Computer Vision
PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
Yaolong Zhu, Peng Li, Jiahao Lu et al. (+8 more)
Feed-forward 3D reconstruction models have achieved remarkable progress through large-scale training and strong learned priors. However, they remain fragile when applied to dynamic in-the-wild
videos, where non-rigid motion, occlusions, and illumination changes are prevalent. A key limitation lies in their reliance on expensive depth and camera pose annotations, which hinders scaling to diverse real-world dynamic data and restricts generalization. To address this issue, we propose PURE, an unlabeled post-training refinement framework that improves depth and camera estimation without requiring ground-truth supervision. Instead of relying on annotations, PURE elegantly distills robust structural knowledge from state-of-the-art 2D priors into 4D feed-forward architectures. PURE leverages relative depth constraints, affine-invariant geometry
distillation, and pose refinement based on feature correspondences to stabilize
geometric predictions under challenging dynamic conditions. Extensive experiments on both synthetic and real-world dynamic
benchmarks demonstrate that PURE delivers consistent improvements across multiple state-of-the-art architectures. Furthermore, our data-efficient paradigm effectively mitigates domain shifts, successfully unlocking the architectural limits of these base models in challenging, in-the-wild dynamic scenes.
Read the full abstract ▾
All authors Yaolong Zhu, Peng Li, Jiahao Lu, Chengfeng Zhao, Mengfei Li, Chao Wang, Wenyue Chen, Zekai Gu, Chengwei Ren, Ronggang Wang, Yuan Liu
Computer Vision
Demiurge: Forging Navigable 4D Worlds via Autoregressive Video Rerendering
Hanxin Zhu, Jianqi Ma, Cong Wang et al. (+10 more)
Recent advances in
video diffusion enable novel-view
video synthesis from a single input
video, supporting world modeling, embodied intelligence, and robotic simulation. However, existing methods process camera trajectories independently, lacking the cross-trajectory consistency needed for coherent, navigable 4D worlds. We introduce Demiurge, an autoregressive
video rerendering pipeline built on a dynamic 4D point-cloud
memory cache. It promotes cross-trajectory consistency through four components: (1) an appearance
video diffusion model that synthesizes photorealistic novel-view
videos conditioned on the 4D
memory; (2) a
memory-consistent
video depth completion model that aligns known-region depths with cached geometry and completes missing regions, mitigating scale ambiguity and discontinuities during
memory updates; (3)
memory-aware dual-stream warping that provides high-fidelity visual guidance and occlusion cues for novel-view synthesis; and (4) geometry-aware
video refinement that enhances perceptual quality. Extensive experiments demonstrate state-of-the-art performance and three key capabilities: coherent spatiotemporal
lattice construction over dense multi-view trajectories; large-parallax
video rerendering under challenging camera motions, including 180-degree rotations with no input-view overlap; and geometry-faithful outputs that can be directly optimized into high-quality 3D Gaussian Splatting representations with minimal artifacts. Project page: https://hanxinzhu-lab.github.io/demiurge_project_page/.
Read the full abstract ▾
All authors Hanxin Zhu, Jianqi Ma, Cong Wang, Zhihao Hu, Junyao Gao, Tianyu He, Junyan Lin, Jiayin Xiao, Jiateng Shou, Sen Liang, Weidong Zhang, Zhibo Chen, Jun Zhang
Computer Vision · Cross-listed from cs.AI
A Hybrid Kinematic GCN and Elastic Transformer for Efficient Indian Sign Language Recognition
Pushp Garg, Himangshu Sarma and Mrinmoy Ghorai
Sign
Language Recognition (SLR) presents complex challenges due to variable signing speeds and spatial intricacies. Specifically, Indian Sign
Language (ISL) requires precise modeling of its inherently bimanual nature and is bottlenecked by the scarcity of large-vocabulary
benchmarks and the inability of standard models to handle irregular signing velocities. To address this, a structurally-aware hybrid framework for efficient, gloss ISL recognition is proposed. To minimize computational redundancy, an
entropy-driven SVD sampler that dynamically extracts informative keyframes is used. Because this subsampling creates irregular physical time gaps, the proposed architecture employs a Continuous Dual Positional Encoding paired with a distance-aware Elastic
Transformer to preserve natural signing rhythm. Spatially, a Kinematically-Conditioned Adaptive GCN explicitly models bimanual geometry using unified bone-joint features. To validate our framework, a 120-class, 9,453-
video native ISL
dataset is created. Augmented by Physical Node Dropout and ArcFace optimization to mitigate subject-specific memorization, our framework achieves a competitive 89.8% accuracy, establishing a strong baseline for complex sign
language modeling.
