g., a test or validation set) to search for and extract the visual prototypes. In this paper, we address this issue and introduce ProDG: Generative Prototypes for Data-Free Post-Hoc Explainability, a novel framework that leverages generative models to synthesize pure, high-fidelity prototypes directly from the frozen model's weights, completely eliminating the dependency on any external data. By establishing this new frontier in Data-Free XAI, ProDG unlocks robust visual interpretability for privacy-sensitive domains, where original data is strictly restricted or fundamentally inaccessible. Project page: https://github.com/piotr310100/ProDG

Semantic search of Earth observation archives remains challenging. Visual foundation models such as CLAY produce rich embeddings of satellite imagery but lack the natural-language grounding needed for intuitive query, and full contrastive training of a remote-sensing CLIP-style model requires paired data and compute that are unavailable at global scale. To allow natural language querying at global scales, we present GeoQuery, a zero-shot retrieval system that sidesteps data and compute constraints through a two-stage semantic and visual search, leveraging a natural language embedding of a subset (proxy) of global data. Rather than training a joint encoder, we generate language descriptions for a 100k proxy subset of global Sentinel-2 tiles and optimise the description-generation prompt so that distances in the resulting text-embedding space correlate with distances in the frozen CLAY visual-embedding space. Queries are resolved in two stages, with a text-similarity search over the proxy subset followed by a visual nearest-neighbour search over worldwide CLAY embeddings On 76 disaster-location queries covering UK floods, US wildfires, and US droughts, GeoQuery achieves 31.6\% accuracy within 50\,km, with the strongest performance on floods (50\% within 50\,km) where terrain features are well captured by RGB embeddings. Deployed within a crisis response system called \ECHO{}, GeoQuery identified vulnerable areas during Brisbane's 2025 Cyclone Alfred, with downstream flood simulations reproducing historical patterns. Prompt-aligned proxies offer a practical bridge between EO foundation models and operational retrieval when full contrastive training is out of reach.

We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language Model (MLLM) with a Multimodal Diffusion Transformer (MMDiT), allowing perception and generation to interact through a shared multimodal interface. Around this architecture, we build a scalable training recipe that combines unified instruction tuning, long-text rendering supervision, spatially grounded data, and both general and spatial editing signals. This design gives the model broad multimodal capability while strengthening geometry-aware reasoning and controllable visual synthesis. Experiments across understanding, generation, long-text rendering, and editing benchmarks show that JoyAI-Image achieves state-of-the-art or highly competitive performance. More importantly, the bidirectional loop between enhanced understanding, controllable spatial editing, and novel-view-assisted reasoning enables the model to move beyond general visual competence toward stronger spatial intelligence. These results suggest a promising path for unified visual models in downstream applications such as vision-language-action systems and world models.

While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A key bottleneck is the lack of a robust general reward model for all editing tasks. Existing edit reward models usually give overall scores without detailed checks, ignoring different instruction requirements and causing biased rewards. To address this, we argue that the key is to move from a simple scorer to a reasoning verifier. We introduce Edit-R1, a framework that builds a chain-of-thought (CoT) verifier-based reasoning reward model (RRM) and then leverages it for downstream image editing. The Edit-RRM breaks instructions into distinct principles, evaluates the edited image against each principle, and aggregates these checks into an interpretable, fine-grained reward. To build such an RRM, we first apply supervised fine-tuning (SFT) as a ``cold-start'' to generate CoT reward trajectories. Then, we introduce Group Contrastive Preference Optimization (GCPO), a reinforcement learning algorithm that leverages human pairwise preference data to reinforce our pointwise RRM. After building the RRM, we use GRPO to train editing models with this non-differentiable yet powerful reward model. Extensive experiments demonstrate that our Edit-RRM surpasses powerful VLMs such as Seed-1.5-VL and Seed-1.6-VL as an editing-specific reward model, and we observe a clear scaling trend, with performance consistently improving from 3B to 7B parameters. Moreover, Edit-R1 delivers gains to editing models like FLUX.1-kontext, highlighting its effectiveness in enhancing image editing.

