Domain adaptation remains a central challenge in 3D vision, especially for multimodal foundation models that align 3D point clouds with visual and textual data. While these models demonstrate strong general capabilities, adapting them to downstream domains with limited data often leads to overfitting and catastrophic forgetting. To address this, we introduce ReFine3D, a regularized fine-tuning framework designed for domain-generalizable tuning of 3D large multimodal models (LMMs). ReFine3D combines selective layer tuning with two targeted regularization strategies: multi-view consistency across augmented point clouds and text diversity through synonym-based prompts generated by large language models. Additionally, we incorporate point-rendered vision supervision and a test-time augmentation mechanism with confidence-based aggregation to further enhance robustness. Extensive experiments across different 3D domain generalization benchmarks show that ReFine3D improves base-to-novel class generalization by 1.36%, cross-dataset transfer by 2.43%, robustness to corruption by 1.80%, and few-shot accuracy by up to 3.11%, outperforming prior state-of-the-art methods with minimal added computational overhead.

Traditional image captioning methods often struggle to generate comprehensive, context-rich descriptions, especially for details not directly observable from visual cues. To overcome this, we propose a novel retrieval-augmented image captioning framework that generates captions with deeper insights, such as object attributes, event context, and underlying significance, by leveraging external knowledge. Our approach features a hierarchical multi-modal article retrieval mechanism that moves beyond monolithic text entities. This retrieval considers article structure-aware features, including weighted textual components (e.g., headlines, body sections) and visual placement patterns, alongside multi-faceted similarity computations (content--visual, visual--visual, and discourse positioning). A subsequent contextual relevance refinement stage further enhances the retrieved information. The retrieved articles then serve as the knowledge base for caption generation: first, a VLM generates a concise image description; second, we segment relevant information from the retrieved articles based on this description; and finally, an LLM utilizes both the description and extracted knowledge to generate a comprehensive, contextually detailed caption. We participated in the ACM Multimedia EVENTA 2025 Challenge and achieved 5th place with an overall score of 0.2824 on the private test set of the OpenEvent-V1 dataset. Source code is publicly released at https://github.com/mf0212/EVENTA-Challange.

Despite their remarkable performance, Vision Language Models (VLMs) incur substantial computational overhead due to the large number of visual tokens. While diversity maximization has become a dominant strategy for token reduction, existing methods rely on cosine-based normalized similarity that discards magnitude information, failing to faithfully approximate the original feature representation and leading to suboptimal performance, particularly on compositional multi-skill reasoning tasks. In this paper, we introduce SPARE, a subspace reconstruction method that reformulates token pruning as a column subset selection problem and explicitly minimizes reconstruction error. By iteratively selecting tokens with large projection residuals, SPARE performs reconstruction-driven pruning beyond angular diversity. Moreover, we reveal a counterintuitive anti-relevance phenomenon: tokens with lower image-text relevance score can better preserve contextual information. Based on this finding, we incorporate anti-relevance into SPARE as an additional selection criterion to promote context-aware token selection. Extensive experiments across multiple VLMs and benchmarks demonstrate that SPARE consistently achieves state-of-the-art performance, with strong gains on compositional tasks. When applied to LLaVA, SPARE removes up to 94% of visual tokens while retaining 95% of the baseline performance, all in a fully training-free manner.

Multimodal Information Extraction (MIE)-covering tasks such as Multimodal Named Entity Recognition (MNER), Relation Extraction (MRE), and Event Extraction (MEE)-is essential for understanding multimedia content but remains constrained by severe data scarcity. Although data augmentation is a promising remedy, existing approaches are impeded by coarse cross-modal alignment and fragmented, task-specific designs that fail to exploit shared semantic knowledge. To overcome these limitations, we introduce Semantic Anchor-aligned Multimodal Augmentation (SAMA), a unified framework for generating high-fidelity, task-aware synthetic data. SAMA constructs structured semantic anchors from ground-truth labels to guide a Collaborative Multi-Experts Multimodal Large Language Model (CME-MLLM), which integrates a Universal Adapter for shared semantics with Task-Specific Adapters to produce diverse yet constraint-compliant textual samples. For image synthesis, SAMA employs an Anchor-Preserving Diffusion mechanism that uses anchor-weighted prompts and latent conditioning to maintain critical semantic anchors while diversifying visual contexts. To eliminate the need for manual verification, SAMA further introduces a Dual-Constraint Filtering module that selects synthetic samples based on both cross-modal consistency and anchor fidelity. Extensive experiments across benchmark datasets for MNER, MRE, and MEE demonstrate that SAMA consistently outperforms state-of-the-art augmentation baselines under both fully supervised and low-resource settings, underscoring its versatility, robustness, and effectiveness.

Vision-language models (VLMs) are rapidly advancing toward sophisticated grounded structured visual reasoning. Training models for such advanced capabilities demands a new genre of data that seamlessly unifies spatial coordinates, open-vocabulary descriptions, structured attributes, and topological relationships into a singular representation. However, existing data annotation tools fundamentally fail to meet these intricate demands, suffering from three systematic bottlenecks: limited expressiveness, severe annotation-training decoupling, and poor data reusability. To bridge this infrastructure gap, we introduce an open-source annotation tool, ScreenAnnotator. First, we define a unified annotation atom schema that binds spatial, semantic, and structural primitives into a single unit. Second, we implement an on-policy annotation loop embedded with a Bayesian Annotation Verifier (BAV). Finally, we design a template-driven multi-task data synthesis process dynamically transforms static atoms into diverse multi-dimensional reasoning tasks, eliminating redundant re-annotation. The on-policy loop drives the annotation accept rate to nearly 100% on flowcharts and 77% on GUI screenshots, while steadily reducing per-image annotation time as labeled data accumulate. In the flowchart scenario, fine-tuning a VLM yields 76.1% average accuracy, which is a 35.1% point absolute gain. Our code is available at: https://github.com/WnQinm/Annotator.

Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly an order-of-magnitude inference cost from multi-step diffusion. We find this cost yields limited direct benefit. On ThinkMorph, removing or noising VTs barely changes accuracy across nine benchmarks. Once rendered, attention concentrates on the VT regardless of content. Yet a KL diagnostic shows that conditioning on a privileged VT trace shifts the model's completion distribution. This suggests the generation pathway encodes useful reasoning beyond the rendered pixels. Motivated by this gap, we propose Visual On-Policy Self-Distillation(Visual-OPSD). Teacher and student share identical weights but differ in context: the teacher sees privileged VTs while the student sees only the question. Token-level JSD distillation on on-policy student trajectories transfers the teacher's reasoning to a text-only student. Across nine benchmarks, Visual-OPSD improves over its generative teacher by $+3.40$pp with $14.3\times$ speedup (10.0s vs. 142.8s per sample) and outperforms same-scale VLMs by $+63.83$pp on VSP. A Gaussian-noise control ($+0.40$pp vs. $+10.28$pp for real VTs) and $58.4\%$ closure of the KL gap confirm that gains come from the semantic content of the generation pathway.

Composed image retrieval (CIR) uses a reference image and a text modification to search for a target image. However, such queries often describe several possible images rather than one exact target, making the user's intent ambiguous. Recent methods address this by using conformal prediction to estimate ambiguity and by asking users clarifying text questions. However, these methods have two limitations: their coverage guarantee only holds at the first interaction, and text questions are often insufficient for resolving fine-grained visual differences such as appearance, attributes, or viewpoint. We propose CLARA, a clarification framework that resolves ambiguity by showing users a small panel of visual alternatives. Instead of answering text questions, the user simply selects the prototype image closest to the intended target. This provides a direct visual signal and avoids relying on a model to predict the user's answer. To maintain valid conformal guarantees across multiple interaction rounds, CLARA reweights calibration using the likelihood ratio induced by the user's selection. The displayed prototypes are also constrained to represent the current candidate set and are snapped to real corpus images, ensuring that generated images cannot artificially improve coverage. Experiments on open-domain and fashion benchmarks show that CLARA matches single-turn state-of-the-art retrieval performance, maintains nominal coverage across interaction rounds, and finds the intended target in fewer rounds than strong text-question baselines. Its advantage is especially clear when ambiguity involves viewpoint or fine-grained attributes, where visual clarification is more effective than textual questioning.

Large Vision and Language Models (LVLMs) have advanced rapidly, yet European Portuguese (pt-PT) remains systematically underserved by existing open-source multimodal models, which either conflate it with Brazilian Portuguese or severely under-represent it in their training data mixes. We introduce AMALIA-VL, the first open-source instruction-tuned LVLM built natively for pt-PT, pairing a high-resolution vision encoder with dynamic image tiling and a fully open pt-PT-optimized language model via a learned connector. We contribute with a purposefully designed three-stage training process - vision-language alignment, general visual instruction tuning, and preference optimization - together with a pt-PT-centric multimodal data mix combining curated and translated public datasets with novel datasets that address the near-total absence of European Portuguese multimodal resources. Our evaluation shows that AMALIA-VL establishes a strong baseline for open-source pt-PT LVLMs.We will release model weights, training data, and construction pipelines along with machine-translated pt-PT evaluation benchmarks to help democratize pt-PT LVLM development.

Visual Question Answering (VQA) in the Remote Sensing (RS) domain presents unique challenges due to the high resolution, multi scale object distribution, and semantic complexity of aerial imagery. While general domain Foundation Models have achieved remarkable success, their direct application to RSVQA is hindered by massive domain shifts and the computationally prohibitive nature of full fine tuning. This study presents a comparative analysis of RS Adapter, a Parameter Efficient Fine Tuning (PEFT) strategy, applied across three distinct Vision Language Model (VLM) architectures: the Dual Encoder CLIP, the Encoder Decoder BLIP, and the Hybrid FLAVA. We introduce a unified architectural surgery pipeline that injects lightweight bottleneck adapters into the attention and MLP layers of frozen backbones, enabling rapid adaptation with less than 5 percent of trainable parameters. Experimental results on the high resolution RSVQA x dataset demonstrate that while all adapted models achieve convergence, the Hybrid FLAVA architecture offers a superior balance of multimodal reasoning and retrieval capabilities compared to its unimodal counterparts. Our findings establish a new baseline for resource efficient VQA in disaster assessment and urban monitoring.

Deploying multimodal foundation models as closed-loop policies increasingly requires conditioning actions on observations that are no longer visible. However, existing benchmarks either expose the full state, conflate hidden-state reconstruction with other agent skills, or test recall only after an episode has ended. We introduce RNG-Bench (Reconstructive Non-Markov Games), a benchmark suite designed to isolate a base model's ability to reconstruct past observations and act on them during multi-step interaction. RNG-Bench includes two complementary games: Matching Pairs, where card identities briefly revealed at specific locations must later be recalled, and 3D Maze, where egocentric views must be integrated into a spatial map. Both games are evaluated under a unified harness with three controlled difficulty axes: grid size, visual pattern, and observation modality. The benchmark further introduces a head-to-head duel protocol to control for instance-level variance and a Memory Gap metric that disentangles forgetting from poor action selection. The hardest configurations require contexts of roughly 128K tokens and 350 image inputs per episode, and remain far from saturated by frontier MLLMs. Memory Gap analysis shows that most residual errors stem from forgetting earlier observations rather than from suboptimal decision making. Finally, fine-tuning Qwen3.5-9B on optimal-policy rollouts and filtered model demonstrations improves performance on RNG-Bench and transfers to existing benchmarks without degrading general multimodal capability.

Passive models for long video understanding typically rely on a "watch-it-all" paradigm, processing frames uniformly regardless of query difficulty, causing computational cost to grow with video duration. Although interactive frameworks have emerged, they often rely on global pre-scanning, and their context cost still scales with video length. We propose OmniAgent, the first native omni-modal agent that formulates video understanding as a POMDP-based iterative Observation-Thought-Action cycle. OmniAgent executes on-demand actions to selectively distill audio-visual cues into a persistent textual memory, effectively decoupling reasoning complexity from raw video duration. To operationalize this, we introduce (1) Agentic Supervised Fine-Tuning to bootstrap native active perception via best-of-N trajectory synthesis with dual-stage quality control, and (2) Agentic Reinforcement Learning with TAURA (Turn-aware Adaptive Uncertainty Rescaled Advantage), which leverages turn-level entropy to steer credit assignment toward pivotal discovery turns. Crucially, OmniAgent exhibits positive test-time scaling, where performance improves as the number of reasoning turns increases, validating the efficacy of active perception. Empirical results across ten benchmarks (e.g., VideoMME, LVBench) demonstrate that OmniAgent achieves state-of-the-art performance among open-source models. Notably, on LVBench, our 7B agent outperforms the 10$\times$ larger Qwen2.5-VL-72B (50.5% vs. 47.3%).

On-policy self-distillation (OPSD) trains a model on its own rollouts and uses a frozen copy to provide dense token-level targets conditioned on a reference target. This works well for LLM reasoning, but a direct extension to multimodal large language models (MLLMs) can create a shortcut: the privileged target may guide tokens mainly based on the text reference target rather than the image. We propose ViGOS, a visually grounded OPSD framework for MLLM post-training. The student first writes a visual description and then reasons toward the final answer. For valid rollouts, an image-only perception teacher supervises the description, while a privileged reasoning teacher supervises the reasoning and final answer on the same student prefix. A reference teacher is used only for invalid rollouts to recover the output format. Across general vision-language, expert reasoning, visual math, spatial grounding, and visual-language-prior benchmarks, ViGOS keeps the main benefits of OPSD and improves image-grounded behavior in shortcut-prone settings.

A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we introduce a diagnostic framework centered on the Linear Separability Ceiling (LSC), the performance achievable by a linear classifier on a VLM's raw visual embeddings. Applying this framework to state-of-the-art VLMs, we uncover a pervasive ''alignment gap'', where most models fail to generatively outperform the linear separability of their representations. We find that the few models surpassing this ceiling do so via two mechanisms: by further refining visual representations into a more linearly separable format or by executing non-linear decision logic. We demonstrate that this bottleneck is not a fundamental limitation but a solvable visual alignment issue. Our method augments standard next-token prediction with a contrastive objective to restructure the visual manifold into a more one-dimensionally linear geometry, improving image-to-image comparison and enabling models to significantly surpass the LSC on abstract compositional reasoning tasks.

Recent advancements in Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision-language tasks, yet the quadratic computational complexity arising from the vast number of visual tokens incurs significant memory and latency bottlenecks. While visual token reduction (VTR) strategies have been explored to mitigate this burden, existing methods overlook the positional and attentional consistency between the full and reduced sequences, resulting in a distorted representation. To this end, we propose RESTORE, a novel VTR framework that rectifies the positional and attentional distortions while maintaining efficiency. Specifically, we present a simple yet effective calibration method that restores lost visual attention by augmenting attention weights based on relative distances. We also introduce a distinctive anchor selection for token merging to mitigate information loss during feature averaging. Experimental results on multiple benchmarks demonstrate that our method consistently improves the accuracy of various reduction methods, achieving state-of-the-art performance while maintaining computational efficiency. Project page is available at https://cvlab.yonsei.ac.kr/projects/RESTORE

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI -- effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3.

Vision-language models (VLMs), like human learners, are frequently exposed to new visual concepts, but how they map novel visual references to language after exposure remains largely underexplored, particularly when those references contradict prior knowledge from pre-training. To study this, we present the Novel Visual References Dataset (NVRD): 19,176 images spanning 90 visual concepts across different levels of visual novelty, each with up to 20 increasingly perturbed versions of the original object to probe generalization. Unlike prior work on visual augmentations of familiar concepts, NVRD comprises entirely novel, open-ended stimuli constructed from scratch, mirroring how humans encounter genuinely new concepts. We evaluate 3 open- and 2 closed-source models alongside 2,400 human judgments for direct human-model comparison, and find that (i) models struggle to acquire novel concepts in-context when they contradict prior knowledge, and (ii) while models and humans show correlated sensitivity to visual perturbations, models significantly overgeneralize, extending learned labels to stimuli that humans reject. We contribute NVRD as a corpus and benchmark for research on visual concept learning in both humans and machines.

Although Multimodal Large Language Models (MLLMs) demonstrate strong omni-modal perception, their ability to forecast future events from audio-visual cues remains largely unexplored, as existing benchmarks focus mainly on retrospective understanding. To bridge this gap, we introduce FutureOmni, the first benchmark designed to evaluate omni-modal future forecasting from audio-visual environments. The evaluated models are required to perform cross-modal causal and temporal reasoning, as well as effectively leverage internal knowledge to predict future events. FutureOmni is constructed via a scalable LLM-assisted, human-in-the-loop pipeline and contains 919 videos and 1,034 multiple-choice QA pairs across 8 primary domains. Evaluations on 13 omni-modal and 7 video-only models show that current systems struggle with audio-visual future prediction, particularly in speech-heavy scenarios, with the best accuracy of 64.8% achieved by Gemini 3 Flash. To mitigate this limitation, we curate a 7K-sample instruction-tuning dataset and propose an Omni-Modal Future Forecasting (OFF) training strategy. Evaluations on FutureOmni and popular audio-visual and video-only benchmarks demonstrate that OFF enhances future forecasting and generalization. We publicly release all code (https://github.com/OpenMOSS/FutureOmni) and datasets (https://huggingface.co/datasets/OpenMOSS-Team/FutureOmni).

LiDAR place recognition determines one's position on a prior point cloud map. The most studied ground-level LiDAR place recognition suffers from pre-visit requirements, incomplete coverage, and limited perspectives. Using pre-acquired, full-coverage Airborne Laser Scanning (ALS) data as an aerial prior map overcomes these drawbacks, making cross-view place recognition necessary and advantageous. However, aerial-ground LiDAR place recognition faces significant challenges, including the domain gap between aerial and ground point clouds, and false positives during initial retrieval. To address these challenges, we present a novel retrieval and re-ranking framework for aerial-ground LiDAR place recognition. Based on the priors that neighboring point cloud patches share similar semantics with anchor patch, our retrieval network introduces patch-level self-supervised learning modules at multiple scales and integrates with scene-level learning to improve global feature discriminativeness between aerial and ground point clouds. Furthermore, leveraging the structured spatial distribution of ALS point clouds, we introduce an Expanded Reciprocal (ER) re-ranking algorithm to exploit neighborhood information maximally and refine each feature based on neighbor features, which are then used to update the similarity matrix for final ranking. Extensive experiments demonstrate that our retrieval network outperforms existing state-of-the-art (SOTA) methods, achieving a 9.8\% improvement in average Recall@1 and a 3.2\% improvement in average Recall@1\% on the CS-Urban-Scenes, while also showing the best performance on the CS-Campus3D dataset. Additionally, our ER re-ranking algorithm further boosts the average Recall@1 by 4.9\% on CS-Campus3D and 10.2\% on CS-Urban-Scenes without additional training.

Scalable, all-weather place recognition increasingly relies on heterogeneous radar place recognition to bridge diverse hardware platforms. A notable application is matching queries from cost-effective 4D automotive radars against high-fidelity reference maps built by dense spinning radars. This process is fundamentally limited by the extreme sparsity (and narrow field-of-view) of the 4D sensor, which captures only a fraction of the structural density present in the spinning radar database. Prior efforts address this issue by unifying different radar signals. That is, projecting both signals into a common representational space. Yet, they suffer performance degradation in multi-session environments. In this paper, we propose spatially-stratified distillation (SSD); a strategy that replaces standard uniform distillation with an asymmetric spatial alignment derived directly from physical radar returns. In regions where both radars exhibit overlapping returns, SSD enforces strong feature alignment. Crucially, in sparse regions where the 4D student lacks returns but the teacher contains valid structure within the shared field of view, SSD applies heavily discounted distillation weights. Extensive evaluations of the recent HeRCULES dataset demonstrate that SSD significantly outperforms prior place recognition methods, achieving state-of-the-art results on its challenging dynamic sequences.

Pedestrian trajectory prediction from an ego-centric camera is challenging since it depends on complex interactions with vehicles and scene context, as well as the intention of the pedestrian. By modelling correlation and intent from the historical and future trajectories of the pedestrian, it will usually result in a multimodal (i.e. multiple modes) distribution. Existing stochastic predictors often sample multiple futures from a single unimodal distribution, which can yield sub-optimal 'mixed-mode' trajectories that lie between distinct motion patterns and become implausible in real scenes. In this paper, we propose MMPM, a mode-aware framework that separately models future trajectory distributions into semantically meaningful modes based on the pedestrian's crossing behavior. MMPM consists of two modules: behavior-aware Pedestrian Interaction Module (PIM) that jointly captures pedestrian-vehicle and pedestrian-environment interactions by introducing gaze, head and hand gesture, and a CVAE-based Mode-aware Trajectory Predictor (MTP) module to model the future trajectory distributions on two modes, crossing and non-crossing the road, separately. A query-based decoder further enforces mode consistency during decoding. Experiments on PIE and JAAD datasets show that our method surpasses state-of-the-art baselines. Our proposed MTP is model-agnostic, which can be integrated into existing frameworks such as BiTrap-NP and SGNet-ED to further improve future trajectory prediction performance. We additionally introduce a data-driven validation protocol that matches predictions to spatio-temporally consistent ground-truth trajectories, demonstrating improved frame-wise displacement errors over previous work.

Training generalist Vision-Language-Action(VLA) models typically requires massive, diverse robotic datasets with high-fidelity action annotations. While egocentric human manipulation videos are abundant and capture significant environmental diversity, the absence of action labels makes them difficult to use in conventional training paradigms. To address this, we propose a latent-action-based framework designed to extract general action priors from unlabeled human videos. The architecture features a Hybrid Disentangled VQ-VAE that decouples motion dynamics from environmental backgrounds through physical masks, enabling the construction of a cross-embodiment action codebook. By pre-training on human videos with the codebook, the VLM backbone learns deep representations of action intent. For adaptation to specific embodiments, we introduce an intent-perception decoupling strategy where the VLM predicts the action intent while a separate frozen visual encoder provides state-specific features to the action expert, thereby reducing action hallucinations. Results in simulation and real-world environments show that our method, pre-trained exclusively on unlabeled human videos, performs competitively with state-of-the-art VLA models trained on massive annotated datasets, requiring only 50 trajectories for downstream adaptation.

Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable alternative to costly real-world experimentation by generating action-consistent video rollouts. However, persistent world modeling remains challenging in manipulation: frequent end-effector occlusions and rapid wrist-camera motion make the current observation insufficient for predicting future views, causing models to forget or hallucinate scene details seen in earlier frames. Existing memory retrieval strategies often fail to identify informative history in dynamic manipulation scenarios. To address this limitation, we propose Mem-World, a memory-augmented multi-view action-conditioned world model. At its core, we present W-VMem, a 4D wrist-view-centered surfel-indexed memory that anchors historical observations to temporally evolving surface elements. By explicitly modeling when and where scene elements are observed, W-VMem enables geometry-aware retrieval of relevant history frames conditioned on future actions. During generation, relevant history frames are selected via surfel-based rendering and scoring, providing informative and non-redundant context for prediction. Extensive experiments show that Mem-World generates persistent rollouts in complex manipulation scenarios, enables more reliable policy evaluation than Ctrl-World, improving the Pearson correlation with real-world performance by 14.5\%, and supports effective policy improvement through synthetic data generation, increasing success rates from 58\% to 72\% on long-horizon tasks.