Read the full abstract ▾
Computer Vision
HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning
Yiming Zhang, Enzhi Zhou, Junan Lin et al. (+4 more)
We introduce HumanPhys, a human-centric
benchmark for real-world physical perception, and a training corpus emitted by the same pipeline. Each question targets a physically grounded quantity related to people, including depth, inter-person distance, gaze angle, displacement, velocity, heading-step trajectory, blink count, and contact-deformation strength. The rendered probes additionally test illumination inference from body and face cues and camera ego-motion, both with and without a person in the frame. All labels are derived programmatically from sensor calibration, source metadata, or renderer state, rather than written by annotators or produced by
estimators on the
benchmark frames. HumanPhys systematically probes six dimensions of human-centric physical perception: spatial state, kinematics, blink events, deformation, illumination, and camera pose. To the best of our knowledge, no existing MLLM
benchmark-and-training corpus jointly supervises this set of human-centered physical quantities under direct metadata- or renderer-derived labels. The six dimensions appear only partially dissociable across the tested MLLMs. We
benchmark a range of open- and closed-source MLLMs on HumanPhys and find that all six capability dimensions remain challenging for current models. We hope HumanPhys will support future research on
multimodal systems that perceive and reason about people in the physical world.
Read the full abstract ▾
All authors Yiming Zhang, Enzhi Zhou, Junan Lin, Dulan Zhou, Weiqiang Wang, Yuge Huang, Jian Liu
Computer Vision
CAST-ASD: Causal Attention over Speakers and Time for Online Active Speaker Detection
Pratham Gupta, Haotian Qi, Tushar Sandhan et al. (+1 more)
We present CAST-ASD (Causal
Attention over Speakers and Time), a causal joint model for active speaker detection (ASD). Recent ASD models improve performance by jointly processing all faces in a scene, but operate offline, with the full clip available before any frame is labelled. Low-latency causal detectors instead process each face independently. CAST-ASD combines joint face
reasoning with fully causal inference. It applies scene-level
attention across faces within the current frame and causal temporal
attention over each face's history, enabling information sharing across speakers with zero lookahead. Its parameter count does not grow with the number of faces. On MSDWild, where most negative face-frames contain a visible competing speaker, CAST-ASD reduces competing-speaker false alarms by 32% relative to the causal per-face detector it extends, with larger gains as scene occupancy increases. It outperforms all causal baselines on both validation splits while using only one-tenth the inter-speaker parameters of a three-block fixed-roster convolution. Code and models are available at https://github.com/prathamg007/CAST-ASD.
Read the full abstract ▾
All authors Pratham Gupta, Haotian Qi, Tushar Sandhan, Gabriel Skantze
Computer Vision
Competition Domains Matter: Selective Head Globalization for Training-Free Sparse Attention in Video Diffusion Transformers
Tiantian Liu, Meng Wan, Zhiqiang Liang et al. (+3 more)
Training-free sparse
attention is a practical route to efficient
video diffusion transformer inference, yet existing methods typically fix the competition domain at each query row for every
attention head. Prior work primarily addresses how to estimate
token-level importance within this fixed domain; whether the domain itself should adapt to head heterogeneity remains under-specified. We introduce EG-Sparse, a training-free framework that routes low-
entropy heads to a grouped cross-head pool while retaining per-row local selection for high-
entropy heads, using only scores already materialized by the sparse pipeline. A controlled diagnostic fixes the ranking score and varies only the competition rule: grouped cross-head selection reduces low-
entropy-head reconstruction error by 9.8%, whereas forcing high-
entropy heads into an all-head global pool increases it by 7.9%. Across four configurations, EG-Sparse achieves higher
video quality while reducing
attention density and GPU denoising latency compared with strong training-free sparse-
attention baselines. Mechanism ablations further show that selective domain adaptation outperforms uniform, random, and fixed domain-assignment policies. These results support competition-domain adaptation as a distinct design axis within centroid-guided training-free sparse
attention.
Read the full abstract ▾
All authors Tiantian Liu, Meng Wan, Zhiqiang Liang, Jue Wang, Ningming Nie, Yangang Wang
Computer Vision
SPARE: Shared Perception and Adaptive Retrieval of Evidence for Streaming Video Understanding
Senbin Xu, Zijun Zhang, Xinhua Wu et al. (+7 more)
Streaming
video understanding requires answering questions from the observed
video, with evidence drawn from recent observations or earlier events. Historical context can improve recall but may interfere with judgments based on recent frames. Its usefulness depends on both when it is introduced and which clips are selected, while relevance alone does not guarantee sufficient evidence for an answer. We propose SPARE, a framework that combines adaptive historical
retrieval with visual encoder sharing. A lightweight gate predicts whether recent observations provide sufficient evidence to answer the question. When additional evidence is predicted to be necessary, a
multimodal embedding model retrieves relevant historical clips to supplement the current context. LoRA instruction tuning trains the understanding model to use recent observations and retrieved history jointly and abstain when the evidence remains insufficient. To reduce redundant visual parameters, the understanding and
retrieval branches share a visual encoder while retaining separate
language backbones. Four linear adapters align the shared features with the
retrieval model through
distillation at the visual
token and final
retrieval embedding levels. With visual-only inputs, SPARE achieves 77.78% on the evaluated Real-time and Backward task groups of OVO-Bench and 73.31% on StreamingBench. Compared with Qwen3-VL-8B-Instruct evaluated at 2 fps, SPARE improves accuracy by 20.68 percentage points on OVO-Bench and 14.15 percentage points on StreamingBench.