Reasoning photo retouching has gained significant traction, requiring models to analyze image defects, give reasoning processes, and execute precise retouching enhancements. However, existing approaches often rely on non-differentiable external software, creating optimization barriers and suffering from high parameter redundancy and limited generalization. To address these challenges, we propose VeraRetouch, a lightweight and fully differentiable framework for multi-task photo retouching. We employ a 0.5B Vision-Language Model (VLM) as the central intelligence to formulate retouching plans based on instructions and scene semantics. Furthermore, we develop a fully differentiable Retouch Renderer that replaces external tools, enabling direct end-to-end pixel-level training through decoupled control latents for lighting, global color, and specific color adjustments. To overcome data scarcity, we introduce AetherRetouch-1M+, the first million-scale dataset for professional retouching, constructed via a new inverse degradation workflow. Furthermore, we propose DAPO-AE, a reinforcement learning post-training strategy that enhances autonomous aesthetic cognition. Extensive experiments demonstrate that VeraRetouch achieves state-of-the-art performance across multiple benchmarks while maintaining a significantly smaller footprint, enabling mobile deployment. Our code and models are publicly available at https://github.com/OpenVeraTeam/VeraRetouch.

Accurate diagnosis of pediatric brain tumors, starting with histopathology, presents unique challenges for deep learning, including severe data scarcity, class imbalance, and fine-grained morphologic overlap across diagnostically distinct subtypes. While pathology foundation models have advanced patch-level representation learning, their effective adaptation to weakly supervised pediatric brain tumor classification under limited data remains underexplored. In this work, we introduce an expert-guided contrastive fine-tuning framework for pediatric brain tumor diagnosis from whole-slide images (WSI). Our approach integrates contrastive learning into slide-level multiple instance learning (MIL) to explicitly regularize the geometry of slide-level representations during downstream fine-tuning. We propose both a general supervised contrastive setting and an expert-guided variant that incorporates clinically informed hard negatives targeting diagnostically confusable subtypes. Through comprehensive experiments on pediatric brain tumor WSI classification under realistic low-sample and class-imbalanced conditions, we demonstrate that contrastive fine-tuning yields measurable improvements in fine-grained diagnostic distinctions. Our experimental analyses reveal complementary strengths across different contrastive strategies, with expert-guided hard negatives promoting more compact intra-class representations and improved inter-class separation. This work highlights the importance of explicitly shaping slide-level representations for robust fine-grained classification in data-scarce pediatric pathology settings.

Accurate inter-vehicle distance estimation is a cornerstone of Advanced Driver Assistance Systems (ADAS) and autonomous driving. While LiDAR and radar provide high precision, their high cost prohibits widespread adoption in mass-market vehicles. Monocular camera-based estimation offers a low-cost alternative but suffers from fundamental scale ambiguity. Recent deep learning methods for monocular depth achieve impressive results yet require expensive supervised training, suffer from domain shift, and produce predictions that are difficult to certify for safety-critical deployment. This paper presents a framework that exploits the standardized typography of United States license plates as passive fiducial markers for metric ranging, resolving scale ambiguity through explicit geometric priors without any training data or active illumination. First, a four-method parallel plate detector achieves robust plate reading across the full automotive lighting range. Second, a three-stage state identification engine fusing optical character recognition text matching, multi-design color scoring, and a lightweight neural network classifier provides robust identification across all ambient conditions. Third, hybrid depth fusion with inverse-variance weighting and online scale alignment, combined with a one-dimensional constant-velocity Kalman filter, delivers smoothed distance, relative velocity, and time-to-collision for collision warning. Baseline validation on a controlled static dataset reproduces a 2.3% coefficient of variation in character height measurements and a 36% reduction in distance-estimate variance compared with plate-width methods from prior work.

Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information. Yet, they face significant challenges due to the high computational and memory demands of processing long sequences of vision tokens. Many existing methods rely on local heuristics, such as attention scores or token norms. However, these criteria suffer from positional bias and information dispersion, limiting their ability to preserve essential content at high pruning ratios and leading to performance degradation on visually detailed images. To address these issues, we propose SVD-Prune, a training-free, plug-and-play token pruning method based on Singular Value Decomposition. It decomposes the vision token feature matrix and selects the top-k tokens using statistical leverage scores, ensuring only tokens contributing most to the dominant global variance are preserved. Experiments show that SVD-Prune consistently outperforms prior pruning methods under extreme vision token budgets, maintaining strong performance even with 32 and 16 vision tokens.