Cloud-hosted large multimodal models (LMMs) can provide strong open-vocabulary perception for Vehicle-to-Everything systems, but naively transmitting full-resolution frames from edge to cloud causes severe communication overhead and high cloud-side prefill latency. We present CABLE, a cloud-assisted bandwidth-efficient LMM-based encoding framework for edge-cloud perception. CABLE propagates the previous cloud segmentation mask on the edge using ego-motion compensation, refines it with residual-motion cues, and consolidates disconnected regions via a corridor envelope to form a robust region of interest (ROI). Only ROI-masked images are uploaded, while the cloud segmentation output is fed back as the prior for the next frame, forming a mask-to-ROI-to-LMM feedback loop. Experiments on five datasets (nuScenes, WOD-ZB, Waymo, KITTI, and CADC) show consistent communication savings while largely preserving perception, achieving $73$--$87\%$ ROI pixel-coverage reduction with $5$--$8\times$ estimated LMM prefill speedup at a modest detection-quality trade-off relative to full-frame inference.

Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating policy rollouts. Autoregressive rollouts accumulate compounding errors, observations across multiple camera views must remain mutually consistent, and the evaluator must generalize to policies whose behaviors lie outside the training distribution. We address these challenges with SC3-Eval, a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator by enforcing three complementary forms of consistency. First, forward-inverse dynamics consistency jointly trains the model to predict frames from actions and to recover actions from frames, anchoring generated rollouts to a physically plausible action manifold and counteracting the drift a forward-only model cannot penalize. Second, cross-view consistency trains the model to inpaint each camera view from the other, keeping the multi-camera observation coherent over long rollouts without any explicit memory mechanism. Third, test-time consistency reuses the inverse dynamics mode at inference as a per-action-chunk uncertainty signal that terminates rollouts whose generated frames drift away from the requested actions. We also demonstrate SC3-Eval rollouts reproduce the failure modes that policies exhibit in real-world rollouts, supporting fine-grained diagnostic comparison rather than aggregate ranking alone. Across seven real-world vision-language-action policies, SC3-Eval attains a closed-loop Pearson correlation of $0.929$ and MMRV of $0.119$, outperforming three strong prior video-model-based baselines, and generalizes to new tasks.

Autonomous navigation of quadrupedal robots in diverse environments fundamentally relies on resilient Simultaneous Localization and Mapping (SLAM). While visual-inertial SLAM has matured across wheeled, handheld, and aerial platforms, a critical evaluation gap remains regarding how hardware-level sensor configurations affect performance under the aggressive dynamics of legged locomotion. Quadrupeds introduce distinct embodiment-induced sensory challenges, including foot-impact shocks, high-frequency mechanical vibrations, and rapid angular rotations, which degrade standard perception pipelines. To address this gap, we present a systematic evaluation of state-of-the-art visual, visual-inertial, and LiDAR-visual-inertial SLAM methods using the GrandTour dataset recorded on an ANYmal D quadruped. We isolate and quantify the impacts of camera modalities, shutter techniques, and inertial sensor tiers, analyzing their trade-offs across localization accuracy, algorithmic robustness, and computational resource utilization. Our empirical findings demonstrate that hardware selection has substantial influence on system resilience: stereo configurations consistently outperform monocular and RGB-D modalities, global shutter cameras significantly mitigate motion-induced tracking failures compared to rolling shutter cameras, and, crucially, standard inertial integration can degrade the performance of primarily vision-based frameworks under harsh legged locomotion. These insights additionally offer concrete design guidelines for tailoring custom sensor payloads to achieve dependable perception on agile legged systems.

Markerless, single-RGB-D-camera motion capture provides a low-cost and non-invasive alternative to conventional marker-based systems for robot teleoperation; however, depth estimation often degrades in the presence of self-occlusion, particularly during upper-limb motion. This paper presents an Arm Kinematic Correction (AKC) method that improves depth estimation by enforcing geometric constraints based on constant arm lengths. The proposed approach reconstructs occluded joint depths by leveraging wrist positions and predefined arm lengths via a deterministic formulation based on the Pythagorean theorem, thereby avoiding the need for complex probabilistic modeling or parameter tuning. Experimental validation against a Vicon reference system demonstrates reliable performance for both static and dynamic joint motions, evaluated using root-mean-square error (RMSE) and Pearson correlation. Furthermore, motion-mapping teleoperation is successfully demonstrated in both simulated and physical robot environments. The results show that AKC enhances robustness and preserves anatomical consistency under long-duration, severe self-occlusion, even when paired with less reliable temporal filters, highlighting its practicality for real-time applications such as robot teleoperation and human-robot interaction.

How can we scalably generate data for robotic manipulation, especially on human-like platforms such as dexterous multi-fingered hands? Learning from human videos has recently emerged as a likely answer to this question. However, difficulties in estimating hand-object interaction and crossing the human-to-robot embodiment gap have hindered the adoption of abundant monocular RGB-only human videos as the primary source of robot manipulation data. In this work, we present DO AS I DO, an algorithm to reconstruct and retarget monocular RGB human videos to multi-fingered dexterous robotic hands. DO AS I DO reconstructs hand-object interactions from various egocentric and exocentric in-the-wild video sources. The algorithm then retargets these hand-object interaction estimates into a sequence of actions executable in the real world, yielding robot-complete manipulation data from disparate human videos. Overall, DO AS I DO outperforms previous state of the art in estimating hand-object interactions and extracting dexterous manipulation trajectories from RGB videos, as we show in experiments on datasets with ground truths and on a dataset of video clips collected online. Our experiments enable us to propose an efficacy playbook for practitioners collecting human data for manipulation.

End-to-end autonomous driving models are typically trained on multi-city datasets using supervised ImageNet-pretrained backbones, yet their ability to generalize to unseen cities remains largely unexamined. When training and evaluation data are geographically mixed, models may implicitly rely on city-specific cues, masking failure modes that would occur under real-world domain shifts when generalizing to new locations. In this work, we formulate zero-shot cross-city transfer as a controlled representation-level stress test for end-to-end autonomous driving and ask how visual pretraining affects transfer behavior under geographic domain shift. We conduct a comprehensive study by integrating self-supervised backbones I-JEPA, DINOv2, and MAE into planning frameworks. We evaluate performance under strict geographic splits on nuScenes in the open-loop setting and on NAVSIM in the closed-loop evaluation protocol. Our experiments reveal a substantial generalization gap when transferring models across cities with different road topologies, traffic conventions, and visual environments. In open-loop evaluation, a supervised backbone exhibits severe degradation when transferring between cities, yet some domain-specific self-supervised methods can substantially reduce both displacement and collision degradation. In closed-loop evaluation, self-supervised pretraining improves average out-of-distribution PDMS in several single-city training settings. Our results provide empirical evidence that representation learning influences the robustness of cross-city planning and motivate zero-shot geographic transfer as an important stress test for evaluating end-to-end autonomous driving systems.

We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence. With natural language as a unified action interface, it predicts physically grounded future visual trajectories from current observations across robotic manipulation, autonomous driving, indoor navigation, and human-to-robot transfer. This unified formulation provides three promising application directions: synthetic data generation for policy training augmentation, scalable virtual environments for policy evaluation, and language-guided planning signals for downstream robot control. This is achieved through a three-part design: a) Double-Stream MMDiT with MLLM Action Encoding, where a 60-layer double-stream diffusion transformer couples frozen Qwen2.5-VL semantics with video-VAE latents through layer-wise joint attention; b) Embodied World Knowledge (EWK), an 8.6M video-text corpus (200M+ frames) with action-language mapping over 20+ embodiments and 500+ action categories; and c) General+Expert Progressive Curriculum, a two-stage training strategy that first learns general visual priors and then injects embodied specialization under a shared language interface. Extensive results show strong competitiveness: ranks 1st overall on EWMBench and DreamGen Bench, outperforms all open-source models on WorldModelBench and PBench. Additional zero-shot analyses on RoboTwin-IF benchmark further support robust generalization and multi-view consistency.

Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale. In this report, we investigate whether this scaling recipe can be applied to robotic manipulation to achieve genuine generalization. This is challenging because, unlike text, manipulation data is heterogeneous by nature, expensive to collect, and narrow in diversity, making alignment and scale simultaneously difficult. We present Qwen-RobotManip, a generalizable Vision-Language-Action foundation model built on Qwen-VL. Qwen-RobotManip introduces a unified alignment framework across the representation, motion, and behavioral dimensions of manipulation, making large-scale multi-source training coherent rather than conflicting. This alignment capability in turn enables Qwen-RobotManip to absorb manipulation data at a scale that prior training regimes could not sustain. A human-to-robot synthesis pipeline converts egocentric hand demonstrations into robot trajectories across 15 platforms, and a rigorous curation pipeline harmonizes heterogeneous datasets. Using only open-source datasets and human videos without proprietary data collection, Qwen-RobotManip constructs a ~38,100-hour pretraining corpus and exhibits emergent generalization capabilities, including zero-shot instruction following, robustness to perturbations, reactive error recovery, and cross-embodiment transfer. We find that standard benchmarks fail to capture pretraining quality and instead adopt OOD settings including RoboCasa365, LIBERO-Plus, EBench, RoboTwin-Clean2Rand, RoboTwin-IF, and RoboTwin-XE. Qwen-RobotManip substantially outperforms prior state-of-the-art models, including $π$0.5, across all OOD settings, ranks 1st in RoboChallenge with a 20% relative improvement, and is validated on real-robot platforms including AgileX ALOHA, Franka, UR, and ARX.

Offline handwritten signature verification aims to distinguish genuine from forged signatures using static images. Since real forgeries are rarely available, negative samples are usually randomly drawn from genuine signatures of other users to create training data. However, this random selection often lacks diversity, increases redundancy, and escalates computational cost, leading to inefficient training. We propose a data-driven strategy to generate diverse, informative negative samples using prototypical signatures, which are compact, non-identifiable summaries of genuine signature features. Based on the experiments results, we conclude that (i) prototypical signatures yield more informative negative samples, improving the detection of skilled forgeries; (ii) the proposed approach is backbone-agnostic, showing robustness across architectures; and (iii) when combined with a primal-form linear SVM, it serves as an alternative to RBF-based models while significantly improving scalability and computational efficiency. Implementation of the method is available at https://github.com/kdmoura/proto_hsv.

Image retrieval in crowded scenes is particularly challenging due to the salience bias of conventional visual encoders, which tend to focus on dominant objects while neglecting low-attention regions that are often crucial for fine-grained retrieval. We propose LARE (Low-Attention Region Encoding), a framework that explicitly models these overlooked regions. LARE adopts a dual-encoding strategy that encodes low-attention regions of an image and the full image in parallel, leading to more diverse and informative image embeddings. To evaluate image retrieval performance in challenging crowded scenes, we introduce Dense-Set, a challenging subset derived from COCO and Flickr30K. In this subset, images are re-captioned to provide richer descriptions of low-attention or previously overlooked regions. This dataset highlights the limitations of existing retrieval models and enables a more rigorous evaluation under densely crowded scene conditions. Experimental results demonstrate that the proposed framework improves retrieval performance by preserving subtle, non-dominant visual cues within the shared latent space.

Accurate identification of Pinus sylvestris var. mongolica plantations is important for monitoring afforestation quality and ecological restoration in northern Shaanxi. This paper proposes ROSA-TFormer, a radar-optical sensor-aware temporal Transformer for P. sylvestris classification using Sentinel-1/2 time-series data generated on Google Earth Engine. The model integrates separate SAR and optical embedding branches, a sensor-aware gate, and temporal attention pooling to capture multi-source seasonal features. Experiments on monthly and half-month point-level datasets show that ROSA-TFormer achieves strong classification performance, with 99.67% overall accuracy, 99.56% macro F1, and 98.91% P. sylvestris F1 on the HalfMonth-dataBig dataset. Spatial block validation and ablation results further indicate the effectiveness of radar-optical temporal fusion and sensor-aware modeling. The results demonstrate the potential of ROSA-TFormer for point-level P. sylvestris plantation classification, while broader wall-to-wall validation remains necessary.

Artificial intelligence provides a practical framework for crop damage assessment from imagery data, supporting early decision-making in agricultural management. In peach orchards, climate change increases abiotic stress and biotic pressures, including pests and diseases, which often produce visually similar foliar symptoms. This overlap makes manual diagnosis difficult, especially across multiple fields with varying environmental conditions, highlighting the need for automated models with strong generalization ability. We propose an image-based classification approach for peach leaf damage detection. A benchmark dataset was created through manual annotation of publicly available images, consisting of 1,366 peach leaves across six damage categories. Several deep learning architectures were evaluated. EfficientNet models achieved the best results, with EfficientNetB0 reaching 92.9 percent accuracy, EfficientNetB3 achieving 91.5 percent, and EfficientNetB5 showing the strongest performance on minority classes. DenseNet121 reached 92.6 percent accuracy. The integration of the Convolutional Block Attention Module (CBAM) improved performance in several backbones, particularly EfficientNetB5 and InceptionV3, while showing limited or negative impact in others. The CBAM-enhanced EfficientNetB5 achieved the best overall accuracy of 93.3 percent. To evaluate robustness under realistic conditions, a local dataset of 180 images across four classes was collected, and transfer learning strategies were applied to address domain shift. Three fine-tuning strategies were tested. EfficientNetB3 combined with CBAM achieved the best performance in the local domain, reaching a 93 percent macro F1-score after transfer. Overall, attention-based models showed improved robustness for minority classes and better generalization across different field conditions.

Visual Place Recognition (VPR) is a key component for localisation in Global Navigation Satellite System (GNSS)-denied environments, but its performance critically depends on selecting an image matching threshold (operating point) that balances precision and recall. Thresholds are typically hand-tuned offline for a specific environment and fixed during deployment, leading to degraded performance under environmental change. We propose a method that automatically selects the operating point of a VPR system to maximise recall at 100% precision. The method uses a small calibration traversal with known correspondences and transfers thresholds to deployment via quantile normalisation of similarity score distributions. This quantile transfer ensures that thresholds remain stable across calibration sizes and query subsets. Experiments with seven state-of-the-art VPR techniques across five benchmark datasets demonstrate that our proposed approach consistently outperforms existing baselines, enabling the underlying VPR technique to operate at 100% precision in approximately twice as many deployment scenarios (median improvement), while retrieving up to 29% more correct matches at that precision. The method eliminates manual tuning by adapting to new environments and generalising across operating conditions. Our code is available at https://github.com/DhyeyR-007/Quantile-Transfer-for-Reliable-VPR.

Crowd counting is a fundamental task in computer vision. However, crowd counting in low-light environments remains largely underexplored, despite its practical importance in the real world. Existing methods mainly focus on well-lit scenes or rely on single-modality Red-Green-Blue (RGB) representations, which often become unreliable under extreme darkness and complex non-uniform illumination. To handle this problem, we construct three new low-light crowd counting benchmarks, which consist of two synthetic datasets, SHA\_Dark and SHB\_Dark, and a real-world benchmark LC-Crowd (Low-light Crowd Dataset). Inspired by Retinex-based physical modeling, we introduce depth and Canny edge cues as complementary geometric and structural priors to enhance the intrinsic reflectance representation under low-light conditions. We propose a Multi-Modal Hyper-Graph Fusion module, which formulates RGB appearance, depth geometry, and edge structure cues as nodes in a unified hyper-graph and explicitly captures their high-order complementary relationships via dynamic hyperedge construction and message passing. Furthermore, to adaptively allocate computation in dense prediction, we propose a Deformable Rectangular Sparse Attention (DRSA) module, which concentrates computation on informative regions through anchor-aware estimation and adaptive rectangular window modeling. Based on these designs, we develop a unified Low-Light Counting Network (LCNet) for robust low-light crowd counting. Extensive experiments on three benchmarks demonstrate that the proposed method achieves the best overall performance against existing state-of-the-art (SOTA) methods. The code is in the supplementary material. The datasets will be made public upon acceptance.

The GOOSE 2D Fine-Grained Semantic Segmentation Challenge at the ICRA 2026 Workshop on Field Robotics evaluates dense semantic segmentation of off-road imagery over a fine-grained taxonomy of 64 classes and 11 evaluated non-void coarse categories. We present the first-place solution to this challenge. Our solution comprises two complementary improvements: (a) a network-level design that combines a self-supervised DINOv3 ViT-L/16 backbone, a ViT-Adapter, and a Mask2Former mask-classification decoder, together with a coarse-category auxiliary loss on the global [CLS] token; and (b) an inference-time aggregation strategy based on multi-scale and horizontal-flip test-time augmentation and an ensemble of the top three checkpoints selected using Codabench scores. Our method achieves an official composite score of 76.57%, consisting of 69.32% fine-class mIoU and 83.81% category-level mIoU, and ranks first on the final phase leaderboard: www.codabench.org/competitions/14257/#/results-tab.

Infrared small target detection remains challenging due to severe background clutter, low contrast, and weak spatial responses where geometric overlap alone is insufficient to characterize detection quality. In this work, we propose REEM (Reweighted Explicit-visibility Enhanced Modulation), a lightweight SCR-guided difficulty-aware optimization framework that incorporates Signal-to-Clutter Ratio (SCR) as a physically meaningful visibility prior during training. Instead of modifying the network architecture or directly optimizing SCR, REEM computes a ground-truth local SCR from the input image and applies a differentiable modulation to the soft-IoU learning signal, emphasizing low-visibility targets while preserving stable optimization and identical inference behavior. REEM is integrated into a U-Net-based MSHNet without introducing additional parameters, architectural modifications, or inference-time overhead. Extensive experiments demonstrate consistent improvements over the baseline, achieving higher IoU and detection probability (Pd) together with substantially reduced false alarms (FA), particularly under challenging low-visibility conditions. These results suggest that SCR-guided difficulty-aware optimization provides an effective and physically grounded complement to conventional overlap-based objectives for infrared small target detection. The code is available at https://github. com/yall-in-one/Reemm.

In Remote Sensing (RS), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key approach to activate the generalizable representation ability of foundation models for downstream tasks. However, existing specialized PEFT methods often fail when applied to large-scale Earth observation tasks, as they are unable to fully handle the multifaceted and unpredictable domain gaps (e.g., spatial, semantic, and frequency shifts) inherent in RS data. To overcome this, we propose CrossEarth-Gate, which introduces two primary contributions. First, we establish a comprehensive RS module toolbox to address multifaceted domain gaps, comprising spatial, semantic, and frequency modules. Second, we develop a Fisher-guided adaptive selection mechanism that operates on this toolbox. This selection is guided by Fisher Information to quantify each module's importance by measuring its contribution to the task-specific gradient flow. It dynamically activates only the most critical modules at the appropriate layers, guiding the gradient flow to maximize adaptation effectiveness and efficiency. Comprehensive experiments validate the efficacy and generalizability of our method, where CrossEarth-Gate achieves state-of-the-art performance on 16 out of 18 cross-domain benchmarks for RS semantic segmentation.

Unsupervised object-centric learning (OCL) decomposes visual scenes into distinct entities. Slot attention is a popular approach that represents individual objects as latent vectors, called slots. Current methods obtain these slot representations solely from the last layer of a pre-trained vision transformer (ViT), ignoring valuable, semantically rich information encoded across the other layers. To better utilize this latent semantic information, we introduce MUFASA, a lightweight plug-and-play framework for slot-attention-based approaches to unsupervised object segmentation. Our model computes slot attention across multiple feature layers of the ViT encoder, fully leveraging their semantic richness. We propose a fusion strategy to aggregate slots obtained on multiple layers into a unified object-centric representation. Integrating MUFASA into existing OCL methods improves their segmentation results across multiple datasets, setting a new state of the art while simultaneously improving training convergence with only minor inference overhead.

Multimodal semantic segmentation with heterogeneous sensors must reconcile complementary information across modalities that differ in spatial resolution and channel dimensionality. In particular, high-resolution RGB imaging provides detailed spatial structure but often fails to distinguish visually similar materials, whereas hyperspectral imaging (HSI) provides discriminative spectral signatures but at lower spatial resolution. We present Bidirectional Cross-Attention Fusion (BCAF), which aligns high-resolution RGB with low-resolution HSI at their native grids via localized, bidirectional cross-attention, avoiding pre-upsampling or early spectral collapse. BCAF uses two independent backbones: a standard Swin Transformer for RGB and an HSI-adapted Swin backbone that preserves spectral structure through 3D tokenization with spectral self-attention. Although our evaluation targets RGB-HSI fusion, BCAF is modality-agnostic and applies to co-registered RGB with lower-resolution, high-channel auxiliary sensors. On the benchmark SpectralWaste dataset, BCAF delivers strong performance, achieving 75.4% at 55 images/s. We further evaluate a novel industrial dataset: K3I-Cycling (first RGB subset already released on Fordatis). On this dataset, BCAF reaches 62.3% mIoU for material segmentation (paper, metal, plastic, etc.) and 66.2% mIoU for plastic-type segmentation (PET, PP, HDPE, LDPE, PS, etc.). These results show that preserving native-grid spatial detail and spectral structure improves multimodal segmentation under real-time constraints. Code and model checkpoints are publicly available at https://github.com/jonasvilhofunk/BCAF_2026.

Multimodal change detection (MMCD) identifies changed areas in multimodal remote sensing data, demonstrating significant application value in land use monitoring and urban sustainable development. However, literature MMCD approaches exhibit limitations in both cross-modal interaction and exploiting modality-specific characteristics. This leads to insufficient modeling of fine-grained change information, thus hindering the precise detection of semantic changes. To address these problems, we propose STSF-Net, a framework designed for MMCD between optical and SAR images. STSF-Net jointly models modality-specific and spatio-temporal common features to enhance change representations. Specifically, modality-specific features are exploited to capture genuine semantic change signals, while spatio-temporal common features are embedded to suppress pseudo-changes caused by differences in imaging mechanisms. Furthermore, we introduce an optical and SAR feature fusion strategy that adaptively adjusts multimodal feature importance based on semantic priors obtained from visual foundation models. Finally, we introduce the novel Delta-SN6 dataset, the first openly-accessible multiclass MMCD benchmark consisting of very-high-resolution fully polarimetric SAR and optical images. Experimental results on Delta-SN6, BRIGHT, and Wuhan datasets demonstrate that our method outperforms the state-of-the-art by 3.21%, 0.87%, and 1.32% in mIoU, respectively.

We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds. The model combines a serialization-based Point Transformer v3 backbone with a lightweight semantic head and a tree-focused cross-attention mask decoder. Semantic predictions restrict instance decoding to tree-class voxels, while instance-aware query initialization, one-to-many seed supervision, and asymmetric mask scoring improve separation in dense and structurally complex stands. We further introduce FOR-instance v3, an expanded benchmark comprising 427 scenes and 26,496 annotated trees across diverse biomes, forest structures, and LiDAR platforms. On the FOR-instanceV2 test split, SegmentAnyTreeV2 achieves 90.5% precision, 80.2% recall, 85.0% F1, 90.7% coverage, and 87.6% semantic mIoU, outperforming previous learning-based methods in both instance detection and mask completeness. Zero-shot evaluation on independent sites further demonstrates strong cross-domain generalization.