Read the full abstract ▾
All authors Senbin Xu, Zijun Zhang, Xinhua Wu, Li He, Jubo Feng, Li Qiao, Zhen Gao, Yan Zhang, Jixiang Luo, Rongrong Ji
Computer Vision
TETRIS-4DGS: Efficient Post-Training Compression of 4D Gaussian Splatting
Chengzhen Wu, Kelei Liu, Sicheng Li et al. (+2 more)
4D Gaussian Splatting (4DGS) has emerged as a powerful dynamic scene representation, supporting real-time high quality rendering but suffers from prohibitive storage overhead. Existing methods typically attempt to solve this by treating compression as a per-scene optimization problem, limiting generalizability and applicability where low-latency compression is required. In this work, we leverage existing image and
video codecs and propose a generalized post-training compression framework for 4DGS to address these issues. Specifically, we apply importance-based adaptive quantization to Gaussians according to their importance levels, effectively refining bitrate allocation while remaining fully compatible with existing codecs. To further improve compression efficiency, we utilize the statistical properties of 4DGS and propose motion- and importance-aware packing to reorganize attributes into codec-friendly 2D maps. Our approach can achieve over 40x compression rate in seconds while maintaining high quality, facilitating the practical deployment of 4DGS.
Read the full abstract ▾
All authors Chengzhen Wu, Kelei Liu, Sicheng Li, Lu Yu, Yiyi Liao
Computer Vision
TGuide: Faster Autoregressive Video Diffusion via Historical Trajectory Guidance
Zhuo Chen, Bin Zou, Fanyue Wei et al. (+3 more)
Can autoregressive
video diffusion be accelerated further when only four denoising steps remain? Existing feature caching approaches struggle in this regime, as large feature changes between denoising timesteps undermine both direct reuse and lightweight predictors. We observe that features across
video chunks remain strongly correlated at matching denoising timesteps, offering a complementary source of guidance. Building on this insight, we introduce TGuide, a framework that accelerates autoregressive
video diffusion through a lightweight Anchor-Transport-Correct (ATC) predictor guided by historical sampling trajectories. Our ATC combines two complementary references: the current chunk's preceding-step features preserve its spatial structure, while the previous chunk's same-timestep features provide information at the target denoising stage. By integrating these references through spatial
retrieval and adaptive correction, ATC improves velocity prediction accuracy despite the large gaps between denoising steps. To mitigate error accumulation across both denoising steps and
video chunks, we train the predictor on its own autoregressive rollouts, allowing it to adapt to states shaped by its own earlier predictions. An optional confidence-aware scheduler further adjusts the quality-efficiency trade-off. Experiments on Self Forcing, Causal Forcing, and HY-WorldPlay show that TGuide preserves generation quality while achieving denoising speedups of up to $1.89\times$ over the original 4-step generators. On Self Forcing, TGuide generalizes from 81-frame training
videos to 333-frame generation, approximately four times the training length, while exceeding the original model's VBench score.
Read the full abstract ▾
All authors Zhuo Chen, Bin Zou, Fanyue Wei, Lixin Duan, Angela Yao, Wen Li
Computer Vision
Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion
Yifan Shen, Yewei Xia, Gongxu Luo et al. (+6 more)
Autoregressive
video generators synthesize long
videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate future. This limited prediction horizon makes it challenging to maintain
video quality over extended rollouts. To address this problem, we introduce Prospective Forcing, a multi-head prediction framework that injects long-range predictive signals into autoregressive
video representations. Built on a rolling-window generator, Prospective Forcing attaches lightweight, offset-specific heads that share the same conditioning information and independently predict chunks at different future temporal offsets. By extending supervision beyond the next chunk, these heads encourage the shared history representation to retain information useful for longer-horizon prediction, supporting temporally consistent generation. At inference time, we accelerate sampling by using accepted future-chunk predictions to skip full-window backbone executions. We equip the head with learnable
embeddings to generate multiple candidates for the next chunk, and a learned verifier either selects a candidate or rejects all and falls back to standard autoregressive generation.
Read the full abstract ▾
All authors Yifan Shen, Yewei Xia, Gongxu Luo, Peiyuan Zhu, Boyang Sun, Zhenhao Chen, Guangyi Liu, Guangyi Chen, Kun Zhang
Computer Vision
TAG: Calibrating SAM3 for Universal Image Segmentation without Dense Supervision
Hao Zhu, Heyu Sun, Shuo Jin et al. (+2 more)
The recent Segment Anything Model 3 (SAM3) extends powerful promptable segmentation from spatial cues to concepts, raising the prospect of a single foundation model for universal image segmentation. However, this promise often fails to translate into reliable performance on downstream segmentation tasks. In this work, we empirically identify concept recognition, rather than mask quality, as the primary bottleneck: SAM3 accurately delineates the objects it recognizes yet struggles to robustly determine which concepts are present. Driven by this, we present \textit{\underline{T}ext \underline{A}nchor re-\underline{G}rounding (\TAG{})}, a simple yet effective framework that rectifies the concept recognition of SAM3 on the target domain without dense annotations. Specifically, \TAG{} introduces an Anchor Residual Pathway comprising image-conditioned, low-rank adapters to re-ground text anchors in the target distribution and modulate subsequent text-conditioned interactions. Guided solely by image-level category labels, \TAG{} jointly optimizes binary cross-
entropy with Soft Boundary Ranking objectives to calibrate presence confidence and distinguish present concepts from confusable negatives. Building upon this, we devise Confidence-Weighted
Distillation to couple rich semantic context of a
multimodal large
language model with fine-grained spatial priors of SAM3, thereby achieving effective calibration in the absence of manual annotations. Extensive experiments demonstrate that \TAG{} unlocks SAM3's segmentation potential with only 3.1M trainable parameters, achieving impressive performance across diverse scenarios, and notably, even surpassing leading mask-supervised methods on several metrics. \href{https://github.com/MiSsU-HH/TAG_SAM3}{Our code will be publicly available at GitHub \faGithub}.