We present a lightweight two-stage framework for low-light image enhancement (LLIE) that achieves competitive perceptual quality with significantly fewer parameters than existing methods. Our approach combines frozen algorithm-based preprocessing with a compact U-Net built entirely from depthwise-separable convolutions. The preprocessing normalizes the input distribution by providing complementary brightness-corrected views, enabling the trainable network to focus on residual color correction. Our method achieved 3rd place in the CVPR 2026 NTIRE Efficient Low-Light Image Enhancement Challenge. We further provide extended benchmarks and ablations to demonstrate the general effectiveness of our methods.

Registration between preoperative CT and intraoperative laparoscopic video plays a crucial role in augmented reality (AR) guidance for minimally invasive surgery. Learning-based methods have recently achieved registration errors comparable to optimization-based approaches while offering faster inference. However, many supervised methods produce coarse alignments that rely on additional optimization-based refinement, thereby increasing inference time. We present a discrete-action reinforcement learning (RL) framework that formulates CT-to-video registration as a sequential decision-making process. A shared feature encoder, warm-started from a supervised pose estimation network to provide stable geometric features and faster convergence, extracts representations from CT renderings and laparoscopic frames, while an RL policy head learns to choose rigid transformations along six degrees of freedom and to decide when to stop the iteration. Experiments on a public laparoscopic dataset demonstrated that our method achieved an average target registration error (TRE) of 15.70 mm, comparable to supervised approaches with optimization, while achieving faster convergence. The proposed RL-based formulation enables automated, efficient iterative registration without manually tuned step sizes or stopping criteria. This discrete framework provides a practical foundation for future continuous-action and deformable registration models in surgical AR applications.

Vision-Language Models (VLMs) are increasingly proposed for autonomous driving tasks, yet their performance on sequential driving scenes remains poorly characterized, particularly regarding how input configurations affect their capabilities. We introduce VENUSS (VLM Evaluation oN Understanding Sequential Scenes), a framework for systematic sensitivity analysis of VLM performance on sequential driving scenes, establishing baselines for future research. Building upon existing datasets, VENUSS extracts temporal sequences from driving videos, and generates structured evaluations across custom categories. By comparing 25+ existing VLMs across 2,600+ scenarios, we reveal how even top models achieve only 57% accuracy, not matching human performance under similar constraints (65%) and exposing significant capability gaps. Our analysis shows that VLMs excel with static object detection but struggle with understanding vehicle dynamics and temporal relations. VENUSS offers the first systematic sensitivity analysis of VLMs focused on how input image configurations - resolution, frame count, temporal intervals, spatial layouts, and presentation modes - affect performance on sequential driving scenes. Supplementary material available at https://TUM-AVS.github.io/VENUSS/.

Mathematical modeling of visual textures traces back to Julesz's intuition that texture perception in humans is based on local correlations between image features. An influential approach for texture analysis and generation generalizes this notion to linear correlations between the nonlinear features computed by convolutional neural networks (CNNs), compiled into Gram matrices. Given that CNNs are often used as models for the visual system, it is natural to ask whether such "texture representations" spontaneously align with the textures' perceptual content, and in particular whether those CNNs that are regarded as better models for the visual system also possess more human-like texture representations. Here we quantify the perceptual content captured by feature correlations computed for a diverse pool of CNNs, and we compare it to the models' perceptual alignment with the mammalian visual system as measured by Brain-Score. Surprisingly, we find that there is no connection between conventional measures of CNN quality as a model of the visual system and its alignment with human texture perception. We conclude that texture perception involves mechanisms that are distinct from those that are commonly modeled using approaches based on CNNs trained on object recognition, possibly depending on the integration of contextual information.

Recently, crowd-sourced online criminal investigations have used generative-AI to enhance low-quality visual evidence. In one high-profile case, social-media users circulated an "AI-unmasked" image of a federal agent involved in a fatal shooting, fueling a wide-spread misidentification. In response to this and similar incidents, we conducted a large-scale analysis evaluating the efficacy and risks of commercial AI-powered facial unmasking, specifically assessing whether the resulting faces can be reliably matched to true identities.