Reinforcement learning has improved the reasoning ability of large language models, but applying outcome-only rewards to video multimodal large language models (Video-MLLMs) provides limited guidance on which visual evidence should support the answer. Inspired by multisensory integration, where consistent cues can enhance the salience and reliability of perceptual estimates, we introduce Consensus Frame GRPO (CF-GRPO), a temporal-annotation-free process-level reward framework for evidence-aware video reasoning. CF-GRPO constructs a consensus frame prior from intrinsic video cues, including temporal coverage, scene-transition cues, and query-conditioned visual relevance. It then computes a model-side frame-use score from visual and response representations and optimizes their agreement through the Consensus Frame Reward (CFR). With salience-aware sparse aggregation and distribution sharpening, CFR provides a high-contrast reward signal without requiring human temporal annotations. Experiments show that VideoCFR achieves competitive performance across complex video reasoning benchmarks and improves several metrics over representative Video-MLLM and RL baselines, while the consensus prior provides an interpretable view of the evidence frames emphasized during training. The implementation is available at https://github.com/1Pansy/VideoCFR.

Motion forecasting is central to visual intelligence: agents must anticipate how objects will move in order to plan actions, reason about physical interactions, and synthesize realistic futures. We argue that 3D points in world coordinates provide a general representation that is class-agnostic, view-stable, compact, and directly useful for downstream tasks. We formalize the task of goal-conditioned 3D point motion forecasting: given a short visual history, a set of 3D query points on an object of interest, and a language description of the intended goal, the model predicts the future 3D trajectory of each point. We introduce a full stack to study this task at scale: (1) MolmoMotion-1M is a large corpus of action-described, object-grounded 3D point trajectories annotated from 1.16M unconstrained videos; (2) PointMotionBench is a human-verified benchmark spanning 111 object categories and 61 motion types; and (3) MolmoMotion is a general motion forecasting model that supports both autoregressive coordinate prediction and flow-matching-based trajectory generation. MolmoMotion accurately predicts diverse motion patterns with different language instructions, and significantly outperforms existing motion prediction baselines on PointMotionBench. Finally, we show that the learned 3D motion prior transfers well to downstream applications: it improves training efficiency and generalization for robot manipulation, and its predicted trajectories provide effective motion guidance for generative models to synthesize videos with more realistic object motion.

Physical events are not understood by their names alone, but by the causal state changes that compose them. A clip-level label such as "bounce" can be correct while hiding the process that makes the event physically valid, from support loss and contact onset to rebound and settling. To make this hidden process explicit, we introduce Atomic Physical Transitions (APTs): minimal, temporally localized state changes that bind a visible cue to an active physical mechanism and before/after dynamical regimes. An APT chain represents a video as an ordered causal transition sequence rather than a single aggregate event label: event labels tell what happened; APT chains explain why it happened. To make APTs learnable by VLMs, we construct mixed-source APT data from human annotations and simulator ground truth, covering 14 transition types across contact, gravity, friction, and rotation/stability, with 27,303 timed instances over 1,246 trials. Using this data, we find that current VLMs miss transition-level physics, with zero-shot recall at most 14% and errors dominated by missed transitions. Direct fine-tuning on APT chains improves transition detection but causes event-level forgetting, indicating that the model learns a specialized answer format rather than a reusable physical representation. We therefore propose APT-Tune, a parameter-efficient recipe that teaches VLMs to use causal transitions without forgetting how to answer video questions. It combines image-pad-aware supervision, format-conditional co-training, and mechanism-conditioned domain-to-type decoding to make APT learning format-robust and physically grounded. With only 11 M LoRA parameters on Qwen3-VL-2B, APT-Tune substantially improves APT recall while also improving event-level video transfer. These results show that APTs are not a new answer format, but a human-aligned causal supervision signal for physical video understanding.

In today's media-driven world, the exponential growth of video content across domains such as surveillance, education, and entertainment has made retrieving semantically relevant videos via natural language queries increasingly critical. Early video retrieval systems relied on handcrafted features or shallow cross-modal mappings, limiting their ability to capture complex semantics and temporal dynamics. While large-scale vision-language models have improved cross-modal alignment, challenges remain in modeling fine-grained temporal dependencies and nuanced linguistic structures. In this paper, we introduce DREAM: Dual-path Representation Enhancement and Alignment Model, a novel multimodal framework that addresses these limitations through enhanced visual and textual encoding. DREAM incorporates a hybrid language modeling strategy that combines masked and permuted language modeling objectives to capture both local and global linguistic semantics. On the visual side, we design a hierarchical vision encoder with cascaded group attention, which integrates spatial and temporal information through multi-stage token interaction and coarse-to-fine attention refinement. We validate DREAM through comprehensive evaluations on the widely-used MSRVTT, MSVD and LSMDC benchmark datasets, where it achieves new state-of-the-art R1 scores of 49.4%, 49.7% and 27.3%, respectively. Qualitative analyses further show the model's ability to maintain coherent attention across frames and align complex queries with dynamic video content. These findings underscore the effectiveness of hierarchical attention and dual-objective textual modeling in enabling robust, context-aware video retrieval, and pave the way for future research in advancing cross-modal representation learning.

This work presents the development of hybrid models that integrate spiking neural networks (SNNs) with components of convolutional neural networks (CNNs) to learn from simulated event-based camera data (Dynamic Vision Sensor, DVS) generated from conventional smartphone videos. Aimed primarily at human fall detection, the approach leverages the energy efficiency and spatio-temporal processing capabilities of SNNs by converting video frames into event-based data. The proposed models are evaluated through simulations on multiple datasets, comparing their performance to that of traditional machine learning models. Results demonstrate significant gains in efficiency without sacrificing accuracy, underscoring the potential of combining SNNs and DVS technology for complex tasks in real-world environments.

Disciplines such as business process management and process mining aid organizations by discovering insights about processes on the basis of recorded event data. However, an obstacle to process analysis is data multi-modality: for instance, data in video form are not directly interpretable as events. Existing approaches rely on a dictionary of activity label as input, cannot provide frame-by-frame labeling explanations, or rely on superseded computer vision techniques. In this work, we present SnapLog, an approach to extract event data from videos by converting frames to feature vectors using image embeddings and performing temporal segmentation through frame-wise similarity matrices. A generalized few-shot classification is then used to assign labels to the video segments, yielding labeled, timestamped sub-sequences of frames that are interpretable as events. Conventional process mining techniques can be used to analyze the resulting data. We show that our approach produces logs that accurately reflect the process in the videos.

While highlight detection for long-form videos is of great practical importance, most existing methods remain limited to short-form content, largely due to the absence of a suitable benchmark. To bridge this gap, we introduce SVHighlights, to the best of our knowledge, the first benchmark for highlight detection in extremely long sports videos, each exceeding one hour in duration, across multiple sports categories. SVHighlights is constructed from pairs of full-length sports videos and their corresponding official highlight videos using a dataset generation pipeline, enabling scalable label generation without conventional per-clip saliency annotation. The benchmark comprises 320 videos with an average duration of 2.00 hours and a total of 640.18 hours, substantially exceeding previous datasets. Existing methods also face fundamental challenges on long videos: models trained on short clips fail to generalize to hour-long content, and their clip-level scoring lacks the broader context needed to identify highlights. To address this and provide a strong baseline, we present TF-SELECTOR, a training-free segment-based approach that divides each video into context-aware segments by merging adjacent shots sharing the same semantic content, and predicts segment-level saliency scores using a large language model with multimodal inputs including visual captions, transcripts, and audio volume. Experiments demonstrate that TF-SELECTOR achieves superior performance across most metrics compared to Video Temporal Grounding (VTG)-tuned baselines, with improvements of +2.50 in HIT@1, +4.04 in HIT@K, and +2.95 in IoU. These results establish SVHighlights as a challenging testbed for long-form highlight detection and demonstrate that a simple segment-based strategy can effectively scale to hour-long videos.

While video segmentation has advanced rapidly on short clips and closed-set benchmarks, open-world video segmentation remains largely unexplored. The challenge is twofold: (1) existing methods are not designed to support object discovery and identity maintenance in long videos of dynamic ego-motion, and (2) existing evaluation protocols rely on a rigid 1:1 matching that unfairly penalizes semantically valid predictions with mismatched granularity. To address both gaps, we introduce Savvy, a practical and strong system for zero-shot open-world long-horizon video segmentation. Savvy combines hierarchical mask discovery, deferred admission, and track consolidation to support persistent object discovery, safe track promotion, and stable long-range identity maintenance. We further propose OGA, a granularity-aware evaluation suite for open-world video segmentation. Built on a Granularity-Agnostic (GA) matching protocol, OGA relaxes conventional 1:1 matching to an n:1 mapping, but still enforces temporal rigor by detecting support discontinuities through sever points and scoring each reference object through its dominant coherent fragment. This prevents fragmented or flickering support from being over-rewarded while enabling GA-adapted metrics and structural diagnostics: identity persistence (IP), and identity concentration (IC). On VIPSeg, we show that standard 1:1 evaluation substantially underestimates open-world methods, whereas GA evaluation recovers much of their suppressed performance. On the more realistic long-horizon benchmarks: ScanNet and HM3D, Savvy consistently outperforms strong baselines across both classical and proposed metrics, including STQ, VPQ$_\infty$, IP and IC. Together, these results establish a practical benchmark and a strong baseline for open-world long-horizon video segmentation.

Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matching Distillation (DMD) and its successor DMD2 achieved strong generation quality and fast convergence. However, due to the nature of the reverse Kullback--Leibler (KL) objective, these methods exhibit two persistent failure modes: a substantial drop in sample diversity, and visibly over-saturated outputs that deviate from real-video appearance. In this work, we propose Data-Forcing Distillation (DFD), a simple post-training framework that restores diversity and fidelity in DMD with only a single-line of code change. At its core is the teacher score discrepancy to guide the student toward the real-data distribution, pulling it to missing modes (mitigating mode collapse) and away from problematic modes absent in real data (avoiding over-saturation). We provide an in-depth theoretical analysis of our framework and validate our approach on text-to-video, image-to-video, and autoregressive video generation. With only 100--300 steps of finetuning, DFD effectively restores diversity and fidelity on both Wan2.1-1.3B and Cosmos-Predict2.5-2B model, resolving the over-saturation artifacts with significantly better video dynamics and appearance, and even outperforms the teacher model.

Generative AI has made content creation increasingly accessible, but many AI-generated videos lack narrative coherence and creative direction, issues that become more substantial at longer durations. Unlike coding, where AI generation benefits from reliable feedback and techniques such as recurrent self-improvement, video generation requires subjective feedback about plot, scenes, and narrative, which naturally motivates approaches that incorporate human creative direction. We introduce CHIEF, a human-AI co-creation video generation framework that places the creator at the center of human-in-the-loop iterative video refinement, and supports them by providing automatic subjective feedback. The creator incorporates their creative direction by driving each iteration, while their revisions are incorporated by a specialized refiner agent. The feedback loop is generated by persona-conditioned multimodal LLMs that watch generated videos and produce subjective critique from the audience perspectives, providing feedback that self-evaluation alone cannot capture. To test the effectiveness of our proposed framework, we work with high school and college students with no prior filmmaking experience to create videos, from short 1-minute videos to a complete short 10-minute film with a complicated plot.

Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods are restricted to forward temporal generation, whereas practical video creation often requires flexible generation order, e.g., conditioning on future context to extend backward, or on both past and future context for inbetween generation. We bridge this gap by training an autoregressive model that supports generation in arbitrary temporal directions. A key technical challenge arises from the Causal 3D VAE widely used in video diffusion models, which encodes latents strictly conditioned on past context. While suited for forward generation, this causal structure causes inter-block discontinuities when generation proceeds backward. To address this, we introduce blockwise anchor latents, a set of auxiliary latents that restore the missing past context at block boundaries during backward generation. Built on this design, we propose UniTemp, a bidirectional distillation framework that trains a single autoregressive student model for any-direction video generation. At inference time, UniTemp conditions on arbitrary past and/or future frames, improving controllability for both bidirectional and inbetween generation. Experiments show that UniTemp maintains competitive performance on short and long video generation compared to forward-only methods, while enabling diverse workflows such as bidirectional video extension, inbetween generation, looping video generation, scene transition, and visual story generation. Project website: https://lzhangbj.github.io/projects/unitemp/

We propose SpectralDiT, a lightweight modification to flow-matching Diffusion Transformers that adds timestep-conditioned spectral correction to the MLP residual branch. The module decomposes each residual update into low- and high-frequency components on the patch-token grid, then learns a zero-initialized additive gate so the model initially matches the baseline DiT. On CIFAR-10 pixel-space generation, SpectralDiT improves FID from 20.78 to 19.71 at patch size 1 and reduces the radial Fourier spectrum gap. Furthermore, we scale our method to latent diffusion on ImageNet-100. With 0.6% additional theoretical FLOPs and 1.36% additional parameters, SpectralDiT improves latent flow-matching, achieving an 8.7% relative FID reduction under classifier-free guidance (CFG 2.0). All reported results are averaged over five seeds. Ablations and gate visualizations on CIFAR-10 reveal stable block-specific spectral correction patterns.

Teaching machines to emulate natural handwriting styles remains an open challenge, as it requires synthesizing stroke sequences that dynamically vary in shape, texture, pressure and script - not only across individuals, but also within a single person's handwriting. Attempts at this challenge have largely explored deep learning methods in both online and offline settings. However, these approaches are often constrained by style-specific architectural choices, heavy reliance on large datasets, high compute costs, and a lack of flexible control over writing styles through natural language. To this end, we introduce HandwritingAgent, a language-driven agent that can synthesize natural handwriting sequences directly in Scalable Vector Graphics (SVG) format with no need for style-specific training. The agent leverages a large reasoning model to geometrically analyse and autoregressively generate target handwritten glyphs as stroke sequences in a discrete grid canvas environment. Generation is conditioned on texts provided in either conversational or non-conversational mode, along with a reference handwriting-style image. Experiments on diverse handwriting tasks spanning imitation, recognition, multi-lingual handwriting synthesis, and generation of complex handwritten maths and science expressions indicate substantial improvement in performance, with HandwritingAgent matching or surpassing state-of-the-art generative handwriting models, while providing a more efficient, controllable, and generalizable synthesis method.

Real image editing enables precise manipulation of visual content, yet existing methods often fail in complex multi-object scenarios, causing semantic blending, object duplication, or incomplete edits. We attribute these failures to attention leakage, where signals across spatial regions and text tokens become entangled during the denoising process. Specifically, we identify two distinct forms of leakage: Edit-Token Leakage, where ambiguous token-region alignment leads to object blending, and Source Dominance Leakage, where tokens of unchanged source objects overwhelm the attention intended for target entities. To resolve these leakages, we propose \textbf{BindEdit}, which enforces attention-level constraints within a single diffusion trajectory. To suppress Edit-Token Leakage, BindEdit jointly regularizes cross- and self-attention so that each target token group is bound to its corresponding spatial region while maintaining instance-level separation. To suppress Source Dominance Leakage, a cross-attention re-balancing mechanism amplifies target token influence and attenuates residual source semantics within editable regions. Moreover, a region fidelity term ensures that each target concept is expressed coherently across the entire editing mask. Additionally, we propose a comprehensive multi-object benchmark encompassing diverse object counts and categories. Extensive experiments demonstrate that BindEdit consistently outperforms existing methods within a single diffusion trajectory, maintaining robust performance across both single- and multi-object editing scenarios.

Current image editing methods excel at static attributes but fail at complex Human-Object Interactions (HOI), a critical challenge unaddressed by existing benchmarks that conflate HOI with static attributes, relying on global metrics incapable of simultaneously assessing dynamic interaction validity and entangled human-object pair preservation. Thus, we first introduce HOI-Edit, a comprehensive benchmark with three progressive cognitive levels, which features an automated metric HOI-Eval that reliably evaluates instance-level interaction by letting VLM Q&A after thinking with images containing grounded Human-Object pairs. Considering the task's essence of remodeling dynamic relationships, we benchmark Image-to-Video (I2V) models, finding them inherently suited for dynamic editing due to their temporal generation capabilities. Crucially, beyond superior performance, this capability provides a "replay of the failure process," offering unique diagnosability into why errors occur. We thus propose SCPE (Self-Correcting Process Editing), a novel, agentic self-correcting framework that constrains the generation of I2V models through iteratively refined prompts, enabling the generated videos to more accurately present the target HOI. Extracted frames from these videos are the final editing results. On HOI-Edit, SCPE achieves performance competitive with state-of-the-art (SOTA) editing models like Nano Banana on interaction. Code is available at https://github.com/oceanflowlab/HOI-Edit.

Recent advances in instruction-based image editing have enabled models to perform complex visual edits from natural language instructions. However, in product-centric scenarios where preserving product features, branding, and textual elements are critical, current open and closed source models often struggle to maintain this fine-grained object identity. This issue is further compounded by the lack of datasets for instruction-based product image editing with text fidelity constraints, leaving it largely treated as an implicit capability of instruction-based image editing models. In this work, we introduce the ProductConsistency dataset which is designed to improve product-centric image editing. Our approach includes a supervised fine-tuning (SFT) dataset of 87k samples for product editing, a reinforcement learning (RL) dataset with 869 unique product images, and a new benchmark dataset, the ProductConsistency Benchmark, to allow rigorous and standardized evaluation of editing models. To guide RL training, we propose a Cyclic Consistency reward that enforces semantic preservation of product identity by using caption similarity between the original product description and captions generated from the edited image. We fine-tune both Qwen-Image-Edit-2511 and Flux.1-Kontext-dev using our dataset and demonstrate consistent improvements over baseline models in OCR and Perceptual metrics, and MLLM-based evaluations as well, indicating stronger product consistency, text rendering, and overall visual quality; with the Qwen-Image-Edit-2511 model achieving a 5x reduction in the character error rate. The code and pipeline is available at https://anonymous.4open.science/r/ProductConsistency-6FCC/README.md

While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructing a highly optimized task-specific specialist offers a promising solution; however, extreme structural compression inevitably triggers a severe representation bottleneck. To conquer this, we propose Moebius, a highly efficient lightweight inpainting framework. We systematically reconstruct the diffusion backbone by introducing the Local-$λ$ Mix Interaction ($LλMI$) block. Comprising Local-$λ$ and Interactive-$λ$ modules, it elegantly summarizes spatial contexts and global semantic priors into fixed-size linear matrices, preserving complex latent interactions while drastically shedding parameters. Furthermore, to unlock the full representational capacity of this highly compact architecture, we synergistically pair it with an adaptive multi-granularity distillation strategy. Operating strictly within the latent space to avoid expensive pixel-space decoding, this strategy dynamically balances multiple gradient-based losses to achieve high-fidelity alignment. Extensive experiments across natural and portrait benchmarks demonstrate that this optimal synergy enables Moebius to rival or even surpass the generation quality of the 10B-level industrial generalist FLUX.1-Fill-Dev. Remarkably, Moebius achieves this using less than 2\% of the parameters (0.22B vs. 11.9B) while delivering a $>15\times$ acceleration in total inference time, setting a new efficiency standard for high-fidelity inpainting. Project page at https://hustvl.github.io/Moebius.

Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering properties such as visual realism and coherent object structure that matching-based training is intended to learn from the data itself. We argue that this reflects a structural mismatch. Matching losses measure $\ell_2$ regression error on the velocity or score field under training-time marginals, a proxy poorly aligned with the visual and semantic properties that determine sample quality at inference. Given a reward aligned with these properties, RL sidesteps the mismatch by evaluating the model on its own samples and following the reward landscape directly. The challenge is to obtain such a reward without relying on human preferences, which are expensive and conflate data realism with annotator inclinations. We propose Discriminator-Guided RL (DRL). DRL trains a discriminator to separate data from base-model samples in a pretrained representation space and uses its logit as the reward in KL-regularized RL. The pretrained space restricts the discriminator to perceptually meaningful directions, and the logit estimates the log-likelihood ratio between data and model, which is the optimal reward for targeting the data distribution. Across SiT, JiT, REPA, and RAE, DRL reduces guidance-free FID (e.g., $9.38 \to 2.62$ on SiT) and semantic-space FD (e.g., $88.2 \to 19.3$ on DINOv3 for SiT), with consistent gains across all backbones, and improves human-preference rewards without training on them. It also yields a better Pareto frontier between preference reward and image fidelity under subsequent preference-based post-training, increasing alignment while reducing low-level artifacts such as oversaturation and excessive brightness.

Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. These systems operate within speech-only pipelines that produce clean vocal sequences without the ambient texture of real conversations. We take a different approach. Our method, ScenA, conditions a text-to-audio flow-matching foundation model, pretrained on large-scale in-the-wild data, directly on multiple reference voices and a free-form natural language prompt that describes an entire multi-speaker audio scene. Leveraging such a foundational model allows us to inherit its capacity for natural, non-studio audio: background noise, room acoustics, overlapping dialogue, and spontaneous paralinguistic events, while adding multi-speaker control without any per-turn structure. Concretely, reference latents are concatenated into the model's token sequence and distinguished by lightweight identity-aware positional encodings. However, we identify a critical obstacle to this approach: the \textit{Reference Shortcut}. During training under standard noise schedules, the model can identify the matching reference by acoustic similarity to the noisy target, bypassing the text prompt entirely. We address this with a high-noise-biased timestep distribution that forces the model to rely on the text prompt for speaker assignment. We evaluate ScenA on the CoVoMix2-Dialogue benchmark, showing that it outperforms existing multi-speaker systems on speaker-binding metrics while generating rich conversational audio with overlapping speech, emotional vocalizations, and ambient sound. Our results demonstrate the advantage of using a general-purpose audio model conditioned on a free-form scene description, rather than passing structured dialog scripts through a speech-only pipeline.

Controllable image-to-video (I2V) generation transforms a reference image into a coherent video guided by user-specified control signals. While precise control over camera motion, object motion, and lighting is essential for high-fidelity creation, existing methods often treat these factors independently. This overlooks the physical coupling among viewpoint, geometry, and illumination in dynamic scenes, leading to visual inconsistencies such as mismatched shadows and perspective drift under simultaneous changes. We present VidCRAFT3, a unified and flexible I2V framework that explicitly models cross-factor interactions among geometry, motion, and illumination, enabling both independent and joint control over camera motion, object motion, and lighting direction. Image2Cloud provides explicit 3D geometric priors for accurate camera motion control. ObjMotionNet encodes sparse object trajectories into multi-scale motion features to guide realistic object motion. A Spatial Triple-Attention Transformer integrates lighting direction through lighting cross-attention for consistent relighting. To address the scarcity of jointly annotated data, we construct the VideoLightingDirection (VLD) dataset with accurate per-frame lighting direction annotations, and introduce a three-stage progressive training strategy that enables robust learning without fully joint annotations. Extensive experiments demonstrate that VidCRAFT3 achieves state-of-the-art performance in control precision and visual coherence across diverse scenarios.