Read the full abstract ▾
All authors Hao Zhu, Heyu Sun, Shuo Jin, Jiayu Xiao, Feng Dai
Computer Vision
Can Synthetic UAV Benchmarks Be Trusted? Real-Synthetic Validation for UAV Model Selection
Yuyi Zhi, Min Du, Bill Shi et al. (+4 more)
Synthetic
UAV imagery can expand pre-deployment test evidence when task-specific Real data are scarce, but visual plausibility or semantic label
alignment alone does not establish validity for model selection. We study when Synthetic evaluation preserves the model-selection conclusions obtained from Real
UAV data through two complementary cases under fixed evaluation protocols. In a requirement-specific road-debris
benchmark, four
language-conditioned perception systems obtain lower absolute F1 on Synthetic data, yet the point-estimate ordering and top-ranked model are preserved; bootstrap analysis yields no supported pairwise reversal, and size-matched resampling preserves the top-model decision. In contrast, a closed-set stress test on a separately materialized business corpus, using four VisDrone-compatible detectors over eight empirically supported classes, changes the point-estimate top-ranked detector and reverses three of six pairwise point-estimate preference directions. A complementary audit of five
UAV business scenarios further reveals substantial Real-Synthetic mismatch in class composition, object density, and target scale, including systematic under-representation of small targets. These results show that Synthetic
UAV benchmark trust is conditional: semantic coverage is insufficient, and validity must be established empirically for the task, operating regime, and model panel of interest.
Read the full abstract ▾
All authors Yuyi Zhi, Min Du, Bill Shi, Guodong Yuan, Junheng Liang, Peifan Liao, Xin Guan
Computer Vision · Cross-listed from cs.CL
PVFH-Bench: Benchmarking Premise-Induced Visual Fixation Hallucinations in Vision-Language Models
Xinhao Wang, Junbo Cui, Zhenghao Liu et al. (+4 more)
Large
Vision-
Language Models (LVLMs) have achieved remarkable progress across a wide range of
multimodal tasks. However, object
hallucination remains a persistent challenge, undermining model reliability in applications such as visual question answering, embodied
agents, and human-AI decision support systems. In this paper, inspired by cognitive science studies on perceptual bias, we investigate a new failure mode termed Premise-Induced Visual Fixation
Hallucination (PVFH). Specifically, PVFH refers to a premise-induced
reasoning error in which models become anchored to visually confusable evidence, accept a false textual premise, and subsequently generate responses about an absent yet visually plausible object. To systematically study this phenomenon, we introduce PVFH-Bench, a
benchmark that automatically constructs visually confusable but absent targets and pairs the core
hallucination setting with diagnostic subsets to trace how models move from object recognition to Premise-Induced Visual Fixation
Hallucination. Experimental results on 10 state-of-the-art LVLMs demonstrate that all evaluated models are highly vulnerable to Premise-Induced Visual Fixation
Hallucination. Moreover, we find that explicit chain-of-thought
reasoning can further exacerbate this failure mode by encouraging models to overinterpret weak visual cues as supporting evidence for hallucinated objects.
Read the full abstract ▾
All authors Xinhao Wang, Junbo Cui, Zhenghao Liu, Yuan Yao, Xiaohua Li, Yu Gu, Ge Yu
Computer Vision
Automatic assembly modeling through attention-based assembly feature mate prediction and assembly feature pattern recognition
Ziheng Dai, Wanbin Pan, Zhihong Tang et al. (+1 more)
Assembly modeling plays an important role in constructing product models, yet it is still mainly performed via interactive operations that are experience-dependent and labor-intensive. Data-driven strategies hold promise for automating this process; however, existing approaches either predict poses that cannot directly generate editable B-Rep assembly constraints or require prescribed part pairs or predefined assembly faces. To reduce the large candidate space of constraint prediction without predefined assembly faces, we propose a data-driven framework based on assembly feature mate prediction. The framework performs automatic assembly modeling from unassembled B-Rep parts, using assembly features to group the
geometric entities of local mating interfaces and restrict candidate formation. Given the lack of suitable assembly feature annotations in existing
datasets, we construct a large-scale
dataset through an automatic annotation pipeline. Using the annotated
dataset, we train an
attention-based network to predict assembly feature mates, with Engineering Compatibility Fusion (ECF) incorporating explicit engineering compatibility into learned matching scores. To improve the accuracy of automatic assembly modeling, we use assembly feature patterns (AFPs) to guide the matching process. Finally, a post-processing search selects assembly feature mate and AFP mate candidates, whose associated constraints are generated and solved to complete assembly modeling. Experimental results show that the framework achieves assembly constraint accuracies of 74.79% on the six-assembly comparison set and 64.09% on the extended test set of 16 assemblies, which includes the comparison set. With ground-truth face labels supplied as additional input, the corresponding accuracies increase to 81.78% and 80.93%, respectively.