We present MeshTailor, the first mesh-native generative framework for synthesizing edge-aligned seams on 3D surfaces. Unlike prior optimization-based or extrinsic learning-based methods, MeshTailor operates directly on the mesh graph, eliminating projection artifacts and fragile snapping heuristics. We introduce ChainingSeams, a hierarchical serialization of the seam graph that orders chains from global structural cuts down to local details in a coarse-to-fine manner, and a dual-stream encoder that fuses topological and geometric context. Leveraging this hierarchical representation and dual-stream vertex embeddings, our MeshTailor Transformer utilizes an autoregressive pointer layer to trace seams vertex-by-vertex within local neighborhoods. Extensive evaluations show that MeshTailor produces more coherent and structurally regular seam layouts compared to recent optimization-based and learning-based baselines.

Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended reasoning modes, particularly in visual question answering (VQA) tasks. We identify attention dispersion as the underlying cause: during multi-step reasoning, the model's visual attention becomes scattered and drifts away from question-relevant regions, effectively "losing focus" on the visual input. To better understand this phenomenon, we analyze the attention maps of MLLMs and observe that reasoning prompts significantly reduce attention to regions critical for answering the question. We further find a strong correlation between the model's overall attention on image tokens and the spatial dispersiveness of its attention within the image. Leveraging this insight, we propose a training-free Visual Region-Guided Attention (VRGA) framework that selects visual heads based on an entropy-focus criterion and reweights their attention, effectively guiding the model to focus on question-relevant regions during reasoning. Extensive experiments on vision-language benchmarks demonstrate that our method effectively alleviates perceptual degradation, leading to improvements in visual grounding and reasoning accuracy while providing interpretable insights into how MLLMs process visual information.

Diabetic retinopathy (DR) and diabetic macular edema (DME) are leading causes of preventable blindness among working-age adults. Traditional approaches in the literature focus on standard color fundus photography (CFP) for the detection of these conditions. Nevertheless, recent ultra-widefield imaging (UWF) offers a significantly wider field of view in comparison to CFP. Motivated by this, the present study explores state-of-the-art deep learning (DL) methods and UWF imaging on three clinically relevant tasks: i) image quality assessment for UWF, ii) identification of referable diabetic retinopathy (RDR), and iii) identification of DME. Using the publicly available UWF4DR Challenge dataset, released as part of the MICCAI 2024 conference, we benchmark DL models in the spatial (RGB) and frequency domains, including popular convolutional neural networks (CNNs) as well as recent vision transformers (ViTs) and foundation models. In addition, we explore a final feature-level fusion to increase robustness. Finally, we also analyze the decisions of the DL models using Grad-CAM, increasing the explainability. Our proposal achieves consistently strong performance across all architectures, underscoring the competitiveness of emerging ViTs and foundation models and the promise of feature-level fusion and frequency-domain representations for UWF analysis.

Automated recognition of surgical phases and steps is a fundamental capability for intraoperative decision support, workflow automation, and skill assessment in robotic-assisted surgery. Existing approaches either depend on large-scale annotated surgical datasets or require expensive domain-specific pretraining on thousands of labeled videos, limiting their practical deployability across diverse robotic platforms and clinical environments. In this work, we propose TASOT (Text-Augmented Action Segmentation Optimal Transport), an annotation-free framework for surgical temporal segmentation that requires no task-specific annotations or surgical-domain pretraining. TASOT extends the Action Segmentation Optimal Transport (ASOT) formulation by incorporating temporally aligned textual descriptions generated directly from the input video, fusing visual and semantic cues within a unified unbalanced Gromov-Wasserstein optimal transport objective. Visual representations are extracted using DINOv3, while temporal captions produced by a vision-language model are encoded via CLIP and temporally aligned to individual frames, providing complementary semantic structure to the transport cost. We evaluate TASOT on three public surgical datasets and four benchmark settings spanning laparoscopic and robotic procedures, showing substantial improvements over the strongest zero-shot baselines: +18.9 F1 on Cholec80, +33.7 on AutoLaparo, +23.7 on StrasByPass70, and +4.5 on BernByPass70. These results suggest that fine-grained surgical workflow understanding in robotic settings can be achieved without manual training annotations or surgical-specific pretraining pipelines, offering a promising alternative for real-world robotic surgical systems.

Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveraging strong visual and language understanding from Vision-Language Models for general-purpose policy learning. Yet, the current VLA landscape remains fragmented and exploratory. Although many groups have proposed their own VLA models, inconsistencies in training protocols and evaluation settings make it difficult to identify which design choices truly matter. To bring structure to this evolving space, we reexamine the VLA design space under a unified framework and evaluation setup. Starting from a simple VLA baseline similar to RT-2, which is the origin of VLA, we systematically dissect design choices along three dimensions: foundational components, perception essentials, and action modelling perspectives. From this study, we distill 12 key findings that together form a practical recipe for building strong VLA models. The outcome of this exploration is a simple yet effective model, VLANeXt. It outperforms the state-of-the-art methods on the LIBERO and LIBERO-plus benchmarks and demonstrates strong performance in real-world experiments. We release a unified and easy-to-use codebase to reproduce our findings, explore the design space, and develop new VLA variants on top of a shared foundation. The codebase is available at https://github.com/DravenALG/VLANeXt.

Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret. Existing explainability methods rely on final-layer attributions, capture either local token-level attributions or global attention patterns without unification, and lack context-awareness of inter-token dependencies and structural components. They also fail to capture how relevance evolves across layers and how structural components shape decision-making. To address these limitations, we proposed the \textbf{Context-Aware Layer-wise Integrated Gradients (CA-LIG) Framework}, a unified hierarchical attribution framework that computes layer-wise Integrated Gradients within each Transformer block and fuses these token-level attributions with class-specific attention gradients. This integration yields signed, context-sensitive attribution maps that capture supportive and opposing evidence while tracing the hierarchical flow of relevance through the Transformer layers. We evaluate the CA-LIG Framework across diverse tasks, domains, and transformer model families, including sentiment analysis and long and multi-class document classification with BERT, hate speech detection in a low-resource language setting with XLM-R and AfroLM, and image classification with Masked Autoencoder vision Transformer model. Across all tasks and architectures, CA-LIG provides more faithful attributions, shows stronger sensitivity to contextual dependencies, and produces clearer, more semantically coherent visualizations than established explainability methods. These results indicate that CA-LIG provides a more comprehensive, context-aware, and reliable explanation of Transformer decision-making, advancing both the practical interpretability and conceptual understanding of deep neural models.

Multimodal Large Language Models have shown promising capabilities in bridging visual and textual reasoning, yet their reasoning capabilities in Open-Vocabulary Human-Object Interaction (OV-HOI) are limited by cross-modal hallucinations and limited viewpoints of images. To address this, we propose ImagineAgent, an agentic framework that integrates cognitive mapping, tool-augmented reinforcement learning (RL), and generative world modeling for robust OV-HOI understanding. Specifically, we first propose an innovative CoT dataset named hicodet-6K for supervised fine-tuning (SFT), which effectively bridges the perception-to-cognition gap by structuring perceived entities into interaction pairs for comprehensive predictions. Subsequently, we develop a multimodal tool library integrating online retrieval, image cropping, and generative modeling, enabling the agent to dynamically augment reasoning with domain-specific tools to resolve visual-semantic ambiguities and hallucinations during inference. Moreover, we incorporate a generative model to reconstruct alternative viewpoints, enabling the agent to 'imagine' under limited viewpoints. Finally, we propose a composite reward mechanism to jointly optimize prediction accuracy and tool efficiency. Evaluations on both SWIG-HOI and HICO-DET datasets demonstrate that our method achieves state-of-the-art performance while requiring merely 36.7% of the training data compared to existing methods, validating our robustness, empirical effectiveness and efficiency.

Adapting pre-trained vision models using parameter-efficient fine-tuning (PEFT) remains challenging, as it aims to achieve performance comparable to full fine-tuning using a minimal number of trainable parameters. When applied to complex dense prediction tasks, existing methods exhibit limitations, including input-agnostic modeling and redundant cross-layer representations. To this end, we propose ParaX, a new adapter-style method featuring a simple mixture-of-experts (MoE) architecture. Specifically, we introduce shared expert centers, where each expert is a trainable parameter matrix. During a feedforward pass, each ParaX module in the network dynamically generates weight matrices tailored for the current module via a simple dynamic parameter routing mechanism, which selectively aggregates parameter matrices in the corresponding expert center. Dynamic weight matrices in ParaX modules facilitate low-rank adaptation in an input-dependent manner, thus generating more customized and powerful feature representations. Moreover, since ParaX modules across multiple network layers share the same expert center, they improve feature diversity by promoting implicit cross-layer feature interaction. Extensive experimental results demonstrate the superiority of ParaX across diverse visual recognition tasks. Code is publicly released at: https://github.com/LMMMEng/ParaX.