Video generation models have advanced significantly through the latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies, unstable motion, and visual artifacts that break the illusion of realistic 3D scenes. 3D-consistent video generation could significantly impact numerous downstream applications in generation and reconstruction tasks. We explore how epipolar geometry constraints improve modern video diffusion models. Despite using massive training data, these models fail to capture fundamental geometric principles. We align diffusion models using pairwise epipolar geometry constraints via preference-based optimization, directly addressing unstable trajectories and geometric artifacts through mathematically principled geometric enforcement. Our approach efficiently enforces geometric principles without requiring end-to-end differentiability. Evaluation demonstrates that classical geometric constraints provide more stable optimization signals than modern learned metrics. Training on static scenes with dynamic cameras ensures metric quality while the model generalizes to various dynamic scenes. By bridging data-driven learning with classical computer vision, we reduce epipolar error by 31% and improve human-rated consistency from 54% to 72% without compromising visual quality.

Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modifications, typically requiring manual prompt tuning to achieve acceptable results. We propose \textbf{CAMEO}, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process rather than a one-shot generation task. CAMEO decomposes editing into coordinated stages of planning, structured prompting, hypothesis generation, and adaptive reference grounding, where external guidance is invoked only when task complexity requires it. To overcome the lack of intrinsic quality control in existing methods, evaluation is embedded directly within the editing loop. Intermediate results are iteratively refined through structured feedback, forming a closed-loop process that progressively corrects structural and contextual inconsistencies. We evaluate CAMEO on anomaly insertion and human pose switching tasks. Across multiple strong editing backbones and independent evaluation models, CAMEO consistently achieves 20\% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.

Visual Autoregressive (VAR) models have recently demonstrated impressive image generation quality while maintaining low latency. However, they suffer from severe KV-cache memory constraints, often requiring gigabytes of memory per generated image. We introduce HeatKV, a novel compression method that adapts cache allocation in each head based on its attention to previously generated scales. Using a small offline calibration set, the attention heads are ranked according to their attention scores over prior scales. Based on this ranking, we construct a static pruning schedule tailored to a given memory budget. Applied to the Infinity-2B model, HeatKV achieves $2 \times$ higher compression ratio in memory allocation for KV cache compared to existing methods, while maintaining similar or better image fidelity, prompt alignment and human perception score. Our method achieves a new state-of-the-art (SOTA) for VAR model KV-cache compression, showcasing the effectiveness of fine-grained, head-specific cache allocation. Code and calibration script available at https://github.com/arm-research/heatkv.

Human-centric video customization, particularly at the garment level, has shown significant commercial value. However, existing approaches cannot support low-latency and interactive garment control, which is crucial for applications such as e-commerce and content creation. This paper studies how to achieve interactive multi-garment video customization while preserving motion coherence using only single-garment video data. We present FashionChameleon, a real-time and interactive framework for human-garment customization in autoregressive video generation, where users can interactively switch garment during generation. FashionChameleon consists of three key techniques: (i) Instead of training on multi-garment video data, we train a Teacher Model with In-Context Learning on a single reference-garment pair. By retaining the image-to-video training paradigm while enforcing a mismatch between the reference and garment image, the model is encouraged to implicitly preserve coherence during single-garment switching. (ii) To achieve consistency and efficiency during generation, we introduce Streaming Distillation with In-Context Learning, which fine-tunes the model with in-context teacher forcing and improves extrapolation consistency via gradient-reweighted distribution matching distillation. (iii) To extend the model for interactive multi-garment video customization, we propose Training-Free KV Cache Rescheduling, which includes garment KV refresh, historical KV withdraw, and reference KV disentangle to achieve garment switching while preserving motion coherence. Our FashionChameleon uniquely supports interactive customization and consistent long-video extrapolation, while achieving real-time generation at 23.8 FPS on a single GPU, 30-180$\times$ faster than existing baselines.

Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors. However, this fixed allocation keeps early frames cached even when the current visual state has substantially diverged from them, while discarding potentially more relevant intermediate history. As a result, the retained long-range context may become less adaptive and bias generation toward outdated cues; in severe cases, RoPE-induced phase re-alignment can homogenize inter-head attention and cause sink collapse, where content regresses toward sink frames. We propose DySink, a retrieval-based framework that maintains a compact memory bank and selects visually relevant historical frames as dynamic frame sinks. DySink couples adaptive retrieval with a sink anomaly gate, which detects excessive inter-head consensus over retrieved context and suppresses collapse-prone context. Experiments on minute-long videos show that DySink consistently improves temporal quality over strong baselines while also achieving higher dynamic degree, enabling coherent and more natural long-horizon visual evolution. The code and model weights are released at https://github.com/yebo0216best/DySink.

Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant strides in maintaining temporal consistency, they are predominantly confined to non-interactive scenarios where models merely showcase garments. This limitation overlooks a crucial aspect of real-world apparel presentation: active human-garment interaction. To bridge this gap, we introduce and formalize a new challenging task: Interactive Video Virtual Try-On (Interactive VVT), where subjects in the video actively engage with their clothing. This task introduces unique challenges beyond simple texture preservation, including: (1) resolving the semantic ambiguity of interactions from standard pose information, and (2) learning complex garment deformations from video where interactive moments are sparse and brief. To address these challenges, we propose iTryOn, a novel framework built upon a large-scale video diffusion Transformer. iTryOn pioneers a multi-level interaction injection mechanism to guide the generation of complex dynamics. At the spatial level, we introduce a garment-agnostic 3D hand prior to provide fine-grained guidance for precise hand-garment contact, effectively resolving spatial ambiguity. At the semantic level, iTryOn leverages global captions for overall context and time-stamped action captions for localized interactions, synchronized via our novel Action-aware Rotational Position Embedding (A-RoPE). Extensive experiments demonstrate that iTryOn not only achieves state-of-the-art performance on traditional VVT benchmarks but also establishes a commanding lead in the new interactive setting, marking a significant step towards more dynamic and controllable virtual try-on experiences.

Image-to-Video diffusion models leverage input images to generate visually stunning content, yet frequently produce motion that violates physical laws. We reveal a surprising finding: a 2-step generation often exhibits better physical consistency than a 50-step output from the same model. Through spectral analysis, we trace this to phase erosion during denoising; the phase degrades significantly (dropping by $\approx 18\%$ from step 2 to step 50), whereas the magnitude remains relatively stable. Building on this insight, we propose PhaseLock, a training-free framework that preserves the valid motion priors from few-step inference throughout the denoising trajectory. Rather than relying on full-step inference for physical consistency, PhaseLock extracts a motion prior from just 2 steps and enforces it onto high-fidelity generation via Latent Delta Guidance. Our approach effectively mitigates phase degradation, improving physical consistency by an average of 6.2 points across diverse models while largely maintaining visual fidelity, with negligible overhead ($1.06\times$ time, $1.02\times$ memory) and reduced reliance on expensive external guidance methods ($\sim5\times$ time). Project Page: https://dnwjddl.github.io/phaselock

We present MoVerse, a real-time video world model that creates an interactively navigable scene from a single narrow-field-of-view image. This setting is challenging because the input observes only a small fraction of the environment, while interactive roaming requires a complete surrounding world, persistent geometry, controllable camera motion, and temporally coherent high-fidelity observations. MoVerse addresses this problem by separating world construction from observation rendering. It first expands the input into a gravity-aligned 360$^\circ$ panorama with topology-aware diffusion, closing the missing field of view before 3D reasoning. It then lifts the panorama into a persistent 3D Gaussian scaffold using panoramic geometry-aware residual prediction, yielding a dense and directly renderable spatial memory. Finally, a Gaussian-conditioned video renderer translates scaffold renderings along user-specified camera trajectories into photorealistic video. To make this renderer practical for interaction, we train a bidirectional diffusion teacher for high-quality conditional rendering and distill it into a causal autoregressive student for bounded-latency streaming. This design combines the controllability and long-range consistency of explicit 3D representations with the perceptual quality of generative video models. MoVerse supports real-time scene roaming at 8~FPS on a single NVIDIA RTX~4090 GPU, demonstrating a practical path toward single-image world creation with interactive video output.

Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions. Together, these elements demand a level of fine-grained control beyond current text-to-video models. Existing work addresses each axis in isolation: multi-subject personalization, temporal control, multi-shot synthesis, or camera control; no prior framework jointly integrates all four. We present CineOrchestra, a unified video diffusion model that controls subjects, events, cameras, and shot transitions simultaneously. Our key insight is that these heterogeneous cinematic elements share a fundamental structure: each is an entity acting over a specific temporal interval, which can therefore all be expressed through one shared structure of entity-centric conditioning primitives, augmented with reference images for visual entities. This formulation reduces the architectural challenge to a single positional encoding problem, which we solve with two parameter-free coordinated rotary embeddings: (a) an interval-sampled temporal RoPE that yields consistent attention behavior across events of dramatically varying duration, and (b) a 2D entity-temporal cross-attention RoPE that disambiguates per-entity conditions and routes each to its corresponding spatiotemporal region. On two new benchmarks, CineOrchestra outperforms six per-axis specialists on dense caption following and shot-transition timing, with consistent gains in a pairwise user study and component ablations. Project page: https://snap-research.github.io/CineOrchestra

Accurately aligning CAD models to their corresponding objects in indoor RGB-D scans is a central challenge in 3D semantic reconstruction. The task requires estimating a 9-Degree-of-Freedom (DoF) pose-position, rotation, and scale along three axes-but is hindered by noisy and incomplete scans, as well as segmentation errors that cause geometric distortions. We present Completion-Assisted Object-CAD Alignment (CAOA), a method that integrates a semantically and contextually aware point cloud completion module with a symmetry-aware relative pose estimation algorithm, enabling precise alignment of CAD models to scanned objects. Existing completion methods are typically trained and evaluated on synthetic datasets, which often fail to generalize to real-world scans. To bridge this gap, we introduce a synthetic data generation strategy tailored to indoor scenes, significantly reducing the synthetic-to-real domain gap-validated through quantitative comparisons with widely used completion datasets. In addition, we release S2C-Completion, an expert-annotated dataset of over 8,500 object-CAD pairs from Scan2CAD, created for real-world indoor single-object completion and intended as a new benchmark for this task. For object-CAD alignment, we incorporate symmetry information via a symmetry-aware loss, improving robustness to symmetric ambiguities. On the Scan2CAD benchmark, CAOA achieves a 17% accuracy improvement over state-of-the-art methods.

Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame attention limits its scalability. Existing training-free accelerators reduce computation uniformly along one axis, missing layer heterogeneity. Our spectral, probing, and causal analyses reveal three regimes: shallow layers lack cross-view structure, middle layers drive cross-view alignment, and deep layers are redundant for dense geometry yet their cross-frame attention remains essential for pose. RegimeVGGT applies layer-wise U-shaped compression along two axes: Saliency-Guided Banded Merging protects geometry- and edge-salient tokens, while Selectively Protected K/V Downsampling preserves cross-frame spatial coverage and the pose-critical path through a phase-shifted spatial grid, a reference-frame anchor, and uncompressed camera/register tokens. Training-free, RegimeVGGT achieves a 6.7x speedup over VGGT* at matched reconstruction quality.

Dynamic 4D Gaussian Splatting reconstructs deforming scenes with high fidelity and is increasingly adopted as a representation for dynamic 3D scenes. Putting such a scene to use, for editing, manipulation or motion analysis, first requires segmenting it: grouping the Gaussian primitives into coherent objects. Current pipelines obtain this grouping by importing 2D masks from foundation models such as SAM and lifting or distilling them into the Gaussian representation. In dynamic scenes these masks must be generated across many frames and views, which is costly, and the resulting segmentation can depend strongly on the quality and consistency of those external masks. We ask how much object-level structure can instead be recovered from the Gaussians themselves, and propose Intrinsic-GS, a training-free, mask-free method that builds a sparse affinity graph over Gaussian primitives from appearance, orientation, scale, deformation-trajectory and non-learned rendered-boundary cues. The graph is partitioned with Leiden community detection, requiring no foundation model and no learned feature field. On the standard 4D Gaussian segmentation benchmarks, Neu3D and HyperNeRF, Intrinsic-GS recovers substantial object structure without mask supervision, reaching 0.746 mIoU on Neu3D and 0.575 on HyperNeRF; on Neu3D, a geometry-only variant reaches 0.902 mIoU, matching SAM-supervised TRASE. On HyperNeRF, Intrinsic-GS runs 12.5x faster than the mask-generation and feature-rendering stages used by mask-supervised pipelines. These results suggest that much of the segmentation signal is already encoded in the Gaussians themselves, offering a fast, mask-free direction for 3D and 4D Gaussian segmentation that may also point toward more generalizable, robust segmentation in settings where external masks are unreliable or expensive.

Surface reconstruction from point clouds is important for consumer-grade 3D capture, including AR/VR and indoor scanning. Local-patch Unsigned Distance Field (UDF) methods are lightweight and generalizable, but their accuracy depends on the support radius, traditionally fixed or selected by a one-dimensional curvature heuristic that cannot capture heterogeneous local geometry. We propose a learned per-query radius selector that predicts a continuous support radius and plugs into a frozen LoSF-UDF backbone. The selector is trained using off-grid target radii obtained by parabolic interpolation of cached UDF error curves. Experiments show improved fine-scale reconstruction accuracy.

Reconstructing simulation-ready digital twins of articulated objects from sensor observations remains constrained by two persistent gaps: (i) part-level geometric reconstruction is decoupled from kinematic-parameter estimation, and (ii) the recovered models often violate basic dynamic invariants such as energy conservation, leading to drift when the URDF is replayed in physics simulators. We present KinemaForge, a constraint-driven pipeline that jointly infers part-level shape, joint topology, and joint parameters from short RGB-D sequences and validates the result against an energy-consistent verifier built on differentiable rigid-body dynamics. The pipeline introduces three components: a kinematic constraint graph that encodes joint-part incidences as soft edges; a differentiable screw-axis solver that backpropagates from rendered observations through Featherstone's articulated-body algorithm to joint parameters; and an energy residual loss that penalises non-physical free responses of the reconstructed model. Across five PartNet-Mobility categories and an internal RGB-D benchmark, KinemaForge reduces the average joint-axis error from 4.52 degrees to 2.83 degrees (-37.4%) over the strongest geometric baseline (PARIS) and from 5.30 degrees to 2.83 degrees (-46.6%) over the interaction-based Ditto baseline, lowers long-horizon simulation drift by 64% (vs. PARIS) over 50 s rollouts, and yields URDFs whose closed-loop manipulation success rate improves by 14.6 percentage points over Ditto in our preliminary evaluation. Code and reconstruction data will be released upon acceptance.

Recovering complete 3D representations of objects from few casual image captures remains a significant challenge. Recent 3D generative models, particularly those based on Flow-Matching (FM), can synthesize high-quality textured assets; however, they often suffer from ''synthetic bias'' where learned priors override observational evidence, alongside a lack of alignment with the observed instance. Conversely, optimization-based methods like 3D Gaussian Splatting (3DGS) provide high fidelity on visible surfaces but fail to reason about unobserved geometry. In this paper, we present FlowObject, a framework that reformulates sparse-view 3D reconstruction as a training-free, guided inverse problem. Our approach applies a dual-space guidance strategy to steer the Ordinary Differential Equation (ODE) trajectory of a flow-matching model, enabling the completion of unseen regions through learned generative priors while enforcing strict consistency with real-world observations. By integrating a 3DGS refinement stage, FlowObject further bridges the gap between ''synthetic-looking'' generative outputs and photorealistic reconstructions. Comprehensive benchmarks on synthetic and real-world datasets demonstrate that current state-of-the-art methods often struggle to achieve geometric completeness and observational consistency simultaneously, especially under severe occlusions. In contrast, our method significantly outperforms state-of-the-art generative models and optimization-based frameworks in both geometric completeness and view-dependent appearance fidelity.

Dynamic 3D hand reconstruction from egocentric videos is essential for next-generation computing platforms such as AR/VR and AI glasses. Despite its importance, most prior works focus either on multi-view 3D hand reconstruction or on 4D human body reconstruction. Egocentric 4D hand reconstruction remains challenging due to fast head motion, rapid hand dynamics, severe occlusions, and inherent ambiguity from single-view observations. To address these challenges, we introduce Hand-4DGS, the first feed-forward framework for reconstructing dynamic 4D hands directly from egocentric videos, enabling both fast (~60 FPS) inference and strong generalization. Our approach incorporates a mesh-guided representation for structural priors and temporal convolutions to model dynamic motion. We evaluate our framework on two challenging egocentric datasets, H2O and ARCTIC, and demonstrate significant improvements over baselines. Our method benefits from the generalization capability of feed-forward networks and effective 2D image supervision through Gaussian splatting, without requiring expensive 3D hand pose ground-truth annotations.

Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial reasoning. Instead, OneCanvas aggregates patch features from all views onto a single equirectangular panoramic canvas. Namely, each patch is unprojected to a 3D world coordinate using its depth and camera pose, then placed on the canvas at the continuous longitude and latitude of that point as seen from the canvas origin, with no rasterization or aggregation across overlapping views. A 3D position embedding of the patch's metric coordinates is added to its feature, restoring the depth lost when collapsing the world position to an angular canvas coordinate. Patches from all frames thus share one spatial coordinate system with no fusion or major architectural modifications of the backbone. The pretrained VLM consumes this representation as if it were an ordinary image. Because the canvas can be centered on any pose of interest, the same representation directly supports situated reasoning from a specific viewpoint, a common requirement in robotics and embodied AI. Thanks to this representation, we can also introduce a spatial pretraining curriculum: by procedurally placing patch features of objects, drawn from real images, at chosen 3D world positions on an otherwise empty canvas, we generate on-the-fly supervision spanning a broad range of spatial reasoning tasks, with answer distributions controlled to reduce spatial reasoning shortcuts. OneCanvas achieves state-of-the-art accuracy on SQA3D and VSI-Bench, and generalizes to out-of-distribution data on SPBench, using an order of magnitude less training compute than the strongest competing methods.

Recently neural implicit rendering techniques have evolved rapidly and demonstrated significant advantages in novel view synthesis and 3D scene reconstruction. However, existing neural rendering methods for editing purposes offer limited functionalities, e.g., rigid transformation and category-specific editing. In this paper, we present a novel mesh-based representation by encoding the neural radiance field with disentangled geometry, texture, and semantic codes on mesh vertices, which empowers a set of efficient and comprehensive editing functionalities, including mesh-guided geometry editing, designated texture editing with texture swapping, filling and painting operations, and semantic-guided editing. To this end, we develop several techniques including a novel local space parameterization to enhance rendering quality and training stability, a learnable modification color on vertex to improve the fidelity of texture editing, a spatial-aware optimization strategy to realize precise texture editing, and a semantic-aided region selection to ease the laborious annotation of implicit field editing. Extensive experiments and editing examples on both real and synthetic datasets demonstrate the superiority of our method on representation quality and editing ability. Project page: https://zju3dv.github.io/neumeshplusplus/

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time. We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global composition. Instead of synchronizing Gaussians, each GPU renders its local subset and exchanges only partial pixel values, maintaining mathematical consistency while keeping communication cost stable as the scene size increases. Splaxel further reduces pixel-level redundancy through geometric and transmittance visibility prediction and improves GPU utilization via conflict-free camera-view consolidation. Evaluated on large-scale datasets with up to 120M Gaussians, Splaxel achieves up to 7.6$\times$ speedup over the state-of-the-art distributed 3DGS framework while preserving high reconstruction quality.

We propose a method for extending the depth-of-field (DoF) to construct high-fidelity neural radiance fields (NeRF) -- an emerging technique for rendering photorealistic novel views from a dataset of images captured at different viewpoints, based on implicit neural representations. The trade-off between DoF and light quantity is inherent not only in conventional cameras but also in NeRF, since the datasets used by NeRF are captured by these cameras. To address this issue, we introduce a coded aperture placed at the camera pupil, preserving spatial frequency components under defocused conditions. We develop a camera model incorporating coded apertures into NeRF, allowing direct input of coded images and enabling the generation of novel views with an extended DoF. We validate the proposed method, termed extended DoF-NeRF (EDoF-NeRF), through simulations and experiments, demonstrating its superior performance compared to conventional aperture cameras.

Conventional production workflow of high-precision mesh assets necessitates a cumbersome and laborious process of manual sculpting by specialized 3D artists/modelers. The recent years have witnessed remarkable advances in AI-empowered 3D content creation for generating plausible structures and intricate appearances from images or text prompts. However, synthesizing realistic surface details still poses great challenges, and enhancing the geometry fidelity of existing lower-quality 3D meshes (instead of image/text-to-3D generation) remains an open problem. In this paper, we introduce SuperCarver, a 3D geometry super-resolution pipeline for supplementing texture-consistent surface details onto a given coarse mesh. We start by rendering the original textured mesh into the image domain from multiple viewpoints. To achieve detail boosting, we construct a deterministic prior-guided normal diffusion model, which is fine-tuned on a carefully curated dataset of paired detail-lacking and detail-rich normal map renderings. To update mesh surfaces from potentially imperfect normal map predictions, we design a noise-resistant inverse rendering scheme through deformable distance field. Experiments demonstrate that our SuperCarver is capable of generating realistic and expressive surface details depicted by the actual texture appearance, making it a powerful tool to both upgrade historical low-quality 3D assets and reduce the workload of sculpting high-poly meshes.

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions, introduces unique challenges for machine learning based methodologies. To combat these issues, diverse strategies have been developed, including converting to a format that has orderliness, extracting local geometry, and permutation-invariant or self-attention-based processing. In this paper, our focus is directed towards deep learning models for three fundamental tasks in 3D vision: point cloud classification, part segmentation, and semantic segmentation. We begin by formally defining point cloud data, followed by an in-depth discussion on its structural characteristics. Then, we categorize notable works based on their backbone structure and evaluate their performance on popular benchmarks. Beyond empirical comparison, we offer insights into architectural innovations and limitations. We also outline open challenges and promising future directions for 3D point cloud understanding.

Vision-Language models (VLMs) reliability in medical diagnosis is challenged by trust-undermining hallucinations. Existing hallucination detection approaches mainly focus on identifying factual inconsistencies between generated text and reference data. While some studies analyze where models attend in images, they seldom verify whether such attention truly reflects the visual evidence supporting the generated text. To address this gap, we propose Co}unter-Evidence Verification (CoEV), a training-free plug-and-play framework that detects and corrects hallucinations through evidence-based factual consistency verification. CoEV performs bidirectional verification between textual assertions and visual evidence, testing whether each statement is supported by its corresponding evidence region, and assigns each statement into a four-quadrant diagnostic map capturing combinations of text factuality and visual grounding. CoEV detects hallucinated content and serves as a post hoc refinement tool, correcting hallucinations without retraining. Extensive experiments on four medical datasets show that CoEV combats hallucinations in VLMs.For hallucination detection, CoEV consistently outperforms existing methods, improving average PR-AUC and ROC-AUC by 3.0% and 3.9% absolute points respectively, with notable gains of up to 18.5% in specific VQA scenarios. For hallucination correction, it improves Micro-F1 by up to 12.5%, reduces hallucination rates by over 11.9% on medical report generation, and also boosts medical VQA accuracy. These results show that CoEV enables reliable detection and correction of hallucinations, providing clinicians with dependable, evidence-based cues for diagnosis. Code will be released upon acceptance.