Read the full abstract ▾
All authors Ziheng Dai, Wanbin Pan, Zhihong Tang, Shuming Gao
Computer Vision
DuSRFlow: Dual-Lens Super-Resolution via Parallax-Aware Flow Estimation and Complementary Reference Warping
Fangpu Zhang, Huanjing Yue, Zifan Cui et al. (+3 more)
Dual-lens super-resolution (DuSR) aims to enhance a wide-angle low-resolution (LR) image by exploiting a telephoto reference (Ref) image. A central challenge in DuSR is reliable reference utilization under large parallax, occlusion, and cross-camera imaging discrepancies. Existing methods often employ off-the-shelf monocular optical flow models to provide
geometric priors. However, their assumptions of photometric consistency and smooth motion are violated in dual-lens scenarios, leading to unreliable
alignment and degraded reference-based reconstruction. To address these issues, we propose DuSRFlow, a dual-lens super-resolution framework that improves reference utilization from both correspondence learning and reference aggregation. First, we introduce DuFlowNet, a dedicated dual-lens flow
estimator for robust cross-view
alignment. To train DuFlowNet without ground-truth flow annotations, we develop a real–synthetic data fusion strategy that composites synthetic foreground objects onto real dual-lens image pairs, generating controllable large-parallax samples while preserving realistic cross-camera imaging characteristics. Second, we observe that reference reliability is highly spatially uneven in DuSR, where unreliable local reference responses may suppress the utilization of reliable cues. We therefore propose a Complementary Reference Warping strategy that coordinates patch-based warping and kernel-free-guided deformable warping according to local reference reliability, producing a more reliable reference representation before LR–Ref fusion. In addition, we construct DuSR-RealV2, a challenging real-world
benchmark with complex depth variations, large parallax, and occlusion. Extensive experiments on multiple DuSR
benchmarks demonstrate that DuSRFlow achieves state-of-the-art performance in reconstruction quality, perceptual quality, and cross-
dataset generalization.
Read the full abstract ▾
All authors Fangpu Zhang, Huanjing Yue, Zifan Cui, Shaoxiong Tu, Qirui Yang, Jingyu Yang
Computer Vision
EarthAlign: Learning Language-Aligned Representations of Earth System Data
Fadillah Adamsyah Maani, Numan Saeed, Jiaqi Ma et al. (+4 more)
Interpreting Earth system conditions is central to understanding environmental risks and informing decisions across weather- and
climate-sensitive sectors. Existing
multimodal weather systems primarily target task-specific prediction, generation, or question answering, while general-purpose
alignment between Earth system data and
language remains underexplored due to the limited availability of diverse
language supervision grounded in meteorological conditions. To fill this gap, we introduce EarthAlign, a large-scale
dataset with broad geographic coverage spanning 2000-2024 that combines 10 expert-curated natural event and disaster data sources with climatology-derived normal-weather samples. Each sample includes temporal and geospatial information and four grounded caption styles aligned with 63-variable ERA5 meteorological data. Building on EarthAlign, we introduce MeteoLIP, a dual-encoder framework for learning aligned meteorology-
language representations. MeteoLIP incorporates MetTok, which uses a geolocation- and time-conditioned query to aggregate variable-specific patch
embeddings into a compact sequence of meteorology
tokens. To comprehensively assess Earth system
multimodal representations, we introduce three downstream tasks: cross-modal
retrieval, weather-condition classification, and physical variable estimation. Our experiments show that MeteoLIP improves upon the corresponding CLIP and SigLIP baselines across these tasks. Further analyses highlight the importance of meteorological input, temporal and geospatial conditioning, and multi-style supervision for meteorology-
language alignment. Thus, EarthAlign and MeteoLIP provide a foundation for learning and evaluating
language-aligned representations of Earth system data. Our code,
dataset, and weights are publicly available at https://github.com/mbzuai-oryx/EarthAlign.
Read the full abstract ▾
All authors Fadillah Adamsyah Maani, Numan Saeed, Jiaqi Ma, Dat Tien Nguyen, Youssef Wehbe, Duncan Watson-Parris, Salman Khan
Computer Vision
EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment
ZiAn Wang, Ruiqi Liu, Zhengbo Zhang et al. (+10 more)
Determining whether an image is AI-generated does not establish whether the situation it depicts is factually supported. We formulate Image Factuality Assessment: given an image and a generic verification instruction, a system returns a supported or refuted verdict with an evidence-grounded explanation. Without a supplied textual claim, the system must progressively refine factual questions during investigation and align external evidence with the specific situation depicted. We introduce EviLens, an expert-reviewed
benchmark of 10,174 supported and refuted images from controlled construction and web collection, covering twelve factual error types and evaluating both verdict accuracy and evidence sufficiency. We develop EviScene, a
multimodal ReAct
agent that interleaves visual inspection, external
retrieval, and evidence analysis, using new findings to refine its questions and revisit relevant image details. We train a compact policy with supervised fine-tuning on reviewed teacher trajectories, followed by privileged on-policy self-
distillation applied to verified decisions from the policy's own investigations. On the 1,527-image test set, the trained Qwen3.5-9B
agent achieves 79.05% balanced accuracy and a Strict Evidence Sufficiency Rate (SESR) of 52.26%, improving over the same-backbone base
agent by 6.71 and 9.37 percentage points, respectively. Its SESR is the highest among the evaluated
agents.Code, models, and data will be released at https://github.com/wangzian828/EVISCENE and https://huggingface.co/ZiAnwang/EviScene.