We introduce PerpetualWonder, a hybrid generative simulator that enables long-horizon, action-conditioned 4D scene generation from a single image. Current works fail at this task because their physical state is decoupled from their visual representation, which prevents generative refinements to update the underlying physics for subsequent interactions. PerpetualWonder solves this by introducing the first true closed-loop system. It features a novel unified representation that creates a bidirectional link between the physical state and visual primitives, allowing generative refinements to correct both the dynamics and appearance. It also introduces a robust update mechanism that gathers supervision from multiple viewpoints to resolve optimization ambiguity. Experiments demonstrate that from a single image, PerpetualWonder can successfully simulate complex, multi-step interactions from long-horizon actions, maintaining physical plausibility and visual consistency.

Recently, Diffusion Transformers (DiTs) have emerged in Real-World Image Super-Resolution (Real-ISR) to generate high-quality textures, yet their heavy inference burden hinders real-world deployment. While Post-Training Quantization (PTQ) is a promising solution for acceleration, existing methods in super-resolution mostly focus on U-Net architectures, whereas generic DiT quantization is typically designed for text-to-image tasks. Directly applying these methods to DiT-based super-resolution models leads to severe degradation of local textures. Therefore, we propose Q-DiT4SR, the first PTQ framework specifically tailored for DiT-based Real-ISR. We propose H-SVD, a hierarchical SVD that integrates a global low-rank branch with a local block-wise rank-1 branch under a matched parameter budget. We further propose Variance-aware Spatio-Temporal Mixed Precision: VaSMP allocates cross-layer weight bit-widths in a data-free manner based on rate-distortion theory, while VaTMP schedules intra-layer activation precision across diffusion timesteps via dynamic programming (DP) with minimal calibration. Experiments on multiple real-world datasets demonstrate that our Q-DiT4SR achieves SOTA performance under both W4A6 and W4A4 settings. Notably, the W4A4 quantization configuration reduces model size by 5.8$\times$ and computational operations by 6.14$\times$. Our code and models will be available at https://github.com/xunzhang1128/Q-DiT4SR.

Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additional training on augmented data, which is computationally expensive and still limited in capturing fine-grained motion. In this work, we present self-refining video sampling, a simple method that uses a pre-trained video generator trained on large-scale datasets as its own self-refiner. By interpreting the generator as a denoising autoencoder, we enable iterative inner-loop refinement at inference time without any external verifier or additional training. We further introduce an uncertainty-aware refinement strategy that selectively refines regions based on self-consistency, which prevents artifacts caused by over-refinement. Experiments on state-of-the-art video generators demonstrate significant improvements in motion coherence and physics alignment, achieving over 70% human preference compared to the default sampler and guidance-based sampler.

Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is inefficient and often yields ambiguous global supervision. To address these limitations, we propose LocalDPO, a novel post-training framework that constructs localized preference pairs from real videos and optimizes alignment at the spatio-temporal region level. We design an automated pipeline to efficiently collect preference pair data that generates preference pairs with a single inference per prompt, eliminating the need for external critic models or manual annotation. Specifically, we treat high-quality real videos as positive samples and generate corresponding negatives by locally corrupting them with random spatio-temporal masks and restoring only the masked regions using the frozen base model. During training, we introduce a region-aware DPO loss that restricts preference learning to corrupted areas for rapid convergence. Experiments on Wan2.1 and CogVideoX demonstrate that LocalDPO consistently improves video fidelity, temporal coherence and human preference scores over other post-training approaches, establishing a more efficient and fine-grained paradigm for video generator alignment.The code is available at https://github.com/1170300714/Local-DPO.