Learning unsupervised representations of medical imaging cohorts can reveal clinically meaningful prototypes without expert labels, which are often noisy and fail to capture true pathological heterogeneity. However, existing deep latent-variable models estimate Gaussian mixture priors via Euclidean averaging, producing prototypes that drift off the curved data manifold and degenerate as the number of sub-populations grows. We propose a manifold-anchored variational framework built on a geometry-aware Expectation-Maximization (EM) algorithm, whose M-step selects each sub-population prototype as the graph medoid with the highest diffusion centrality on a heat-kernel-weighted latent graph, ensuring that every prototype remains on-manifold. A Dirichlet energy regularizer enforces geometric smoothness of the latent space, and a per-sub-population uncertainty score enables label-free quality assessment. \rev{The manifold-anchored EM is a general-purpose geometric tool that extends standard EM and applies readily to other latent-variable models beyond this setting.} On cardiac scar and brain MRI benchmarks, our framework attains the highest accuracy among all compared methods, produces the sharpest prototypes reported to date, and remains stable at large sub-population counts where all baselines degenerate.

The noise of Magnetic Resonance Imaging MRI poses challenges for Deep Learning DL when tumor boundaries are obscured tumor location and appearance are complex Therefore we develop BrainFusionNet that combines Convolutional Neural Networks CNNs Vision Transformers ViT and Gated Recurrent Units GRUs to extract spatial contextual and sequential features from MRI images for improved brain tumor classification Furthermore explainable AI such as SHAP LIME and GradCAM are integrated to visualise and highlight image regions that contribute to BrainFusionNets decisionmaking process The proposed BrainFusionNet model is evaluated on two publicly available MRI datasets Kfold validation suggests 98 accuracy on both datasets The model was compared with the six stateoftheart SOTA CNNs and transfer learning Among the SOTA CNNs DenseNet121 and VGG16 achieved the highest accuracy of 96 The novelty of BrainFusionNet is that the hybrid model effectively extracts local and global features from MRI images even in smallscale tumor regions and small tumor sizes The model has a balanced sequential CNN architecture to capture lowlevel and deeperlayer features a customized ViT that captures local features stabilizes gradient flow and reduces the risk of vanishing gradients during MRI image training The CNN and ViT outputs are fed into a GRU for final classification Furthermore we analyze pixel intensities to determine whether MRI image quality affects image classification Our findings are very novel in image interpretation as we found that the distribution of pixel intensities in MRI images affects DL performance

Despite recent advancements in deep learning, accurately classifying brain tumors from MRI images continues to pose challenges. In this research, we present a comprehensive evaluation of five different convolutional neural networks (CNN) architectures, including a customized baseline model and four pre-trained models - for use in classifying multi-class brain tumors using a clinically-sourced dataset of approximately 10,000 MRI images. We have utilized five different architectures; VGG16, VGG19, DenseNet121, and EfficientNetB0, which were all tested and trained within an identical experimental framework. Performance was measured by both overall accuracy and tumor-wise recall as a means to measure the clinically-relevant performance of each architecture. We found that EfficientNetB0 had the best overall classification accuracy at 95%, when compared to the other architectures tested; specifically VGG16 (94.37%), VGG19 (92.29%), DenseNet121 (90.91%) and the customized CNN (78.00%). An especially important finding of our research was the considerable improvement in detecting meningiomas; specifically, while simple CNNs could detect meningiomas with a recall rate of approximately 20%, EfficientNetB0 was able to detect meningiomas with a recall rate of 89%. Meningiomas are often difficult to detect because they can appear very subtly on MRI images. Additionally, an interesting finding was that the deeper VGG19 performed worse than the shallower VGG16. This indicates that in many cases the architectural efficiency of a CNN model may be more important than its depth when working with medical images. Overall, EfficientNetB0 appears to provide the optimal trade-off between classification accuracy, number of parameters used in the model and clinically meaningful performance.

Automated segmentation of skin lesions using deep learning models for dermoscopic images can be very helpful in finding melanomas earlier than they would normally be detected. However, most deep learning methods available do not perform well. The aim of this paper is to present a parameter-efficient fine-tuning method called PEFT-MedSAM for adapting the Medical Segment Anything Model (MedSAM) to automatically segment dermoscopic skin lesions. The PEFT-MedSAM method uses only the lightweight mask decoder for training the model while keeping the pre-trained image encoder and prompt encoder frozen. The experiments performed on the ISIC 2018 benchmark dataset shows that PEFT-MedSAM obtains a dice coefficient of .9411 and an intersection over union value of .8918 when compared to both a fully trained U-Net baseline (.8715 dice coefficient) and zero-shot MedSAM inference (.8997 dice coefficient). The external validation of the model using PH2 dataset shows .9467 dice coefficient with +/- .0310 standard deviation. Supportive evidence for these claims include a p-value less than .0001 for Wilcoxon signed rank tests comparing the two datasets and bootstrap-estimated 95% confidence intervals of [.9364,.9447] that represent the estimated range of possible values for the average dice coefficient obtained by repeating the test. To increase clinical trustworthiness, we used Grad-CAM explainability along with a pointing game based evaluation methodology to evaluate the CNN baseline model on the validation set. The results showed that we had an accuracy rate of 98.27% on the validation set of 519 images and confirmed that the model classified regions containing skin lesions.

Intravascular ultrasound (IVUS) lumen and external elastic membrane (EEM) segmentation is important for quantitative coronary plaque burden assessment. Errors in lumen or EEM delineation directly propagate to plaque area, plaque burden and geometric measurements. However, standard methods prioritising overlap scores often suffer from boundary drift and topology errors, leading to inaccurate clinical measurements. We present GeoCat, a geometry-consistent network that processes 5-frame IVUS clips using dual Cartesian-polar encoders with cross-domain attention and temporal fusion. A differentiable geometry consistency loss directly supervises clinically relevant descriptors including diameters, orientations, and cross-sectional areas. The model is trained on 12,242 annotated frames from 146 patients acquired with two commercial IVUS systems. We evaluate performance using both segmentation accuracy and plaque-relevant clinical metrics, including Dice/IoU, boundary measures(95HD (mm), ASSD), topology violation rate, and clinical geometry errors (dmax/dmin, angles, and areas). On our dataset, GeoCat achieves a Dice of 0.93, reduces 95HD to 0.14 mm, and lowers topology violations to 1.0%. Importantly, it significantly improves geometric fidelity, yielding diameter errors of 0.13-0.16 mm and angular errors of ~8 degrees, supporting reliable plaque burden quantification.

Zero-shot anomaly detection (ZSAD) is attractive for medical imaging because clinical systems must handle heterogeneous acquisition protocols, changing patient populations, and pathologies for which annotated training data may be unavailable. Most existing zero-shot anomaly detection methods are designed for 2D images, and their direct extension to 3D medical volumes is limited by the scarcity of large-scale volumetric foundation models or by the difficulty of utilizing volumetric context. We propose CS3F, a training-free batch-based framework for ZSAD in 3D medical images using 2D foundation models. Each volume is decomposed along multiple anatomical axes and encoded slice-wise by a 2D vision transformer. These are then converted into localized volumetric tokens by pooling neighboring slice features. Anomaly scores are obtained from cross-subject mutual similarity: tokens that lack close analogues in other subjects are assigned higher anomaly scores. To reduce the attenuation of focal lesion signals caused by depth pooling, we introduce a coarse-to-fine tokenization strategy that enables fine-resolution volumetric scoring without exhaustive matching. CS3F is evaluated on brain MRI across metastases, glioma, and stroke, as well as validated on lung CT to test generalizability beyond atlas-aligned brain MRI. The results show that frozen 2D foundation models can support anomaly localization in 3D medical images, and that the benefit of fine tokenization depends strongly on lesion contrast and imaging modality.

We introduce SMART, a framework for learning a flexible, interpretable, and scalable spatio-temporal brain atlas from longitudinal high-resolution 3D medical images. Existing approaches to spatio-temporal atlas construction rely on black-box generative models that lack flexibility, limit interpretability, and struggle to scale to high-dimensional data. SMART addresses these challenges by learning a continuous disease-time atlas that decouples global group-wise disease dynamics from their patient-specific anatomical manifestation. Guided by anatomically inspired priors, SMART models interpretable global trajectories of regional progression along a shared disease timeline through region-specific differential equations. Global trajectories are further personalized to individual anatomies via dense diffeomorphic displacements parameterized by a flexible and scalable multi-scale Neural Cellular Automata. Evaluated on five longitudinal MRI datasets in Alzheimer's disease (ADNI-1/GO/2, OASIS-3, AIBL; > 1,300 subjects), SMART produces anatomically meaningful predictions of disease progression and achieves state-of-the-art forecasting accuracy and improved temporal consistency over adversarial and diffusion baselines. Our approach establishes a new paradigm for flexible, interpretable, and scalable modeling of spatio-temporal change in high-dimensional medical image time-series.

Ultrasound (US) is widely used for surgical navigation, yet real-time registration between intraoperative 2D slices and preoperative 3D volumes remains challenging due to partial observability, speckle noise, and the action-dependent US acquisition. Existing methods are one-shot or short-horizon, making it hard for them to gather evidence over time or capture how surgeons adjust probe motion based on on-screen feedback. We propose DreamReg, a belief-driven world-model framework that formulates 2D-3D registration as belief updating over rigid transformations. DreamReg maintains a latent belief state that summarizes past observations and poses information, and continuously refines the transformation through learned dynamics as new slices arrive. During training, DreamReg is exposed to probe-motion trajectories that mimic clinical scanning behavior and learns to update its belief by conditioning pose refinement on the current US observation. During inference, DreamReg refines registration via internal imagination: it rolls out the learned world model to simulate candidate probe motions and their predicted observations, and integrates these imagined outcomes to converge to an accurate rigid transformation. Experiments on CAMUS and u-RegPro datasets demonstrate improved robustness and competitive registration accuracy for real-time guidance compared with state-of-the-art methods.

Reliable pixel-level uncertainty quantification holds the potential to transform clinical workflows by enabling high-fidelity longitudinal monitoring and distinguishing true pathological changes from artifacts. Ideally, these models provide the stability required for critical treatment planning and surgical intervention. However, standard deep learning models often suffer from miscalibration, yielding overconfident predictions that mask underlying vulnerabilities at subtle pathological boundaries. To address this, we propose QUAM-SM, a post-hoc framework using targeted adversarial search to identify "adversarially fragile" pixels. By actively seeking perturbations that expose predictive instability, our method highlights regions where decisions are most vulnerable to being flipped. Importantly, the framework disentangles epistemic uncertainty from aleatoric uncertainty. Experiments on two public datasets with multiple expert annotations demonstrate that QUAM-SM outperforms both standard and recent uncertainty estimation approaches in terms of reliability and boundary sensitivity. Code is available at https://github.com/HanaJebril/quam_sm

Single-shot echo-planar prostate diffusion-weighted imaging (DWI) is frequently complicated by geometric distortions, which impact the ability to derive reliable diagnoses from such images. Developing automated correction methods is challenged by the absence of paired distorted and undistorted clinical scans. In this paper, we first propose a novel weakly-supervised image quality transfer (IQT) framework from undistorted to distorted images that utilizes image quality assessment (IQA) signals to supervise the transfer process. Unlike traditional methods that require expensive, voxel-wise paired data or resort to developing unpaired algorithms, our approach utilizes image-level quality labels (here, distorted vs. undistorted) to establish latent quality prototypes within a pre-trained feature space. Recognizing that simulating realistic distortions is more reliable than direct unpaired correction, we describe a weakly-supervised prototype flow matching algorithm to explicitly regularize generative trajectories towards distorted prototypes, producing realistic susceptibility artifacts that mimic clinical degradations. By synthesizing these realistic pairs, we enable a second IQT model to be trained in the forward direction for distortion correction. Experimental results demonstrate that our generated images successfully mimic the diagnostic interference of real-world artifacts, which leads to more capable distortion correction IQT models. In addition to qualitative comparisons, we also conduct exhaustive quantitative evaluations that compare our approach with existing unpaired approaches (e.g., CycleGAN, UNIT-DDPM, and OT-FM) - as either forward or reverse alternatives - by assessing clinical downstream task performance in PI-RADS and Gleason score classification, using both in-distribution and external data sets.

Clinical prostate multi-parametric MRI relies heavily on high-quality diffusion-weighted imaging (DWI), yet reading DWI is frequently compromised by geometric distortion, often caused by rectal air. Assessing quality via the PI-QUAL scoring system is an emerging clinical standard, but it is subjective, time-consuming and suffers from a class imbalance where low-quality cases are diverse and relatively scarce. Using the PRIME clinical trial as an example, there are $6\%$ images with PI-QUAL scores lower than 4, $87\%$ of DWI issues are due to distortion. Many of the other clinical quality issues are under-represented. To address this common dual-scarcity of annotated clinical data, we propose a few-shot biparametric prototypical network for automated image quality assessment (IQA). Our framework utilizes a dual-branch 3D ResNet to fuse T2-weighted and DWI features, providing anatomical context to distinguish true morphology from distortion. To handle real-world heterogeneity, we introduce feature-wise linear modulation (FiLM) and a gradient reversal layer (GRL) to align feature distributions conditioned on varying b-values while suppressing acquisition-related biases. We demonstrate that a model meta-trained solely on comparatively objective, readily obtainable distortion labels can effectively adapt to predicting complex, multi-factorial clinical quality scores such as PI-QUAL using only five representative samples. Experimental results on two datasets show that our method significantly outperforms few-shot learning baselines for this challenging IQA task, offering a practically feasible and data-efficient solution for standardizing prostate MRI quality control in clinical workflows.

Optical coherence tomography (OCT) is essential in ophthalmology, but inconsistent image quality especially in low-cost devices hinders automated analysis. To address this, we introduce a flow-matching-based test-time adaptation method that generates high-quality surrogate images from noisy inputs. Typically, domain gaps between test and training data cause pixel distribution mismatches during the denoising process. We overcome this by matching the test image's histogram to synthetic reference trajectories, successfully aligning the input with expected distributions. Additionally, we remove the network's time conditioning to account for slight deviations in real-world noise distributions. Our approach achieves state-of-the-art performance in segmenting critical biomarkers for two stages of Age-related Macular Degeneration (AMD). Code is available: https://github.com/Veit21/tta-flow.

Although DINOv3 has demonstrated remarkable semantic discrimination in natural imagery, its direct application to volumetric medical segmentation is hindered by inherent dimension and domain disparities. To resolve these issues, we propose DINO-Med3D, a two-stage progressive framework that repurpose the pre-trained DINOv3 encoder for 3D medical tasks. In the first stage, we mitigate the dimension gap by introducing a multi-slice embedding module that incorporates pseudo-3D context, while simultaneously employing a segmentation proxy task to adapt representations learned from natural scenes to the medical domain. Subsequently, we further enhance volumetric understanding by adding lightweight 3D adapters into the frozen backbone to enforce global inter-slice continuity. Finally, to compensate for the spatial information loss inherent in the embedding process, we design a parallel detail recovery stream to explicitly preserve high-frequency boundary cues. Extensive experiments on five public datasets demonstrate that our approach successfully adapts DINOv3 to the medical domain and significantly outperforms state-of-the-art baselines.

We present an automated approach to distinguish between ply instances in semantic segmentation masks of high-resolution carbon-fiber reinforced polymer micrographs. Interpreting the segmentation mask as a graph with pixels as vertices, enables us to use a shortest-path algorithm yielding the ply-separating paths. Thereby, we bridge the gap between semantic segmentation and ply instance segmentation using global information. We successfully apply our approach on high-resolution micrographs featuring a broad range of characteristics like artificially added gaps in single or multiple plies, different stacking sequences and ply traversing cracks. Assigning each fiber pixel to a ply based on the calculated paths, allows for a comprehensive, quantitative ply analysis with respect to its microstructural properties like the local fiber volume fraction as well as locally resolved ply and interleaf layer thickness. These insights help to reveal manufacturing-induced inhomogeneities, draw conclusions on manufacturing parameters and link mechanical properties to underlying microstructural imperfections.

Pelvic segmentation is one of the most important and fundamental research problems in precise and intelligent diagnosis and treatment, as well as surgical planning and navigation for pelvic fractures. By combining an improved geodesic active contour model with deep neural networks, we propose GUMP-Net, an interpretable model-data-driven intelligent algorithm for multi-class pelvic segmentation, in which three network modules are designed to constitute the overall segmentation framework together: the object detection module for automatic level set initialization, the edge detector module for learning an anatomy-aware edge detector function and the iteration module for deep level set evolution. Leveraging the advantages of level set representation and deep learning, GUMP-Net shows more accurate, robust and consistent segmentation performance, especially in small training data situation, compared to the state-of-the-art methods. Extensive experiments on pelvic datasets demonstrate the rationality and effectiveness of the proposed algorithm. Further experiments extended to ankle dataset indicate broader applications to other anatomies. The proposed algorithm not only provides an efficient segmentation method for complex fracture reduction, but also gives an interpretable geometric perspective for understanding deep learning segmentation.

Glioma segmentation in multiparametric MRI is a critical component of treatment planning. A segmentation model that fails silently on treatment-critical sub-regions represents a patient safety risk that overlap-based metrics such as Dice scores cannot expose. We ask whether voxel-level uncertainty estimation via Monte Carlo (MC) Dropout can reliably identify segmentation errors in clinically critical sub-regions, and whether calibration failure modes are detectable from standard reporting metrics alone. In an empirical two-model case study on 126 BraTS21 patients, we evaluate a high-performance pretrained SegResNet and a locally trained UNet with residual units (UNet-Res). MC dropout preserved segmentation accuracy ($|Δ\text{Dice}|$ $<0.01$) while achieving strong uncertainty-error alignment (AUROC for entropy (H) $\approx$0.97), indicating uncertainty correctly ranks erroneous voxels above correct ones. Entropy-based patient stratification identified a high-uncertainty subgroup with substantially lower segmentation performance (median whole-tumour Dice $0.835$ vs. $0.925$), supporting uncertainty as a practical triage signal. However, global alignment can mask important region-specific differences. Despite similar AUROC, UNet-Res exhibited near-zero enhancing tumour entropy ($0.054$) and Expected Calibration Error (ECE) of $0.915$, with a Dice of only $0.714$, indicating severely miscalibrated confidence on the most clinically critical sub-region, a failure mode invisible to standard Dice and AUROC reporting. These findings demonstrate that strong uncertainty-error alignment is necessary but insufficient for clinical safety: sub-region-specific calibration assessment must accompany AUROC evaluation when selecting models for clinical deployment.

Four-dimensional computed tomography (4DCT) captures the full respiratory cycle of thoracic anatomy, yet current Internal Target Volume contouring workflows process each phase in isolation, discarding temporal coherence and leaving contours vulnerable to phase-specific artifacts. We present a lightweight framework that applies parameter-efficient fine-tuning to the Segment Anything Model 3 (SAM 3) via low-rank adaptation (LoRA) to align its text-prompted segmentation with the medical domain using only seven annotated 3D CT volumes. Furthermore, the framework incorporates a hard negative mining strategy to improve boundary discrimination in low-contrast thoracic regions. At inference, phase-wise predictions are refined through phase-coherent temporal filtering and spatial connectivity analysis. Since respiratory motion is continuous and periodic, genuine anatomy appears in contiguous blocks of phases, whereas transient artifacts appear sporadically and are thus effectively suppressed. Experiments on pulmonary and cardiac structures yield median Dice scores of 0.968 and 0.910 with 95th-percentile Hausdorff distances of 0.998 mm and 2.931 mm, respectively. The proposed framework effectively eliminates the severe false-positive predictions inherent in the zero-shot inference of the unadapted SAM 3. With only seven annotated volumes, the framework retains over 95% of full-data accuracy, and the entire pipeline is trainable on a single consumer-grade GPU, demonstrating a scalable, data-efficient solution for adaptive radiotherapy.

High-throughput microfluidic live-cell imaging generates rich single-cell data. Yet semi-automated procedures for locating regions of interest (RoIs), each containing one cell population, and removing surrounding microfluidic structures from recorded images, scale with the number of RoIs. This prevents real-time image analysis and delays time-to-insight by hours to days. We introduce the Design-Aware and Real-Time capable (DART) paradigm for microfluidic cultivation chips, which aligns the CAD blueprint with the physical chip and thereby enables throughput-independent localization of all RoIs and fully automated image processing across diverse RoI geometries and chip layouts. DART establishes this alignment through embedded fiducial markers and deep-learning-based marker detection. We validate DART using the Swiss Army Knife chip, which combines eight structurally distinct RoI designs across 1164 RoI locations. DART localizes all RoIs in five minutes, removes microfluidic structures from raw microscopy images in 40 ms, and performs fully automated image analysis, including cell segmentation, in under 1.1 s per image. Together, these capabilities establish DART as an end-to-end hardware-software paradigm with real-time-capable analysis that paves the way toward closed-loop and outcome-driven smart microscopy.

Medical image classification is often constrained by limited labeled data, motivating generative augmentation; recently, quantum generative models have been proposed for this purpose, frequently reporting accuracy gains. However, such claims are typically based on single training runs, do not match the parameter budgets of the quantum and classical generators, and do not characterize the data regime in which any benefit appears. We present a controlled benchmark that isolates the contribution of a quantum generator to brain-MRI augmentation. Images are encoded into a KL-regularized latent space in which a conditional Wasserstein GAN with gradient penalty is trained using either a variational quantum generator or a classical generator of near-identical parameter count (1648 vs. 1632). Synthetic samples are decoded and used to augment a pretrained classifier across labeled data fractions from 5% to 100%, evaluated over eight random seeds with paired significance testing (with multiple-comparison correction) and with intraset diversity and latent-distribution analyses. Across all fractions, no augmentation variant significantly outperforms real-data-only training, and the quantum and classical generators are statistically indistinguishable. Any low-data benefit behaves as regularization rather than faithful data expansion:synthetic samples are off distribution and severely mode collapsed precisely where data is scarce, and the quantum generator is no more diverse thanits classical counterpart. We release the protocol as a testbed for rigorous evaluation of quantum generative augmentation in medical imaging.

With the growing volume of CT examinations, there is an increasing demand for automated tools such as organ segmentation, abnormality detection, and report generation to support radiologists in managing their clinical workload. Multi-label classification of 3D Chest CT scans remains a critical yet challenging problem due to the complex spatial relationships inherent in volumetric data and the wide variability of abnormalities. Existing methods based on 3D convolutional neural networks struggle to capture long-range dependencies, while Vision Transformers often require extensive pre-training on large-scale, domain-specific datasets to perform competitively. In this work, we propose a 2.5D alternative by introducing a new graph-based framework that represents 3D CT volumes as structured graphs, where axial slice triplets serve as nodes processed through spectral graph convolution, enabling the model to reason over inter-slice dependencies while maintaining complexity compatible with clinical deployment. Our method, trained and evaluated on 3 datasets from independent institutions, achieves strong cross-dataset generalization, and shows competitive performance compared to state-of-the-art visual encoders. We further conduct comprehensive ablation studies to evaluate the impact of various aggregation strategies, edge-weighting schemes, and graph connectivity patterns. Additionally, we demonstrate the broader applicability of our approach through transfer experiments on automated radiology report generation and abdominal CT data.