Read the full abstract ▾
All authors ZiAn Wang, Ruiqi Liu, Zhengbo Zhang, Yi Han, Jialiang Shen, Ruoxin Chen, Manni Cui, Ximo Zhu, Jin Jiang, Mingzhe Liu, Linhao Wang, Wenhao Wang, Shu Wu
Computer Vision
Bidirectional Adaptive Transformers for Multimodal Anomaly Detection
Yuxin Jiang, Yunkang Cao and Weiming Shen
The effective integration of features derived from RGB images and 3D point clouds presents a substantial challenge in the field of
multimodal anomaly detection (MAD). Existing MAD methods typically rely on static fusion paradigms built upon frozen pre-trained encoders. While these frameworks facilitate spatial
alignment, they lack the mechanism to establish latent semantic correspondence, thereby inducing cross-modal interference that degrades anomaly discriminability. To mitigate these limitations, this study proposes a Bidirectional Adaptive
Transformers (BAT) framework, which constructs comprehensive and semantically aligned
multimodal representations by leveraging complementary attributes across modalities. The BAT framework introduces a Bidirectional Feature
Alignment (BFA) module, which employs a mutual predictive mechanism to bridge the gap between 2D textural patterns and 3D
geometric structures. This bidirectional interaction explicitly enhances the textural granularity of point cloud descriptors while augmenting the spatial contextual awareness of RGB features. To ensure that the latent representations possess sufficient informational density for
alignment, BAT incorporates a parameter-efficient adaptation architecture. By utilizing lightweight image and point cloud adapters, the framework facilitates specialized fine-tuning of pre-trained models, mitigating the information loss inherent in frozen encoders. Extensive experiments conducted on MVTec 3D-AD and Eyecandies confirm that BAT achieves state-of-the-art anomaly detection performance, significantly outperforming existing MAD methods.
Read the full abstract ▾
Computer Vision · Cross-listed from cs.RO
ToF-Wheel Odometry: Navigating Degeneration of Localization With Limited Sensing Capabilities
Xu Yang, Wenhao Li, Zhengyu Wei et al. (+3 more)
Wheel odometry provides an efficient motion prior for ground
robots but is prone to transient violations such as wheel slip or terrain-induced tilt. In filtering-based odometry, these violations frequently trigger divergence when they coincide with constrained
geometric observability (e.g., featureless corridors). We address this challenge by proposing ToF-Wheel Odometry (TWO), a tightly-coupled filtering framework that integrates wheel kinematics with
geometric constraints from Time-of-Flight (ToF) cameras. The primary contribution of this work is a degeneracy-aware, directional covariance-shaping strategy that replaces heuristic online covariance tuning with geometry-conditioned inflation. The core idea is to infer process noise from
geometric corrections with a strict reliability check. We decompose the posterior-to-prior correction into a wheel-explainable subspace and an orthogonal remainder. The process covariance is anisotropically adjusted according to the observability of the ToF update: if the geometry is degenerate in non-kinematic directions, the remainder is suppressed as sensor noise; if the geometry is distinct, it is admitted as a valid kinematic violation. Additionally, we introduce an intra-frame feedback loop that retrospectively repairs the process covariance within the current frame to reduce structural lag during bursty disturbances. Extensive experiments on challenging scenarios demonstrate that TWO improves trajectory accuracy and robustness compared to static and adaptive Gaussian filtering, robustly navigating the trade-off between kinematic reliability and limited sensing capabilities.
Read the full abstract ▾
All authors Xu Yang, Wenhao Li, Zhengyu Wei, Zening Li, Longxiang Huang, Bo Wang
Computer Vision
Attribute-Centric Vision-Language Alignment for Fine-Grained Gait Understanding
Saihui Hou, Chenye Wang, Wenpeng Lang et al. (+5 more)
Walking sequences reveal human-interpretable attributes related to body structure, posture, and motion. Gait attribute recognition provides a concrete route to fine-grained gait understanding by predicting these attributes. However, existing
benchmarks provide limited fine-grained annotations, while classifier-based gait attribute recognition methods typically represent candidate classes through learned output weights rather than directly matching visual evidence with textual class representations. To address the annotation gap, we present RA-GAR, a large-scale, richly annotated
multimodal benchmark for gait attribute recognition, containing 1,001 subjects, 242,729 walking sequences, and annotations for 15 static and motion gait attributes. We further propose Gait-VL, an attribute-centric
vision-
language alignment framework that recognizes gait attributes by matching attribute-specific multi-frame visual evidence with textual class prototypes. On the visual side, attribute-specific learnable queries aggregate RGB features across spatial locations and frames into per-attribute visual
embeddings. On the
language side, diverse descriptions expanded by a large
language model are combined with context about relevant body regions to construct textual class prototypes. Beyond attribute recognition, we evaluate the transferability of the attribute-pretrained visual encoder by using it to replace generic upstream large
vision models in identityoriented gait recognition pipelines; attribute pre-training uses no identity classification or metric-learning objectives. Experiments demonstrate state-of-the-art attribute recognition performance on RA-GAR and consistent improvements in downstream identity recognition across multiple pipelines and
benchmarks, supporting the effectiveness and transferability of attribute-centric gait representation learning.