Intraoperative navigation in spine surgery demands millimeter-level accuracy. Currently, this is achieved through radiation-intensive intraoperative imaging and bone-anchored markers that are invasive and disrupt surgical workflow. Markerless RGB-D registration methods offer a promising alternative. However, existing approaches rely on weak segmentation labels to isolate relevant anatomical structures, potentially propagating errors through the registration process. We present End2Reg, an end-to-end deep learning framework that jointly optimizes segmentation and registration, eliminating the need for segmentation labels and manual steps. The network learns task-specific segmentation masks optimized for registration, guided solely by the registration objective without explicit segmentation supervision. End2Reg achieves state-of-the-art performance on ex- and in-vivo benchmarks, reducing median Target Registration Error by 32% and mean Root Mean Square Error by 61%, while maintaining robust performance under partial occlusions. Ablation results confirm that end-to-end optimization significantly improves registration accuracy. Overall, End2Reg advances towards fully automatic, markerless intraoperative navigation. Code and interactive visualizations are available at: https://lorenzopettinari.github.io/end-2-reg/.

Deep learning-based methods have recently achieved significant success in image reconstruction problems. However, challenges have emerged, as these methods may generate unrealistic artifacts or hallucinations, which can interfere with analysis in safety-critical scenarios. This paper introduces a framework for quantifying and characterizing hallucinated artifacts in image reconstruction models. The proposed method, termed the Conformal Hallucination Estimation Metric (CHEM), enables the identification of hallucination-prone regions in model predictions. It leverages wavelet and shearlet representations to localize such regions at the level of image features, and uses conformalized quantile regression to assess hallucination levels in a distribution-free manner. A theoretical analysis is provided, characterizing the sensitivity of CHEM to hallucinated artifacts and its relationship to the mean squared error. Building on these insights and adopting a viewpoint grounded in approximation theory, we investigate why U-shaped networks, widely used architectures for image reconstruction, tend to hallucination-prone predictions. We assess the effectiveness of the proposed approach on astronomical image deconvolution using the CANDELS dataset with architectures such as U-Net, SwinUNet, and Learnlets, and on natural image super-resolution using the DIV2K dataset with models such as DRUNet, Unfolded DRS, RAM, and DPS.

Structurally repetitive environments produce visually plausible but aliased LiDAR loop candidates that can destabilize pose-graph optimization when admitted as loop factors. We propose Query-Calibrated Segmental Admission (QCSA), a descriptor-agnostic sparse loop-admission policy for graph-stability-oriented insertion. The policy scores short descriptor segments against hard negatives, calibrates which query-level segment hypotheses reach geometry, and inserts representative pairs validated by Generalized Iterative Closest Point (G-ICP). We evaluate it on the SNU Library Dataset (SNULib) and HeLiPR overlap routes. Aggregated over seven LiDAR descriptor families on SNULib, QCSA reduces inserted loop factors by 3.8 times, raises factor precision from 0.542 to 0.717, and sharply lowers false admissions per query group. With this sparser graph, it maintains comparable mean absolute trajectory error (ATE) and substantially reduces worst-sequence ATE versus dense Top1+G-ICP, from 1.064 to 0.778 m. The aggregate mean and worst-sequence ATE remain lower than the odometry-only reference. Under a matched factor budget, QCSA also attains lower trajectory error than SeqSLAM and sparse Top1+G-ICP selections. Fixed-transfer validation on HeLiPR, with no route-specific tuning, likewise suppresses hard-negative admissions. These results support the proposed admission layer for aliasing-heavy simultaneous localization and mapping (SLAM). Our implementation and dataset will be released at: https://github.com/wanderingcar/snu_library_dataset.

The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate. This visual dimension is critical for advanced applications like flexible content generation and precise, program-driven editing of visualizations. However, progress has been impeded by the scarcity of high-quality multimodal code data, a bottleneck stemming from challenges in synthesis and quality assessment. To address these challenges, we make contributions from both a data and modeling perspective. We first introduce a complete synthesis toolkit that leverages reciprocal synergies between data modalities to efficiently produce a large-scale, high-quality corpus spanning from standard charts to complex interactive web UIs and code-driven animations. Leveraging this toolkit, we construct JanusCode-800K, the largest multimodal code corpus to date. This powers the training of our models, JanusCoder and JanusCoderV, which establish a visual-programmatic interface for generating code from textual instructions, visual inputs, or a combination of both. Our unified model is a departure from existing approaches that build specialized models for isolated tasks. Extensive experiments on both text-centric and vision-centric coding tasks demonstrate the superior performance of the JanusCoder series, with our 7B to 14B scale models approaching or even exceeding the performance of commercial models. Furthermore, extensive analysis provides key insights into harmonizing programmatic logic with its visual expression. Our code and checkpoints are available at https://github.com/InternLM/JanusCoder.