Understanding disease progression is a central clinical challenge with direct implications for early diagnosis and personalized treatment. While recent generative approaches have attempted to model progression, key mismatches remain: disease dynamics are inherently continuous and monotonic, yet latent representations are often scattered, lacking semantic structure, and diffusion-based models disrupt continuity with random denoising process. In this work, we propose to treat the disease dynamic as a velocity field and leverage Flow Matching (FM) to align the temporal evolution of patient data. Unlike prior methods, it captures the intrinsic dynamic of disease, making the progression more interpretable. However, a key challenge remains: in latent space, Auto-Encoders (AEs) do not guarantee alignment across patients or correlation with clinical-severity indicators (e.g., age and disease conditions). To address this, we propose to learn patient-specific latent alignment, which enforces patient trajectories to lie along a specific axis, with magnitude increasing monotonically with disease severity. This leads to a consistent and semantically meaningful latent space. Together, we present $Δ$-LFM, a framework for modeling patient-specific latent progression with flow matching. Across three longitudinal MRI benchmarks, $Δ$-LFM demonstrates strong empirical performance and, more importantly, offers a new framework for interpreting and visualizing disease dynamics.

Weakly supervised segmentation enables model training from plane-level labels. Existing methods often rely on 2D encoders, neglecting the volumetric nature of medical data. We propose TranSamba, a hybrid Transformer-Mamba architecture designed to capture 3D context via cross-plane modeling. TranSamba augments a Vision Transformer backbone with Cross-Plane Mamba blocks, leveraging linear-time modeling for efficient information exchange across neighboring planes. This exchange improves in-plane self-attention and subsequent attention maps for object localization. TranSamba maintains linear time complexity and constant space complexity with respect to the input volume depth. Extensive experiments on three datasets covering diverse modalities and pathologies show that TranSamba achieves state-of-the-art performance, demonstrating the generalizable efficacy of cross-plane modeling. Code is available at: https://github.com/YihengLyu/TranSamba.

Deep learning-based CT segmentation systems often achieve high accuracy on clean benchmark images, but their performance may degrade under heterogeneous clinical imaging conditions such as noise, resolution loss, contrast variation, intensity shift, and artifacts. This instability can limit reliable deployment in real-world medical imaging workflows. We propose Robustness via Augmented Multi-corruption Pipeline (RAMP), a robustness-oriented augmentation framework for CT segmentation. RAMP combines anatomically constrained spatial perturbations, CT intensity transformations, and stochastic multi-corruption composition to expose models to clinically plausible image degradation during training. Across two CT segmentation evaluation settings, RAMP achieved the strongest corrupted-image performance and the smallest clean-to-corrupted robustness gap. In the five-organ noisy evaluation benchmark, RAMP improved mean corrupted Dice from 0.610 to 0.753 and reduced the robustness gap from 0.264 to 0.064 compared with the nnU-Net baseline. In Abdomen1K, RAMP improved mean corrupted Dice from 0.633 to 0.789 and reduced the robustness gap from 0.290 to 0.070. Although RAMP did not achieve the highest clean-image Dice, it substantially mitigated worst-case segmentation collapse under severe image degradation. These results suggest that multi-corruption augmentation can serve as a practical pre-deployment strategy for improving the reliability of CT segmentation systems in heterogeneous clinical environments.

In-silico trials of medical devices require the generation of virtual populations of anatomies. In cardiovascular applications, virtual anatomy is typically represented as a 3D+t mesh sampled from a generative model. However, most existing mesh generators focus on static anatomy, while sequence models often lack explicit periodicity. To this end, we propose 4D F-MeshLDM, a conditional generative framework comprising a convolutional mesh VAE to encode meshes, a structural latent space that parameterises motion using a truncated Fourier series, and a diffusion prior that learns the latent distribution over Fourier coefficient tokens. By conditioning the diffusion process on clinical covariates via affine modulation, we enable controllable synthesis. Sampling tokens and performing inverse Fourier synthesis yield cycle-consistent latent trajectories, which can be decoded into 3D+t cardiac mesh sequences. Experiments on 5,000 UK Biobank subjects demonstrate that 4D F-MeshLDM outperforms state-of-the-art baselines in anatomical fidelity and achieves near-zero cycle closure error. Furthermore, the generated cohorts accurately preserve clinical functional indices, highlighting the potential of our framework for reliable in-silico cardiac trials.

Multiple Instance Learning (MIL) is a standard paradigm for Whole-Slide Image (WSI) analysis and has achieved strong results in computational pathology. However, most MIL pipelines assume a single "gold" label per slide, which conflicts with clinical practice where substantial inter-pathologist variability is common. Existing multi-annotator learning and label-refinement methods typically estimate global annotator reliability or rely on single-instance assumptions, making them poorly suited to MIL and to localized diagnostic contexts where experts disagree. We propose RaLMPH (Reliability-aware Learning for Multi-Pathologist Harmonization), a MIL-based label reconciliation framework for WSIs annotated by multiple pathologists. RaLMPH introduces a reliability field that jointly models (i) local neighborhood structure in WSI feature space and (ii) expert uncertainty (entropy), enabling per-sample identification of trustworthy reference neighborhoods. Leveraging this field, RaLMPH performs sample-wise local annotator ranking to select reliable opinions per slide and applies an adaptive gating mechanism to fuse labels conditioned on local reliability. Experiments on a clinical WSI dataset with labels from six pathologists, as well as controlled simulated benchmarks, show that RaLMPH consistently outperforms existing approaches. Further analyses clarify how our reliability-aware mechanism improves label reconciliation and downstream MIL performance.

Pathological images are inherently multi-scale, requiring pathologists to integrate evidence from global tissue architecture at low magnification to cellular morphology at higher magnification for accurate diagnosis. While existing pathological datasets for vision-language model (VLM) include various scales, they often lack an explicit cross-scale reasoning objective. This limitation prevents VLMs from capturing essential cross-scale representations and learning evidence-based reasoning. To bridge this gap, we introduce the first cross-scale training and evaluation paradigm that formulates pathology interpretation as multi-magnification reasoning. However, creating such a task reveals a critical challenge: multi-image visual question answering (VQA) is prone to text-only shortcuts, which allow models to guess answers using magnification-dependent artifacts rather than visual evidence. To address this, we propose a leakage-aware curation pipeline that combines adversarial text-only screening with constraint-guided question design. Using this pipeline, we construct Scale-VQA, a high-quality benchmark with 4,685 multiple-choice questions grounded in 2,537 pathology images across multiple magnification levels. Finally, we present ScaleReasoner-R1, a model trained via reinforcement learning to optimize performance on the cross-scale VQA task. ScaleReasoner-R1 achieves state-of-the-art performance on our cross-scale reasoning benchmark and generalizes to SOTA performance on established single-scale benchmarks. Findings suggest that even the limited cross-scale supervision can significantly improve pathological understanding. The code and demos will be open-sourced.

Computed tomography (CT) is a cornerstone imaging modality for non-invasive, high-resolution visualization of internal anatomical structures. However, when the scanned object exceeds the scanner's field of view (FOV), projection data are truncated, resulting in incomplete reconstructions and pronounced artifacts near FOV boundaries. Conventional reconstruction algorithms struggle to recover accurate anatomy from such data, limiting clinical reliability. Deep learning approaches have been explored for FOV extension, with diffusion generative models representing the latest advances in image synthesis. Yet, conventional diffusion models are computationally demanding and slow at inference due to their iterative sampling process. To address these limitations, we propose an efficient CT FOV extension framework based on the image-to-image Schrödinger Bridge (I$^2$SB) diffusion model. Unlike traditional diffusion models that synthesize images from pure Gaussian noise, I$^2$SB learns a direct stochastic mapping between paired limited-FOV and extended-FOV images. This direct correspondence yields a more interpretable and traceable generative process, enhancing anatomical consistency and structural fidelity in reconstructions. I$^2$SB achieves superior quantitative performance, with root-mean-square error (RMSE) values of 49.8 HU on simulated noisy data and 152.0 HU on real data, outperforming state-of-the-art diffusion models such as conditional denoising diffusion probabilistic models (cDDPM) and patch-based diffusion methods. Moreover, its one-step inference enables reconstruction in just 0.19 s per 2D slice, representing over a 700-fold speedup compared to cDDPM (135 s) and surpassing DiffusionGAN (0.58 s), the second fastest. This combination of accuracy and efficiency indicates that I$^2$SB has potential for real-time or clinical deployment.

Table Structure Recognition (TSR) using a pointer network achieves impressive results by predicting HTML sequences while aligning tags to detected text (or cell) regions. However, our analysis reveals that when pointer networks fail, 79.6% of errors occur between spatially adjacent cells (Manhattan distance <= 2). Despite this, standard cross-entropy loss weights all negative candidates equally. In this work, we propose Geometry-Aware Pointer (GAP) Loss, which reweights the cross-entropy objective based on spatial proximity to ground truth. By applying inverse distance weighting, GAP focuses gradient flow where the model struggles most: immediate neighbors receive stronger gradients than distant cells. Our approach requires only a straightforward modification to the loss computation, maintaining the same model architecture with zero additional inference cost. Extensive experiments on PubTabNet and SynthTabNet demonstrate that GAP consistently reduces adjacent-cell errors, achieving new state-of-the-art performance. Our findings suggest that incorporating geometric inductive biases at the loss level provides a simple yet effective approach to robust TSR. Our code is available at https://github.com/teamreboott/GAP

Data scarcity and structural distortion significantly limit handwriting recognition in high-security authentication. Existing augmentation methods often cause topological and morphological damage, particularly when processing complex Chinese characters where stroke intersections, ligatures, and sharp turns render traditional branch-point detection unreliable. To address this, this paper proposes a fuzzy geometry-driven structure-aware (FGSA) augmentation framework. We model branch points as fuzzy sets within the skeleton space, constructing a continuous branch-point membership field by integrating topological neighborhood evidence with direction field divergence. This membership field is adaptively optimized via an unsupervised surrogate objective, enabling robust stroke decoupling without manual annotation. Finally, kinematically-aligned samples are synthesized through parameterized cubic Bézier reconstruction and multi-strategy perturbations, ensuring a balance between structural fidelity and sample diversity. Moreover, we establish LZUSig, a large-scale, highly challenging dataset specifically dedicated to fine-grained structural degradation in Chinese handwritten signatures. Extensive experiments on CASIA-HWDB1.1, ChiSig, and LZUSig demonstrate that FGSA significantly reduces the word-level error rate ($Δ$WER), achieving optimal recognition gains over the compared baselines. More importantly, it strikes a robust trade-off among task gain, structural fidelity, and discriminative feature preservation, offering a highly controllable solution for handwriting augmentation.

Recent studies have shown that handwritten text recognition (HTR) systems perform worse on Arabic-script datasets than on Latin-script data. However, the reasons for this gap are still not well understood due to the lack of controlled comparisons. In this work, we present a comprehensive study of Arabic and Latin scripts HTR using a unified CRNN model for line-level HTR across nine datasets (including KHATT (Arabic), Muharaf (Arabic), NUST-UHWR (Urdu), PHTD (Persian), IAM (English), READ-2016 (German), and others) and di ferent training sizes (K in {100, 500, 1000, 2000, ..., Kfull}). Our results show the performance gap remains: it is large in low-resource settings, decreases with more data, but remains even at full scale, with a consistent difference of 5-7 CER points. We show that annotation quality matters, as many datasets contain labeling errors. Cleaning reduces error rates and narrows the gap, but does not eliminate it. In addition, we find that a fixed number of training samples provides less effective coverage in Arabic due to higher visual variability, requiring more data to learn similar representations. We compare recognition across datasets in terms of the number of text lines and the number of characters, showing an equivalence trade-off. We compare character frequency distributions across scripts and show that Arabic is significantly more heavy-tailed than Latin. Our error analysis reveals that around 30 percent of substitution errors in Arabic datasets (e.g., KHATT) are caused by confusion between visually similar characters, compared to about 15 percent in Latin-script datasets such as IAM.

European Portuguese (pt-PT) is largely absent from OCR benchmarks, which skew toward high-resource languages. The few benchmarks that cover pt-PT focus on historical artifacts and literature. This work addresses modern OCR applications, introducing PorTEXTO, the first benchmark for contemporary and culturally relevant pt-PT visual text extraction. To ascertain quality, we employ an annotation pipeline combining transcriptions from a frontier LVLM with exhaustive review by native speakers. We observe a sharp performance drop from synthetic to real world samples in most models, and find that, currently, specialized multilingual data is a better driver for pt-PT performance than model size or resolution budget, motivating the release of open pt-PT OCR resources.

Automatic Handwritten Text Recognition (HTR) is inherently a challenging task, and its complexity is further increased when dealing with cursive scripts. Although significant efforts have been made on various cursive scripts, research regarding Urdu Handwritten Text Recognition (UHTR) has been relatively limited. This lag of research is primarily due to the unique challenges posed by its script, and the scarcity and unavailability of benchmark datasets. Therefore, to advance research in UHTR, this study presents a specialized real dataset called the Urdu Katib Handwritten Dataset (UKHD). To the best of our knowledge, this is the first offline Urdu handwritten text lines dataset specifically curated from the materials written by Katibs in historical times. It encompasses a diverse range of flat nib writing variations in the Nastalique calligraphic style. Additionally, the effectiveness of different CRNN-based hybrid models has been evaluated to identify the optimal architecture for Urdu Katib Handwriting Recognition (UKHR). Among the analyzed models, the CNN-BGRU-CTC model showed more robust performance, with low Character Error Rate (CER) and Word Error Rate (WER). This research work aims to support and encourage the research community in developing a robust recognition system for preserving Urdu handwritten literature.

Digital twins have a major potential to form a significant part of urban management in emergency planning, as they allow more efficient designing of the escape routes, better orientation in exceptional situations, and faster rescue intervention. Nevertheless, creating the twins still remains a largely manual effort, due to a lack of 3D-representations, which are available only in limited amounts for some new buildings. Thus, in this paper we aim to synthesize 3D information from commonly available 2D architectural floor plans. We propose two novel pixel-wise segmentation methods based on the MDA-Unet and MACU-Net architectures with improved skip connections, an attention mechanism, and a training objective together with a reconstruction part of the pipeline, which vectorizes the segmented plans to create a 3D model. The proposed methods are compared with two other state-of-the-art techniques and several benchmark datasets. On the commonly used CubiCasa benchmark dataset, our methods have achieved the mean F1 score of 0.86 over five examined classes, outperforming the other pixel-wise approaches tested. We have also made our code publicly available to support research in the field.

Handwritten Text Recognition (HTR) with limited labeled data remains a challenging problem, particularly for Arabic-script languages. Although modern sequence-based recognizers perform well in high-resource settings, their accuracy degrades sharply as training data becomes scarce. Arabic-script languages share a common writing system with substantial character overlap, motivating cross-lingual learning as a strategy to mitigate data scarcity. We conduct a controlled line-level study of cross-lingual joint training for Arabic-script HTR under low-resource regimes (number of samples K = 100, 500, 1000 labeled lines) on Arabic (KHATT), Urdu (NUST-UHWR) and Persian (PHTD). CRNN and Vision Transformer-based HTR-VT models are trained on the union of multiple related Arabic-script datasets to mitigate the data scarcity and are evaluated on individual target languages. Both architectures benefit from cross-language training under low-resource conditions. CRNN remains more effective under extremely limited target-language data, whereas the benefits of cross-language training for HTR-VT become less consistent as larger amounts of target-language data become available. On Persian (PHTD), joint training achieves a Character Error Rate (CER) of 9.99 , surpassing previously reported results despite not using the full available training data. On an additional Urdu dataset (UNHD), joint training reduces CER from 17.20 to 14.45.

Correspondence is fundamentally relational: it seeks the unknown transformation between two observations of a common scene, not the content of either. Yet the dominant learning-based methods do not represent the transformation as a first-class object in the architecture. They encode each image independently and let a learned similarity function or a deep decoder discover the mapping implicitly. Phase correlation is the canonical exception, measuring the inter-image relationship directly in the Fourier domain, but the rigidity of its fixed basis confines it to global translation. We introduce a learned generalization of phase correlation that lifts this restriction by learning the basis on which the transformation decomposes. The same algebraic primitive extends to dense non-rigid deformations and to unitary dynamics. On the ACDC cardiac-MRI benchmark the framework matches or exceeds prior published baselines on both registration directions. On CAMUS echocardiography it matches state-of-the-art without auxiliary scoring or adaptive-smoothness mechanisms. Applied to time-evolved wavefunction pairs of the 1-D quantum harmonic oscillator, the same framework recovers the Hermite-function eigenstates and the quantized energy levels of the unknown Hamiltonian from observation pairs alone.

Spiking neural networks (SNNs) have garnered significant interest in computer vision due to their potential for efficiency and biological inspiration. While spiking CNN-based methods have shown promise for image restoration (IR) tasks, their performance is constrained by the inherent receptive field limitations of CNN operations. In the paper, we explore the benefits of discrete wavelet transformation and propose a spiking pyramid wavelet-based model (SPWM) for high-efficient and low-energy target. Specifically, we develop a spiking dual pyramid wavelet (SDPW) block to model long-range dependency and exploit the properties of the degradation in the wavelet domain. Experimental results on several benchmarks demonstrate that SPWM significantly lowers computational costs and energy consumption while maintaining image quality. Our method showcases the potential of SNNs in the field of IR, offering new insights for future applications of resource-limited devices.

This paper addresses low-rank tensor completion (LRTC) by proposing a novel nonconvex surrogate, namely the ratio of the tensor nuclear norm to the tensor Ky Fan p-k norm (TNPK), to accurately approximate the tensor tubal rank. The TNPK possesses appealing properties, including scale invariance, parameter flexibility, and the existence of closed-form solutions under specific choices of p and k. With specific parameter settings of p and k, it reduces to the ratio of the tensor nuclear norm to the tensor Ky Fan k norm (TNK) or the ratio of the tensor nuclear norm to the tensor Frobenius norm (TNF). We construct a LRTC model and, under the tensor null space property (NSP), prove that low-rank tensors are local minimizers of the proposed model. Moreover, we derive the proximal operator of the Ky Fan p-k inverse-norm and further develop an efficient alternating direction method of multipliers (ADMM) algorithm with guaranteed subsequential convergence under mild conditions. Extensive experiments on synthetic and real-world datasets validate the superior performance of our method against state-of-the-art competitors.

All-in-One image restoration aims to develop a unified restoration framework for handling diverse degradation types. Existing end-to-end methods usually regard the restoration process as a black-box mapping, lacking an explicit optimization interpretation. Although deep unfolding provides an interpretable iterative modeling paradigm for image restoration, existing methods mostly rely on fixed degradation assumptions or predefined degradation information, making them difficult to adapt to unified restoration requirements under complex degradations and locally damaged content. This limitation restricts their performance in degradation suppression and structural detail recovery. To address these issues, this paper proposes DVANet, a deep unfolding network inspired by the half-quadratic splitting optimization algorithm, which formulates unified image restoration under complex degradations as a collaborative unfolding process between degradation-aware observation consistency and visual-prior-guided reconstruction. Specifically, in the degradation-aware observation consistency branch, a degradation representation module is employed to extract global degradation attributes and local degradation cues, and degradation-conditioned mapping is used to enhance the model's adaptability to different degradation types. In the visual-prior-guided reconstruction branch, DINOv3 is introduced to provide structural and semantic information as hierarchical visual priors, thereby complementing the missing structural information in damaged regions and improving detail recovery. Extensive experiments demonstrate that DVANet achieves superior or competitive performance on multi-scenario degradation and cross-domain image restoration tasks, showing favorable degradation adaptability and generalization ability.

The automated analysis of heterogeneous natural textures is frequently hindered by physical damage and data loss, presenting a significant challenge to computer vision. While deep learning has shown success in controlled environments, its application to complex geological materials under conditions of incomplete information remains underexplored. This study presents an integrated framework for the inpainting and classification of high-resolution core sample images. We propose an end-to-end pipeline that utilizes object detection for sample segmentation, followed by image inpainting using Generative Adversarial Networks (GANs) with Contextual Residual Aggregation (CRA) to reconstruct missing high-frequency details. Subsequently, we evaluate the performance of modern Transformer-based (Swin, ViT) and CNN architectures on the reconstructed data. Our experiments revealed a critical divergence between reconstruction quality and downstream utility: despite high structural fidelity (PSNR 28.7~dB, FID 74.01), classification accuracy plateaued at 53\%. To improve minority-class detection, we propose a confidence-based hybrid ensemble that raises MCA from 48\% to 58\%. These results highlight the limitations of current state-of-the-art generative models, which may produce visually plausible but semantically ambiguous features ("hallucinations") that confound classifiers. This work provides insights into the dependencies between image reconstruction quality and classification performance, offering a reproducible baseline for future research in non-destructive testing and material science. Given that cross-well accuracy remains in the 49--53\% range, we position the resulting system as a decision-support and screening tool for lithofacies interpretation rather than as a fully autonomous classifier. The code is available at https://github.com/GalymzhanAbdimanap/Lithology_recognition

The unstructured and irregular nature of points poses a significant challenge for accurate point cloud quality assessment (PCQA), particularly in establishing accurate perceptual feature correspondence. To tackle this, we propose the Multi-scale Implicit Structural Similarity Measurement (MS-ISSM). Unlike traditional point-to-point matching, MS-ISSM utilizes radial basis function (RBF) to represent local features continuously, transforming distortion measurement into a comparison of implicit function coefficients. This approach effectively circumvents matching errors inherent in irregular data. Additionally, we propose a ResGrouped-MLP quality assessment network, which robustly maps multi-scale feature differences to perceptual scores. The network architecture departs from traditional flat multi-layer perceptron (MLP) by adopting a grouped encoding strategy integrated with residual blocks and channel-wise attention mechanisms. This hierarchical design allows the model to preserve the distinct physical semantics of luma, chroma, and geometry while adaptively focusing on the most salient distortion features across High, Medium, and Low scales. Experimental results on multiple benchmarks demonstrate that MS-ISSM outperforms state-of-the-art metrics in both reliability and generalization. The source code is available at: https://github.com/ZhangChen2022/MS-ISSM.

Diffusion posterior sampling solves inverse problems by combining a pretrained diffusion prior with measurement-consistency guidance. However, full-band guidance can be unreliable at high noise levels, where clean estimates contain score-induced errors and high-frequency measurement directions are weakly identifiable. We argue that posterior guidance should expose measurement frequencies according to the instantaneous diffusion noise level. Based on this principle, we propose a posterior continuation framework that constructs a family of intermediate posteriors whose likelihood emphasizes currently reliable frequency bands and gradually returns to full-band consistency. We instantiate this framework with a stabilized sampler that combines a diffusion predictor, frequency-limited likelihood refinement, and a Haar-domain commitment rule that commits reliable coarse corrections while deferring weakly identifiable details. Across super-resolution, inpainting, and deblurring, our method achieves competitive-to-state-of-the-art restoration performance, including up to 5 dB PSNR improvement on motion deblurring over strong baselines in evaluations on FFHQ and ImageNet.