Read the full abstract ▾
All authors Saihui Hou, Chenye Wang, Wenpeng Lang, Qiannan Guo, Zhengxiang Lan, Chao Fan, Shiqi Yu, Yongzhen Huang
Computer Vision · Cross-listed from cs.RO
Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies
Chen Zhao, Zipeng Ye, Haitao Shen et al. (+3 more)
Test-time sampling promises to turn one action prediction into a set of distinct executable candidates that a verifier can choose among. Downstream fine-tuning works against that promise. A
vision-
language-action model trained to solve one task distribution concentrates its flow-matching decoder around the dominant demonstrated action, so repeated samples differ only marginally and the verifier receives many copies of one decision. We call this proposal contraction and identify it as a key constraint on test-time scaling: repeated samples can remain highly redundant as the candidate budget grows. Action Dynamic Sampling (ADS) alleviates the constraint on the proposal side, during training. At each training step, ADS integrates $K$ additional trajectories from the current policy under fresh base noise, scores each by the flow support along its path with a Hutchinson trace
estimator, and corrects the policy's local action distribution toward this weighted set through a detached finite-set KL term. Training cost rises; deployment cost is unchanged. Across simulation and four physical-
robot tasks, ADS raises proposal spread without the success penalty that Gaussian perturbation incurs, lifts oracle best-of-8 success on RoboCasa from 57.6% to 63.0%, improves fixed verifiers by 2.4 to 4.9 points in simulation, and raises TokenPB by up to 13.0 points on real-world manipulation.
Read the full abstract ▾
All authors Chen Zhao, Zipeng Ye, Haitao Shen, Guanlin Li, Yuchen Xie, Jing Zhang
Computer Vision · Cross-listed from cs.RO
Remembering What Matters for Long-Horizon Robotic World Models
Hao Wu, Tianyu Shao, Shengju Qian et al. (+10 more)
Autoregressive
robot video world models based on discrete visual
tokens remain unreliable over long rollout horizons. Retaining the entire generated history does not necessarily improve prediction quality. We investigate a possible
memory-role conflict in Full Context decoding: persistent scene information, recent visual-action states, and stale generated history compete for
attention despite their different predictive roles. This perspective motivates ReCAP (Receding Context with Anchor Preservation), a training-free context-scheduling method for long-horizon
robot video world models. ReCAP keeps the pretrained tokenizer, world model, and visual decoder frozen. It preserves the initial scene anchor and a contiguous window of recent complete visual-action blocks while evicting older generated history. The schedule preserves within-block structure and temporal order, requires no additional modules or parameter updates, and bounds active-context growth independently of rollout length. We evaluate ReCAP on RT-1, BridgeV2, LIBERO-90, and CALVIN using frozen autoregressive world models. Across evaluated environments and horizons, ReCAP improves visual fidelity, action-conditioned consistency, and
robot structure preservation relative to Full Context. On BridgeV2, it reduces LPIPS by 63.3%. In the system
benchmark at H=64, it reduces the logical KV footprint by 73.3% and p50 latency by 6.51%.
Attention analyses show increased
attention to retained recent states, while history interventions associate larger amounts of stale context with higher prediction error. These observations are consistent with the
memory-role-conflict hypothesis, although they do not isolate it from context-length and position-handling effects. Our results support inference-time context scheduling as a practical approach to improving long-horizon
robot video prediction and computational efficiency without retraining.
Read the full abstract ▾
All authors Hao Wu, Tianyu Shao, Shengju Qian, Yizhou Zhao, Fan Zhang, Penghao Zhao, Weiyan Wang, Yufei Huang, Fan Xu, Kun Wang, Xin Wang, Ming-Hsuan Yang, Yuxuan Liang
Computer Vision
FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation
Muyu Liu, Mingming Liu, Hong Gu et al. (+2 more)
In autoregressive
video generation, retaining all historical key-value (KV) states increases
memory usage and per-step
attention costs as
videos grow longer. A fixed cache budget bounds these costs but raises the challenge of preserving historical content that supports consistent, high-quality generation. Existing methods control cache size through history selection or consolidation, yet deciding what to retain and how to limit the loss of useful content remains a shared challenge. Our analysis shows that spatial queries depend on different historical content and that higher current
attention coverage does not necessarily yield better long-
video quality. We introduce FrameFold, a training-free KV cache consolidation method that compares the content retrieved by the same recent historical queries before and after merging to guide both representative construction and merge selection. Exploiting temporal redundancy between adjacent historical entries, FrameFold merges their KV states into shared representatives while retaining complete spatial grids. It fits value-merging coefficients in closed form by matching conditional
attention responses, then selects the merge with the lowest remaining response distortion. Under matched KV cache budgets, experiments on Self Forcing and Causal Forcing at 30 and 60 seconds and on LongLive at 120 seconds demonstrate improved consistency and visual quality. Continuous eight-minute Self Forcing rollouts further show less quality degradation than the baselines.