Generative Image Restoration (GIR) has achieved impressive perceptual realism, but how far have its practical capabilities truly advanced compared with previous methods? To answer this, we present a large-scale study grounded in a new multi-dimensional evaluation pipeline that assesses models on detail, sharpness, semantic correctness, and overall quality. Our analysis covers diverse architectures, including diffusion-based, GAN-based, PSNR-oriented, and general-purpose generation models, revealing critical performance disparities. Furthermore, our analysis uncovers a key evolution in failure modes that signifies a paradigm shift for the perception-oriented low-level vision field. The central challenge is evolving from the previous problem of detail scarcity (under-generation) to the new frontier of detail quality and semantic control (preventing over-generation). We also leverage our benchmark to train a new IQA model that better aligns with human perceptual judgments. Ultimately, this work provides a systematic study of modern generative image restoration models, offering crucial insights that redefine our understanding of their true state and chart a course for future development.

The inherent electronic and speckle noise complicates clinical interpretation of ultrasound images. Conventional denoising methods rely on explicit noise assumptions whose validity diminishes under composite noise conditions. Learning-based methods are usually pretrained in a limited image domain using a labeled dataset, which implies inevitable domain shift in complex in vivo environments. This study proposes a Pyramid Self-Contrastive Learning (PSCL) framework for test-time ultrasound image denoising without pretraining. Given multiple noisy samples from only one-shot imaging, PSCL disentangles anatomical similarity and noise randomness into separate pyramid latent spaces. The clean image is then decoded from the anatomy space while discarding the noise space. We first apply PSCL to synthetic aperture ultrasound (SAU), where an Aperture-to-Aperture loop serves as a self-supervised proxy task to ensure denoising fidelity. Simulation experiments, including noise levels from 0 to 30 dB and inclusion geometries from simple to complex, demonstrated improvements of 69.3% in SNR and 34.4% in CNR. The in vivo results showed 84.8% SNR and 25.7% CNR gains using only two aperture data of the heart in six echocardiographic views, liver, and kidney. PSCL delivers clear images across diverse imaging targets and configurations, paving the way for more reliable anatomical visualization without domain shift and pretraining costs.

Implicit Neural Representations (INRs) have recently shown impressive results, but their fundamental capacity, implicit biases, and scaling behavior remain poorly understood. We investigate the performance of diverse INRs across a suite of 2D and 3D real and synthetic signals with varying effective bandwidth, as well as both overfitting and generalization tasks including tomography, super-resolution, and denoising. By stratifying performance according to model size as well as signal type and bandwidth, our results shed light on how different INR and grid representations allocate their capacity. We find that, for many tasks involving dense signals, a simple regularized grid with interpolation trains faster and to higher or comparable quality than any INR with the same number of parameters. We also find limited settings -- namely fitting binary signals such as shape contours -- where INRs outperform grids, to guide future development and use of INRs towards the most advantageous applications.

Adversarial patches pose a practical threat to modern object detectors. Prior work shows vulnerability, but three gaps limit actionable insight: (i) few \emph{score-based black-box} attacks \emph{jointly} optimize patch \emph{location, texture, and size} under tight query budgets; (ii) success is rarely tied to the patch's \emph{visual footprint}; and (iii) evaluations often conflate EOT robustness with plain-view suppression. We present \method{}, a query-efficient, budget-adaptive black-box attack that couples a lightweight \emph{Contextual Thompson-Sampling} placer with NES-style pixel updates, growing the patch only when progress stalls. Reporting is anchored by a \emph{strict plain-image} suppression test; EOT is audited but never used as a substitute for success, and optional appearance/printability weights expose strength--visibility trade-offs. Across YOLOv5, Faster R-CNN, and YOLOS, \method{} achieves strong suppression on CNN-based detectors and substantial suppression on the transformer-based detector, using compact patches and exposing clear query--footprint trade-offs relative to fixed-size and heuristic baselines. A print--capture pilot further shows transfer across unseen physical objects and viewpoints.

Face Presentation Attack Detection (PAD) systems constitute a critical security layer in biometric authentication; however, existing approaches exhibit systematic performance disparities across demographic groups, disproportionately affecting individuals with darker skin tones. This paper presents a comparative empirical investigation of whether Vision Transformer architectures reduce demographic bias in face PAD systems relative to convolutional baselines. Experiments are conducted on the CASIA-SURF Cross-Ethnicity Face Anti-Spoofing (CeFA) dataset. Three architectures are evaluated: a Multimodal ViT-Tiny trained from scratch, a ResNet18 CNN baseline, and a pretrained DeiT-S fine-tuned on CeFA across African, East Asian, and zero-shot Central Asian demographic groups. DeiT-S achieves the highest overall accuracy of 97.27% and the lowest EER of 0.86%, outperforming ResNet18 at 90.15% accuracy. In terms of fairness, DeiT-S reduces the inter-ethnic ACER gap between African and East Asian subjects to 0.13%, compared to 0.75% reported in an LBP-based work [6], representing an 83% reduction. Most notably, while ResNet18 records a BPCER of 10.44% on zero-shot Central Asian subjects, DeiT-S maintains 2.89% on the same unseen group, demonstrating a 3.6x generalization advantage. These results suggest that pretrained Vision Transformers achieve superior PAD accuracy, produce smaller demographic performance gaps, and generalize more equitably across unseen demographic groups, indicating that cross-demographic fairness in PAD may partly be influenced by architectural design.

Recent advances in generative AI, such as diffusion models and face-swapping tools, have enabled the creation of highly realistic deepfakes, leading to real-world harms including financial fraud and non-consensual explicit content. In response, deepfake detection has become an active research area, with recent methods increasingly focusing on improving generalization to unseen manipulations. This is typically evaluated using the Area Under the ROC Curve (AUC) measured separately across multiple datasets. However, such an evaluation fails to reflect real-world scenarios where detectors face a mixture of data sources and varying artifact types. To address this limitation, we introduce a novel metric, Cross-dataset AUC (Cross-AUC) that averages per-domain AUCs with a measure of prediction polarization for taking into account the robustness to domain shift. The polarization extent is quantified by the Wasserstein Distance between class score distributions. Cross-AUC not only assesses the generalization capabilities of deepfake detectors under domain shifts more realistically, but it is also interpretable as it better explains the reason behind a drop in performance. Experiments performed on seven benchmark datasets demonstrate its practical relevance.

Text-rich images often contain privacy-sensitive, transactional, or decision-relevant information. As recent multimodal image generation models become increasingly capable of synthesizing realistic textual content and structured visual designs, detecting AI-generated text-rich images has become an important challenge for digital trust and content authenticity. Existing benchmarks, however, largely focus on object-centric images and provide limited coverage of scenarios where textual semantics and layout organization are central. In this paper, we introduce a multi-domain benchmark for detecting text-rich images generated by OpenAI's GPT Image 2. The benchmark contains 8,602 images across six representative categories: commercial posters, infographics, academic posters, receipts, tables, and UI screenshots. Using this benchmark, we evaluate five representative AI-generated image detectors in a zero-shot setting and analyze their overall, category-wise, and post-processing robustness. Our results show that detector performance is highly domain-dependent: methods that perform well in some categories often fail on others, and even the strongest conventional detector exhibits severe sensitivity to JPEG compression. We further conduct an exploratory evaluation with a multimodal vision-language model, revealing both its promise and its limitations on structured formats. These findings highlight the need for text- and layout-aware detection methods for modern AI-generated images. Our dataset is released at XXX.

Vision-language models (VLMs) are now widely used in downstream tasks. However, real-world applications often expose VLMs to distribution shifts induced by semantic variation (e.g., shape, size, and style). Robustness certification determines if a model's prediction changes when transformations are applied to its input. While most certification frameworks study geometric or pixel-level transformations over inputs, this work proposes a novel framework that enables certifying VLM robustness under semantic-level transformations. Leveraging the open-vocabulary capability of VLMs, we use text prompts as semantic proxies to construct transformations parameterized by an extent that controls the degree of semantic variation. By characterizing the VLM decision boundary in closed form, our framework quantitatively certifies extent intervals for which the predicted class remains unchanged under the semantic transformation. Our framework is the first to certify VLM robustness under semantic-level variations without requiring additional data for each variation, making it practical to apply. Experiments on both synthetic and real-world data show that our framework enables certifying robustness under diverse semantic variations across scenarios.

While prior research on text-to-image generation has predominantly focused on biases in human depictions, demographic bias in generated objects remains relatively underexplored. We introduce SODA (Stereotyped Object Diagnostic Audit), a novel framework for systematically measuring these biases through automated attribute discovery and three standardized metrics: Base vs. Demographic Divergence (BDS), Cross-Demographic Disparity (CDS), and Visual Attribute Concentration (VAC). Applying SODA to 8,000 images across five state-of-the-art models and eight object categories (e.g., cars), we find that "neutral" prompts produce outputs most visually similar to middle-aged and White people, suggesting these groups are implicitly over-represented in model defaults. Furthermore, demographic cues trigger highly skewed stereotypical outputs: 26.6% of object-model-demographic combinations produce results where all 20 generated images share the exact same attribute value (e.g., rose gold laptops for women). Finally, prompt-level debiasing reduces inter-group disparity but paradoxically collapses within-group diversity, replacing one stereotype with another. SODA offers a practical pipeline for making these implicit associations measurable, serving as a step toward more responsible AI development.

Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibility of hijacking multiple stateless decisions simultaneously using a single universal perturbation. We introduce the Semantic-Aware Universal Perturbation (SAUP), which acts as a semantic router, "actively" perceiving input semantics and routing them to distinct, attacker-defined targets. To achieve this, we conduct theoretical and empirical analysis on the geometric properties in the latent space. Guided by these insights, we propose the Semantic-Oriented (SORT) optimization strategy and annotate a new dataset with fine-grained semantics to evaluate performance. Extensive experiments on three representative MLLMs demonstrate the fundamental feasibility of this attack, achieving a 66% attack success rate over five targets using a single frame against Qwen.

The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent. To address this challenge, we propose Adv-TGD, a generative adversarial attack framework that synthesizes photorealistic faces capable of impersonating target identities and deceiving face recognition systems. Built upon Stable Diffusion v2.1, Adv-TGD performs per-sample LoRA fine-tuning conditioned on concise textual prompts to generate natural yet adversarially manipulated identities. Unlike conventional identity attack approaches, our method optimizes lightweight cross-attention adapters for each source-target pair within a fixed-timestep denoising process. Latent blending is constrained by a face-local heatmap mask to ensure spatially precise identity manipulation while preserving non-sensitive regions. We introduce a composite objective that integrates masked epsilon-MSE reconstruction, thresholded identity divergence in FR embedding space, directional feature alignment, and source-similarity suppression to balance adversarial attack and visual realism. Optionally, LLaVA-generated attribute prompts enhance fine-grained semantic details without reintroducing identity cues. Under the black-box evaluation protocol, Adv-TGD attains an average attack success rate (ASR) of 85.90% across IR152, IRSE50, MobileFace, and FaceNet, surpassing the semantic SOTA baseline Adv-CPG by 6.25 points, the diffusion-based makeup method DiffAIM by 3 points, and the noise-based P3-Mask by 16 points. Despite its strong attack efficacy, Adv-TGD preserves high visual fidelity (PSNR = 28.18 dB, SSIM = 0.981). Furthermore, we demonstrate the flexibility of our framework by successfully extending it to in-the-wild datasets (LADN), general object classification (ImageNet), and transformer-based diffusion models (FLUX.1).

Machine Unlearning (MUL) has emerged as a key mechanism for privacy protection and content regulation, yet current techniques often fail to guarantee the complete removal of sensitive information. While most existing works focus on verifying the execution of unlearning, they overlook the critical question of whether models remain robust against adversarial attempts to recover forgotten knowledge. In this work, we advocate for the principle of Robust Unlearning, which requires models to be both indistinguishable from retrained counterparts and resilient against diverse adversarial threats. To instantiate this principle, we propose a unified benchmark, RUB (Robust Unlearning Benchmark), that systematically evaluates the robustness of unlearning algorithms across classification, image-to-image reconstruction, and text-to-image synthesis. Within this framework, we introduce the Unlearning Mapping Attack (UMA) as a generalizable method to detect residual information, and demonstrate how existing attack strategies can be adapted into this framework as long as they conform to the generic UMA framework. Our experiments across discriminative and generative tasks reveal that state-of-the-art unlearning methods remain vulnerable under these evaluations, even when passing standard verification metrics. By positioning robustness as the central criterion and providing a benchmark for adversarial evaluation, we hope RUB paves the way toward more reliable and secure unlearning practices. The codebase and model checkpoints in RUB will be published.

Adversarial robustness of deep autoencoders (AEs) has received less attention than that of discriminative models, although their compressed latent representations induce ill-conditioned mappings that can amplify small input perturbations and destabilize reconstructions. Existing white-box attacks for AEs, which optimize norm-bounded adversarial perturbations to maximize reconstruction damage, often converge to suboptimal perturbations, thereby potentially overstating AE robustness. We show that this limitation is linked to vanishing adversarial loss gradients during backpropagation through ill-conditioned layers, associated with near-zero singular values in their intermediate weight matrices. To address this, we propose GRILL (Gradient Signal Restoration in Ill-Conditioned Layers), a framework designed to mitigate gradient degradation and improve the reliability of adversarial robustness evaluation in encoder-decoder architectures. GRILL is designed to mitigate adversarial gradient degradation during optimization, enabling attacks to better approximate high-distortion perturbations under fixed norm constraints. Through extensive experiments across multiple AE architectures, under both sample-specific and universal attacks, as well as standard and adaptive attack settings, we show that GRILL significantly increases attack effectiveness, thereby exposing vulnerabilities hidden by existing attack limitations. Beyond AEs, we provide preliminary evidence that modern multimodal encoder-decoder architectures exhibit similar vulnerabilities.

Edge-AI systems increasingly require real-time CNN inference under strict energy, performance, security, and privacy constraints. Approximate computing improves hardware efficiency by exploiting the error resilience of neural network workloads; however, most approximate CNN accelerators do not jointly consider secure, privacy-aware edge deployment. This paper presents SPARX, a Secure and Privacy-Aware Approximate CNN Acceleration framework integrated within a heterogeneous RV32IMC RISC-V System-on-Chip (SoC). SPARX combines a custom RISC-V instruction extension, an approximate logarithmic CNN acceleration unit, a lightweight differential-noise-based privacy engine, and a challenge-response authentication mechanism. To guide arithmetic selection, an approximation-aware decision framework is introduced that uses the Approximation Severity Index (ASI), Approximation Efficiency (AE), Quality of Approximation (QoA), Approximation Figure-of-Merit (AFOM), and Hardware Acceleration Efficiency (HAE). Evaluation across 11 state-of-the-art approximate MAC architectures identifies the Iterative Logarithmic Multiplier (ILM) as the most suitable design, achieving 51.7% area reduction, 81.5% power reduction, and 2.13x throughput improvement compared with an accurate radix-4 Booth MAC, while only reducing ResNet-20/CIFAR-10 accuracy by 2.82 percentage points. FPGA implementation on a Xilinx VC707 platform achieves 58.4 GOPS/W energy efficiency at 250 MHz, while 28-nm CMOS physical implementation validates ASIC feasibility

The Vines-DB dataset contains 1,218 original high-resolution RGB images of seven ornamental vine species collected under field conditions at the Utah Agricultural Experiment Station's Greenville Research Farm in Logan, Utah, USA. The dataset was generated from 168 individual vine plants that were transplanted in 2022 and photographed repeatedly across multiple months during the 2023 and 2024 growing seasons (July-October). Images were captured with an iPhone 16 Pro equipped with a 48 MP camera between 10:00 AM and 12:00 PM under daylight. Vines were grown on 1.2m x 2.4m trellises and photographed from a distance of 1m against black or white Styrofoam backdrops to improve contrast and reduce background noise. The dataset includes Akebia quinata, Campsis radicans, Hydrangea anomala petiolaris, Lonicera x heckrottii, Campsis x tagliabuana 'Madame Galen', Parthenocissus quinquefolia, and Wisteria floribunda. All original images were manually annotated in Roboflow by trained annotators to produce polygon-based instance segmentation masks for eight classes, including seven species and background. After preprocessing and data augmentation, the working dataset was expanded to 2,307 images for model development and evaluation. The augmented dataset was divided into 2,019 training images, 192 validation images, and 96 test images using stratified sampling to maintain balanced representation. Vines-DB supports the development and evaluation of deep learning models for multi-class instance segmentation in precision horticulture and urban ecology. The dataset enables applications such as automated canopy cover estimation, species identification, and scalable field phenotyping. In addition, repeated monthly imaging of the plants captures temporal variation in canopy development and plant appearance, increasing the dataset's utility for segmentation benchmarking under realistic field conditions.

The rapid advancement of text-to-image diffusion models has enabled the creation of highly photorealistic synthetic images that closely resemble real photographs, making it increasingly difficult to distinguish authentic content from AI-generated fabrications. This poses challenges for cybersecurity, digital forensics, and disaster response, where fake imagery of floods, fires, or earthquakes can spread misinformation or disrupt emergency operations. To address this, we introduce Forged Calamity, a benchmark dataset for synthetic disaster detection containing 30,000 images, including 6,000 real and 24,000 synthetic samples generated by four diffusion models. Comprehensive experiments across fine-tuned and zero-shot settings reveal consistent weaknesses in current forensic approaches. Fine-tuned detectors perform well in-distribution but lose up to 50\% accuracy on unseen generators or disaster types, showing overfitting to model-specific artifacts. Zero-shot generalized detectors also struggle to maintain stable accuracy, with only limited resilience in a few representation-robust models. These findings highlight persistent generalization gaps and the urgent need for domain- and model-agnostic detection methods to ensure visual authenticity in the diffusion era.

In the realm of computer vision, indoor image recognition presents challenges due to the intricate interplay of lighting conditions, occlusions, and diverse object arrangements within confined spaces. To address the lacks of training indoor images, we introduce a novel approach leveraging Stable Diffusion (SD) for the generation of synthetic images, which serve as a powerful data augmentation tool. The utilization of SD offers a principled framework for synthesizing diverse and realistic indoor scenes, thereby enriching the training data pool for robust indoor image recognition models. Experimental findings on the MIT Indoor Scene dataset reveal the potential of our proposed approach in enhancing the training of deep models when authentic data is limited. Furthermore, to prevent the misuse of SD synthetic images, we introduce a counter measure based on DIffusion Reconstruction Error (DIRE). The powerful DIRE presentation enables training robust classifiers only using lightweight deep models. Experiments show that our approach can perfectly recognize SD generated images with the accuracy of 100% using MobilenetV3.

An experimental investigation of neural image classification on the CIFAR-10 benchmark is presented through fully connected and convolutional network formulations. The analysis emphasizes the complete learning pipeline: image vectorization, normalization, one-hot class encoding, supervised loss minimization, learning-rate selection, mini-batch training, convolutional feature extraction, max-pooling, and validation-based generalization assessment. A convolutional architecture with six convolutional layers and three max-pooling stages is evaluated for ten training epochs using a batch size of 128 and an Adam optimizer with a learning rate of 0.001. The validation accuracy reaches approximately 74.77%, while the validation loss begins to increase after the middle of training despite continued reduction in training loss. The resulting behavior illustrates the practical difference between representation learning and memorization, and it provides a compact experimental baseline for future studies on regularization, data augmentation, deeper architectures, and reproducible image-classification education.

Air-ground collaborative perception is crucial for robust visual understanding in real-world dynamic environments. However, existing studies typically formulate collaboration as single-task cross-view fusion, overlooking the functional dependencies among localization, target association, and fine-grained parsing. In addition, the heterogeneous nature of aerial and ground views introduces substantial geometric, scale, and occlusion discrepancies, making uniform feature sharing vulnerable to negative transfer. To tackle these issues, we model air-ground perception as a progressive cross-task collaboration task and construct the Air-Ground Progressive Collaboration (AGPC) benchmark, a spatio-temporally aligned benchmark comprising more than 745K raw video frames. Built upon this benchmark, we propose Socialized Co-Perception (SCP), a coarse-to-fine framework that organizes collaboration progressively from aerial global localization to ground target association and identity-aware parsing. Its core module, the Dual-Layer Router (DLR), decouples input-side multi-scale expert selection from output-side task-conditioned modulation, enabling selective cross-view and cross-task interaction while suppressing harmful interference. Extensive experiments demonstrate the effectiveness of SCP. It achieves a 3.73\% coevolutionary gain and a 7.86\% improvement in average downstream performance. These results show that task-conditioned collaboration is more effective than uniform fusion for heterogeneous air-ground perception. The code is available at https://github.com/g1136639260-spec/AGSCP.

Video generative models ( VGMs) have become a new frontier that can be used not just for video generation but for a multitude of downstream tasks, including world modeling. To advance these tasks, a good video model must understand the physical reality of the world. Evaluating this understanding is an emerging field and has led to the Physics-IQ benchmark, which quantifies this explicitly by comparing model-generated videos to real-world videos of physical experiments. In this work, we present a systematic audit of the Physics-IQ benchmark, expose shortcomings and propose three solutions that sharpen how we can measure physical understanding of VGMs. Specifically, we improve prompt and ground-truth quality to reduce the influence of confounding factors and further introduce a sample-level scoring system that weights each sample and metric equally. Our resulting benchmark, Physics-IQ Verified, refines 57.6\% of all samples and improves over 34.8\% of prompts. In a comparison study using six image-to-video generative models, we observe moderate but meaningful ranking changes (Kendall's $τ= 0.46$). We hope Physics-IQ Verified advances the community by providing a more reliable signal toward physically accurate VGMs. The code for the benchmark can be accessed at https://github.com/google-deepmind/physics-iq-benchmark

Single-photon LiDAR (SPL) based on single-photon avalanche diode (SPAD) sensing enables time-resolved photon measurements with extreme sensitivity, offering unique potential for active 3D perception in photon-starved scenarios.However, real-world single photon perception remains fundamentally challenging due to unique measurement noise and complex multi-return transient phenomena, which jointly complicate geometric reconstruction and semantic scene understanding. Despite growing interest in SPAD-based sensing, existing studies are largely limited to simulated data or small-scale controlled captures. As a result, systematic evaluation of real-world single photon perception across depth estimation, multi-view reconstruction, and 3D semantic understanding remains underexplored. To bridge this gap, we introduce SP-TransientBench (STB), a real-captured multi-task benchmark for single photon perception. SP-TransientBenc comprises 10 diverse scenes and 10,297 views captured using a solid-state single-photon LiDAR at $256\times192$ resolution. Each view provides full time-of-flight histograms with multi-return behavior,standardized metadata, and calibrated camera poses for multi-view evaluation. We further provide 13-class 3D semantic annotations for selected scenes. By providing dedicated data splits and evaluation protocols for each task, STB enables consistent and reproducible benchmarking of real-world single photon perception across multiple 3D vision problems. The dataset and code will be released upon acceptance.

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception and reasoning capabilities. While numerous benchmarks have evaluated LVLMs from holistic or task-specific perspectives, their capabilities on fine-grained image tasks-fundamental to computer vision-remain insufficiently understood. To address this gap, we introduce FG-BMK, a comprehensive fine-grained evaluation benchmark containing 1.01 million questions and 0.28 million images, covering diverse scenarios from common object-centric domains to specialized domains. FG-BMK jointly evaluates dialogue-level fine-grained semantic recognition and feature-level visual discriminability through human-oriented and machine-oriented paradigms, enabling diagnostic analysis of whether LVLM failures arise from insufficient visual representations, weak visual-to-semantic grounding, or limited fine-grained knowledge. Through extensive experiments on a diverse set of representative LVLMs/VLMs, we find that current LVLMs remain inadequate fine-grained recognizers, with failures arising from intertwined bottlenecks in visual representations, semantic grounding, modality alignment, and category-level knowledge. We further analyze training design factors for improving fine-grained capabilities and examine how visual and linguistic perturbations affect LVLM predictions. These findings provide diagnostic insights into the limitations of current LVLMs and offer guidance for future data construction and model design in developing more reliable LVLMs for fine-grained visual tasks. Our code is open-source and available at https://fg-bmk.github.io/.

Training-free neural architecture search promises efficient discovery of high-performance networks without costly training. However, existing zero-cost proxies rely on fragmented heuristics that fail to capture the fundamental question: what makes an architecture trainable? This paper introduces Intrinsic Trainability (InTrain), a unified theoretical proxy that formalizes trainability as an architectural invariant emerging from two synergistic components: geometric capacity and optimization resilience. We operationalize intrinsic trainability through analysis of neural information processing. Geometric capacity is quantified via the participation ratio of activation covariance eigenspectrum, capturing the effective dimensionality of representation manifolds. Optimization resilience is measured through cumulative gradient health, assessing the robustness of backpropagation across network depth. InTrain synthesizes these dimensions through a scale-invariant multiplicative coupling, which we hypothesize is essential for capturing their synergistic, non-additive relationship. Extensive experiments on standard NAS benchmarks and search spaces demonstrate that InTrain achieves ranking correlations on par with state-of-the-art ensemble-based proxies and outperforms other single-metric methods.

In real-world applications, a machine learning model is required to handle an open-set recognition (OSR), where unknown classes appear during the inference, in addition to a domain shift, where the data distribution differs between the training and inference phases. Domain generalization (DG) aims to handle the domain shift situation where the target domain of the inference phase is inaccessible during the model training. Open domain generalization (ODG) considers DG and OSR. Domain-augmented meta-learning (DAML) is a method targeting ODG; however, it has a complicated learning process. By contrast, although various DG methods have been proposed, they have not been evaluated in ODG situations. In this study, we comprehensively evaluate the existing DG methods in ODG and show that the two simple DG methods, CORrelation ALignment (CORAL) and maximum mean discrepancy (MMD), are competitive with DAML in several cases. In addition, we propose simple extensions of CORAL and MMD by introducing the techniques used in DAML, such as ensemble learning and Dirichlet mixup data augmentation. The experimental evaluation demonstrates that the extended CORAL and MMD can perform comparably to DAML with lower computational costs. This suggests that the simple DG methods and their simple extensions are strong baselines for ODG.

Multi-graph matching is a fundamental problem in computer vision. Our work is motivated by a challenging application in bioimaging, where dozens or even hundreds of 3D microscopy images of worms must be brought into correspondence. Existing datasets do not cover this large-scale regime, and virtually all existing methods are inapplicable because they assume a complete or dense problem setting. To support further research, our first contribution is a new large-scale dataset based on problem instances from bioimaging. Our second contribution is a comprehensive analysis of the two main multi-graph matching paradigms: direct and permutation synchronization-based formulations. We argue, in part by proof, that practical large-scale methods must explicitly address problem sparsity and incompleteness. Since standard permutation synchronization approaches fail in this setting, we further introduce a sparse permutation synchronization paradigm. Our final contribution is GREEDA, a general method for sparse and incomplete problems that can be instantiated across cost orders and paradigms. While our paper focuses on objective functions up to quadratic order, GREEDA is inherently generalizable to arbitrary orders. On larger, sparse instances, GREEDA outperforms competing methods in both objective value and runtime. For example, for moderately-sized problems based on 30 worm images GREEDA produces a high-quality solution within 2 minutes, whereas competitors require at least half an hour and yield far worse results. On smaller dense problems, GREEDA remains on par with leading methods while being an order of magnitude faster.

Human head detection, keypoint estimation, and 3D head model fitting are essential tasks with many applications. However, traditional real-world datasets often suffer from bias, privacy, and ethical concerns, and they have been recorded in laboratory environments, which makes it difficult for trained models to generalize. Here, we introduce \method -- a large-scale synthetic dataset generated with diffusion models for human head detection and 3D mesh estimation. Our dataset comprises over 1 million high-resolution images, each annotated with detailed 3D head meshes, facial landmarks, and bounding boxes. Using this dataset, we introduce a new model architecture capable of simultaneous head detection and head mesh reconstruction from a single image in a single step. Through extensive experimental evaluations, we demonstrate that models trained on our synthetic data achieve strong performance on real images. Furthermore, the versatility of our dataset makes it applicable across a broad spectrum of tasks, offering a general and comprehensive representation of human heads.

Avoiding the risk of undefined categorical labels using nearest neighbor interpolation overlooks the risk of exacerbating pixel level annotation errors in augmented training data. Additionally, the inherent low pass filtering effects of interpolation algorithms exacerbate the risk of degrading high frequency structural details within annotated regions of interest. To avoid these risks, the author modified convolutional neural networks data transformation functions by incorporating a modified geometric transformation function, removing reliance on nearest neighbor interpolation, and integrating a mean-based class filtering mechanism to handle undefined categorical labels with alternative interpolation algorithms. The author also implemented an offline data augmentation pipeline to generate interpolation specific augmented training data, enabling quantitative assessment of interpolation specific low pass filtering effects on augmented training data. Experimental evaluation on three medical image segmentation datasets and the XBAT+ datasets demonstrated performance gains across multiple quantitative metrics.

We present UniTalk, a novel dataset emphasizing challenging scenarios to enhance model generalization for the task of active speaker detection (ASD). Previously established benchmarks such as AVA predominantly comprise old movies and thus exhibit significant domain gaps with real-world video. In contrast, UniTalk covers diverse video types reflecting challenging real-world conditions, including underrepresented languages, noisy backgrounds, and crowded scenes, while being on par with AVA in scale. Extensive evaluations reveal that ASD remains unsolved under realistic conditions: state-of-the-art models near-perfect on AVA fail to reach saturation on UniTalk. Conversely, models trained on UniTalk generalize better to modern in-the-wild datasets including Talkies and ASW. UniTalk thus establishes a new benchmark for ASD, providing researchers with a valuable resource for developing and evaluating versatile and resilient models.

Salient object detection exemplifies data-bounded tasks where expensive pixel-precise annotations force separate model training for related subtasks like DIS and HR-SOD. We present a method that dramatically improves generalization through large-scale synthetic data generation and ambiguity-aware architecture. We introduce S3OD, a dataset of over 139,000 high-resolution images created through our multi-modal diffusion pipeline that extracts labels from diffusion and DINO-v3 features. The iterative generation framework prioritizes challenging categories based on model performance. We propose a streamlined multi-mask decoder that handles the inherent ambiguity in salient object detection by predicting multiple valid interpretations. Models trained only on synthetic data achieve 20-50% error reduction in cross-dataset generalization, while fine-tuned versions reach state-of-the-art performance across DIS and HR-SOD benchmarks.

E-commerce short videos represent a high-revenue segment of the online video industry characterized by a goal-driven format and dense multi-modal signals. Current models often struggle with these videos because existing benchmarks focus primarily on general-purpose tasks and neglect the reasoning of commercial intent. In this work, we first propose a multi-modal information density assessment framework to quantify the complexity of this domain. Our evaluation reveals that e-commerce content exhibits substantially higher density across visual, audio, and textual modalities compared to mainstream datasets, establishing a more challenging frontier for video understanding. To address this gap, we introduce E-commerce Video Ads Benchmark, which is the first benchmark specifically designed for e-commerce short video understanding. We curated 3,961 high-quality videos from Taobao covering a wide range of product categories and used a multi-agent system to generate 19,785 open-ended Q&A pairs, which consist of five distinct tasks. Finally, we develop E-VAds-R1, an RL-based reasoning model featuring a multi-grained reward design called MG-GRPO. This strategy provides smooth guidance for early exploration while creating a non-linear incentive for expert-level precision. Experimental results demonstrate that E-VAds-R1 achieves a 109.2% performance gain in commercial intent reasoning with only a few hundred training samples. Data is available at https://github.com/TaobaoTmall-AlgorithmProducts/E-VAds_Benchmark.

Regressing 3D rotations of objects from 2D images is a crucial yet challenging task, with broad applications in autonomous driving, virtual reality, and robotic control. Existing rotation regression models often rely on large amounts of labeled data for training or require additional information beyond 2D images, such as point clouds or CAD models. Therefore, exploring semi-supervised rotation regression using only a limited number of labeled 2D images is highly valuable. While recent work FisherMatch introduces semi-supervised learning to rotation regression, it suffers from rigid entropy-based pseudo-label filtering that fails to effectively distinguish between reliable and unreliable unlabeled samples. To address this limitation, we propose a hardness-aware curriculum learning framework that dynamically selects pseudo-labeled samples based on their difficulty, progressing from easy to complex examples. We introduce both multi-stage and adaptive curriculum strategies to replace fixed-threshold filtering with more flexible, hardness-aware mechanisms. Additionally, we present a novel structured data augmentation strategy specifically tailored for rotation estimation, which assembles composite images from augmented patches to introduce feature diversity while preserving critical geometric integrity. Comprehensive experiments on PASCAL3D+ and ObjectNet3D demonstrate that our method outperforms existing supervised and semi-supervised baselines, particularly in low-data regimes, validating the effectiveness of our curriculum learning framework and structured augmentation approach.

The offshore wind energy sector is expanding rapidly, increasing the need for independent, high-temporal-resolution monitoring of infrastructure deployment and operation at global scale. While Earth Observation based offshore wind infrastructure mapping has matured for spatial localization, existing open datasets lack temporally dense and semantically fine-grained information on construction and operational dynamics. We introduce a global Sentinel-1 synthetic aperture radar (SAR) time series data corpus that resolves deployment and operational phases of offshore wind infrastructure from 2016Q1 to 2025Q1. Building on an updated object detection workflow, we compile 15,606 time series at detected infrastructure locations, with overall 14,840,637 events as analysis-ready 1D SAR backscatter profiles, one profile per Sentinel-1 acquisition and location. To enable direct use and benchmarking, we release (i) the analysis ready 1D SAR profiles, (ii) event-level baseline semantic labels generated by a rule-based classifier, and (iii) an expert-annotated benchmark dataset of 553 time series with 328,657 event labels. The baseline classifier achieves a macro F1 score of 0.84 in event-wise evaluation and an area under the collapsed edit similarity-quality threshold curve (AUC) of 0.785, indicating temporal coherence. We demonstrate that the resulting corpus supports global-scale analyses of deployment dynamics, the identification of differences in regional deployment patterns, vessel interactions, and operational events, and provides a reference for developing and comparing time series classification methods for offshore wind infrastructure monitoring.

The Atlantic Forest in Brazil is a critical biodiversity hotspot, yet less than 12-15% of its original cover remains. Although monitoring forest restoration on a large scale is essential, traditional methods are limited by the impracticality of on-the-ground reporting on such a scale and by the saturation of remote-sensing indices such as NDVI. Furthermore, reforestation is a gradual process as opposed to the rapid spectral changes caused by deforestation. In this study, we examine 1,729 restoration sites in São Paulo, using satellite embeddings from the AlphaEarth Foundation's model to evaluate their effectiveness in characterising early restoration success. We introduce the concept of a 'Reference Trajectory Embedding', defining a metric of restoration success based on cosine similarity to reference sites of mature secondary forest. We observe distinct clusters in embedding space according to different land use and land cover (LULC) types, and we can identify sites with clear change vectors. However, the signal can be noisy, and embeddings may require further fine-tuning to capture and predict site metadata beyond LULC.

Accurate, spatially explicit characterization of tropical forest structure is essential for carbon accounting and ecosystem monitoring, yet most ML pipelines predict canopy-top height proxies (e.g., RH95/RH98) or AGBD as separate scalar targets, rather than learning the forest vertical structure as an ordered profile. The community lacks a ML-ready multimodal benchmark for predicting the entire GEDI RH profile jointly with AGBD, or for evaluating methods that enforce physically consistent ordering across RH percentiles. We address this with Biomazon, a 20 m multimodal benchmark dataset over the Amazon Basin that pairs GEDI RH and AGBD targets with multi-sensor predictors (Sentinel-1/2, ALOS-2 PALSAR-2, Copernicus DEM, Dynamic World LULC, and AlphaEarth embeddings) under standardized spatial splits and evaluation protocols. Using a shared encoder-decoder with task-specific heads as a baseline framework, we conduct a comprehensive ablation study of (i) backbone/model scale, (ii) modality contributions, and (iii) the use of auxiliary embeddings under standalone and fusion settings, and we report both single-target and joint-target results to quantify tradeoffs under a unified training protocol. Finally, we contextualize baseline performance through regionally aligned comparisons against existing gridded products, including GEDI L4D RH10-RH98 and AGBD, at matching temporal scale. Biomazon, together with the accompanying protocols and baseline results, establishes a reference benchmark for future work on structurally consistent RH-profile prediction and structure-biomass modeling in tropical forests.

Dataset condensation aims to construct compact datasets from real data via synthesis or selection. However, existing approaches are ill-suited for diffusion model training: synthetic data generation often yields low-fidelity samples unsuitable for authentic modeling, while real subset selection typically fails to preserve the distributional geometry required by diffusion likelihood objectives. To address this, we propose to reformulate real subset selection as a geometry-aware distribution alignment problem. By incorporating one-sided partial optimal transport, our method selectively aligns a compact subset with the full data distribution while allowing unmatched mass in low-density regions, ensuring the preserved geometric structure necessary for effective diffusion model training. To further ensure distributional fidelity, we complement geometric alignment with lightweight feature-statistics and semantic consistency regularization. An efficient two-stage discrete optimization strategy is proposed to achieve this alignment objective. Extensive experiments across diffusion variants, subset sizes, image resolutions, and training rounds show that our method achieves superior fidelity and distributional coverage in diffusion model training. Codes are available at https://github.com/2018cx/GADC.

Current automated pipelines for audio-visual Question Answering (QA) generally adopt a ``video-caption-QA'' paradigm. However, these methods typically segment videos into short clips and generate separate descriptions for audio and visual modalities. This decoupled processing severs inherent associations between sounds and their visual sources, while independent clip processing often causes inconsistent descriptions of the same entity across segments. Furthermore, coupling long-text comprehension and QA synthesis into a single step often restricts models to localized events, yielding questions lacking long-term temporal connections and deep cross-modal reasoning. To address these issues, we propose an automated data engine featuring two mechanisms: (1) \textbf{Entity-Anchored Video Scripting} transforms videos into structured scripts, comprising summaries, main entity lists, and segment-wise audio-visual descriptions. The entity list serves as a global prior to ensure cross-segment referential consistency and reconstruct audio-visual associations. (2) \textbf{Clue-Guided QA Generation} prompts models to first mine cross-segment, multimodal clues from the script, and subsequently generate QA pairs based on these high-value clues. Leveraging this pipeline, we construct the instruction-tuning dataset \textbf{OmniVideo-100K} and a human-verified test set, \textbf{OmniVideo-Test}. Fine-tuning VITA-1.5, Qwen2.5-Omni-7B and Qwen3-Omni-30B on OmniVideo-100K yields performance gains of up to 20.59% on OmniVideo-Test, demonstrating strong generalization (up to 12.64% improvements) across established benchmarks like Daily-Omni and JointAVBench.

Current multilingual evaluations for Vision-Language Models (VLMs) assume a one-to-one mapping between language and orthography, overlooking billions of users of multi-script languages. We introduce PuMVR (Punjabi Multimodal Visual Reasoning), a benchmark of 1,000 strictly parallel image-text instances across Punjabi's three active scripts: Gurmukhi, Shahmukhi, and Roman. Evaluating 10 state-of-the-art VLMs, we expose a substantial and systematic Script Gap. Models frequently solve visual tasks in one script while failing identical tasks in another, with accuracy deltas reaching 16%. Crucially, visual input boosts absolute performance uniformly yet does not close the orthographic gap. Furthermore, cross-script in-context transfer is highly brittle, exposing script-locked knowledge representation. Supported by McNemar tests across all script pairs, our findings demonstrate that current "multilingual" VLMs are not truly multi-script. We propose the Script Consistency Rate (SCR), which falls as low as 24.8% on our benchmark, as a mandatory metric for script-agnostic evaluation to ensure equitable AI access. Data and code are available at: https://github.com/prabhjotschugh/Not-Truly-Multilingual-PuMVR.

The development of Time-Series Forecasting (TSF) models is often constrained by the lack of comprehensive datasets, especially in Global Station Weather Forecasting (GSWF), where existing datasets are small, temporally short, and spatially sparse. To address this, we introduce WEATHER-5K, a large-scale observational weather dataset that better reflects real-world conditions, supporting improved model training and evaluation. While recent TSF methods perform well on benchmarks, they lag behind operational Numerical Weather Prediction systems in capturing complex weather dynamics and extreme events. We propose PhysicsFormer, a physics-informed forecasting model combining a dynamic core with a Transformer residual to predict future weather states. Physical consistency is enforced via pressure-wind alignment and energy-aware smoothness losses, ensuring plausible dynamics while capturing complex temporal patterns. We benchmark PhysicsFormer and other TSF models against operational systems across several weather variables, extreme event prediction, and model complexity, providing a comprehensive assessment of the gap between academic TSF models and operational forecasting. The dataset and benchmark implementation are available at: https://github.com/taohan10200/WEATHER-5K.

In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of (1) a weighted Mean Square Error (wMSE) loss and (2) a Cross-Entropy loss incorporating soft labels. Thanks to the decoupled structure of DKL loss, we have identified two areas for improvement. Firstly, we address the limitation of KL loss in scenarios like knowledge distillation by breaking its asymmetric optimization property along with a smoother weight function. This modification effectively alleviates convergence challenges in optimization, particularly for classes with high predicted scores in soft labels. Secondly, we introduce class-wise global information into KL/DKL to reduce bias arising from individual samples. With these two enhancements, we derive the Generalized Kullback-Leibler (GKL) Divergence loss and evaluate its effectiveness by conducting experiments on CIFAR-10/100, ImageNet, and vision-language datasets, focusing on adversarial training, and knowledge distillation tasks. Specifically, we achieve new state-of-the-art adversarial robustness on the public leaderboard -- RobustBench and competitive knowledge distillation performance across CIFAR/ImageNet models and CLIP models, demonstrating the substantial practical merits. Our code is available at https://github.com/jiequancui/DKL.

Generalist embodied agents require more than object recognition: they must reason about spatial relations, actions, procedures, human intentions, environmental constraints, and commonsense consequences from situated visual observations. Yet existing visual and embodied question answering benchmarks often provide limited control over the reasoning dependencies being tested, making it difficult to distinguish grounded embodied reasoning from shortcut-driven visual or linguistic pattern matching. We present ERQA-Plus, a diagnostic benchmark for reasoning in embodied AI. ERQA-Plus contains 1,766 question-answer instances grounded in 711 robot-centric images and organized according to a structured taxonomy spanning perceptual, action-centric, social-interaction, navigation-environmental, and contextual commonsense reasoning. The dataset is constructed using a multi-stage generation and validation pipeline that combines taxonomy-guided question generation, automatic quality judging, iterative revision, and human assessment to improve visual grounding, answer validity, and reasoning quality. We benchmark representative general-purpose vision-language models and embodied models, including LLaVA-NeXT-8B, Prismatic-7B, MiniCPM-V-4.5-8B, Qwen3-VL, RoboRefer-8B, and RoboBrain2.5-8B. Although the strongest model, Qwen3-VL-32B, achieves 83.4% overall accuracy and 61.4 SBERT score, category-level results reveal persistent weaknesses in spatial reasoning, procedural reasoning, event prediction, and intention inference. ERQA-Plus therefore provides a fine-grained evaluation framework for measuring not only whether embodied agents answer correctly, but also which forms of embodied reasoning they can and cannot perform reliably. The dataset is available https://huggingface.co/datasets/huggingdas/erqa-plus and the project page at https://github.com/LUNAProject22/erqa-plus.

Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual limitations and domain hallucinations in complex geological scenarios. To address these challenges, we propose an instruction-driven agentic framework comprising three components. First, LandslideBench, a multimodal fine-grained dataset with seven subtype labels, high-resolution imagery, pixel-level masks, and high-quality textual descriptions, is constructed via multi-VLM cross-validation and interactive annotation. Then, LandslideVLM, a landslide-oriented VLM, is fine-tuned via LoRA on LandslideBench to enhance geological semantic understanding. Finally, LandslideAgent, a domain rule-enhanced agent taking LandslideVLM as its cognitive backbone, employs a dual-rule controller incorporating structured report metadata constraints and cross-validation identification constraints to regulate automated tool invocation. Experiments demonstrate that LandslideBench provides effective baselines across five mainstream models on fine-grained classification and semantic segmentation. LandslideVLM achieves accuracy improvements of 10.96%, 32.87%, and 15.91% on landslide discrimination, fine-grained classification, and semantic description quality, respectively. LandslideAgent further enables autonomous multi-source spatial data inference, realizing full-process intelligence for landslide identification and analysis.

Despite the widespread adoption of Vision Transformers (ViTs) and their success across numerous computer vision applications, the fundamental understanding of their dimensional and representational geometry remains relatively underexplored. To address this gap, we introduce Transformer Geometry Observatory (TGO), a systematic framework of experiments and analysis pipelines designed to investigate the representational geometry and dynamics of Vision Transformers. TGO-I, the first installment of the framework, focuses on the spectral geometry of ViT representations. Using a ViT-Small/16 model trained on ImageNet-100, we analyze Effective Rank, Stable Rank, Participation Ratio, Spectral Entropy, Spectral Flatness, Spectral Anisotropy, covariance structure, eigenspectra, and singular value spectra throughout training. Our results reveal a consistent increase in dimensional utilization, accompanied by decreasing anisotropy, increasing spectral entropy, increasing participation ratio, and progressively flatter eigenspectra. Contrary to the common intuition that training should concentrate information into a small number of dominant directions, we observe a progressive redistribution of variance across representational dimensions. This phenomenon is particularly pronounced in the final CLS token representation, which exhibits the highest effective dimensionality and lowest anisotropy within the network.

Valuable critique of generative image models within visual culture and the humanities has emphasized the role of datasets in shaping the images they produce. Yet, close studies of the ideological positions embedded into the mechanism of the models have been neglected, leaving them imagined as "black boxes." In a bid to expand, rather than replace, dataset critique, this paper examines the mechanisms of the latent diffusion model in terms of the problems they were brought in to solve on behalf of computer vision engineers, and the decisions each component was tasked with automating. I interpret that ensemble through the histories of its parts and the theory of vision the system inscribes into every generated image. Drawing on Impett and Offert's notion of neural exchange value, I offer this analysis to argue that the model operates as a neural economy: a contained symbolic system that abstracts social communication into commensurable vectors as it transfers the social sphere into parcels for sale. Tracing the training and generation pipelines component by component reveals what each operation displaces, and how it further entrenches the logics of platform and attention economies over social communication. The paper warns that any critique fixated exclusively on copyright and commodity defenses risks reaffirming the very fetishism the model produces, and argues instead for centering social exchange.