Read the full abstract ▾
All authors Muyu Liu, Mingming Liu, Hong Gu, Yuyao Zhang, Qin Lu
Computer Vision
Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation
Chenxi Xia, Yixuan Xu, Shan Liu et al. (+7 more)
Autoregressive
video generation models generate
videos sequentially, with each new block conditioned on previously generated blocks. By training on the model's own rollouts, Self Forcing and its follow-up methods substantially mitigate exposure bias caused by the mismatch between training- and inference-time history distributions. However, these models still suffer from error accumulation during long-horizon generation. We identify a key underlying limitation: the model remains highly sensitive to errors in its generated history, allowing small deviations to be amplified through subsequent generations. We refer to this underexplored problem as the local history robustness gap. To address this gap, we introduce
Adversarial Gradient Forcing (AGF), a framework designed to improve the robustness of few-step autoregressive
video models to perturbations and accumulated errors in their own generated histories. AGF uses distribution matching gradients from future block predictions to select
adversarial perturbations of self-generated histories. It then jointly trains the generator on the original and perturbed histories to improve the robustness of future generation. Extensive experiments show that AGF achieves the highest VBench Total score on 60-second
video generation and the best visual quality on four-minute
video generation. Notably, AGF achieves such long-horizon robustness while requiring only 5-second rollouts for training.
Read the full abstract ▾
All authors Chenxi Xia, Yixuan Xu, Shan Liu, Jiapeng Wang, Maohua Li, Hanlin Tang, Kan Liu, Tao Lan, Weiyi Lu, Xinggao Liu
Computer Vision
InfraWorld: Motion-Aware World Modeling for Roadside 4D Occupancy Forecasting
Songkai Wang, Xiaokai Bai, Lei Yang et al. (+1 more)
Roadside 4D occupancy forecasting predicts future semantic occupancy in a fixed infrastructure coordinate system. Roadside scenes are globally structured yet locally evolving, requiring comprehensive scene-level context while precisely modeling sparse localized motion. However, existing forecasting paradigms struggle to tackle both requirements. To address this limitation, we propose InfraWorld, a world model formulating roadside occupancy forecasting as selective state
evolution. InfraWorld maintains a dense BEV state for the complete scene and persistent motion queries for moving regions, assigning complementary states to global context and local dynamics. Specifically, we propose Dynamic Query Initiation (DQI) to initialize queries in regions supported by motion in the observed history. During rollout, the dense state is updated through Long–Short Temporal Fusion (LST), which combines short-term adjacent-frame continuity with long-term motion trends to preserve stable context while capturing scene
evolution. Motion-Aware Query Injection (MAQI) then refines the queries and injects confidence-weighted query information into corresponding BEV
tokens, enabling targeted dynamic updates without perturbing global context. Together, InfraWorld concentrates predictive capacity on evolving traffic regions. Extensive experiments on the InfraOcc and Occ3D–nus
datasets demonstrate that InfraWorld achieves state-of-the-art performance for roadside 4D occupancy forecasting while retaining its effectiveness under ego-centric settings. Code will be released.
Read the full abstract ▾
All authors Songkai Wang, Xiaokai Bai, Lei Yang, Hui-liang Shen
Computer Vision · Cross-listed from cs.AI
ScienceBuddy-PV: A Verifier-Governed Recursive Improvement Protocol for Panvascular Intervention Research
Lingsen You, Yujun Guo, Xinyu Zhong et al. (+4 more)
ScienceBuddy-PV adapts the ScienceBuddy recursive-in-recursive design to panvascular intervention research through a structured evidence ledger, device-vessel ontology, abstention contract and retained failure bank. Recursive harness optimization and outer-loop model learning, including reinforcement learning, are specified but not executed. We audit a fixed component, rather than the complete
agent system, using separate ARCADE syntax and stenosis tasks (1,000 training, 200 validation and 300 test images per task). A shared task-masked convolutional model was trained once per representation setting; its parameters and the heuristic support gate were then held fixed, with the stenosis threshold selected on validation data. On the locked test sets, syntax Dice was 0.475 (95% CI 0.459-0.490) and stenosis Dice was 0.231 (95% CI 0.214-0.249). Stenosis pixel AUROC was 0.957 and AUPRC was 0.180 at prevalence 0.00975. The gate accepted 76.7% of stenosis-frame outputs versus 100% for a score-only comparator. In a constructed mask audit, it accepted 44.3% of reference candidates and rejected 55.7%, exposing the cost of abstention. Acceptance does not establish correctness or clinical safety. This public-data component audit makes support and abstention measurable and provides a reproducible protocol for future collaborative
agent studies. It does not demonstrate recursive improvement, patient-level validity or clinical device recommendations.
Read the full abstract ▾
All authors Lingsen You, Yujun Guo, Xinyu Zhong, Zijie Feng, Wentong Wang, Li Shen, Junbo Ge
Computer Vision
We Have Been Interpreting Diffusion Transformer Backbone Behaviors Wrong
Benyuan Meng, Longtao Huang, Yang Liu et al. (+1 more)
During a network forward call,
diffusion backbones naturally produce many intermediate activations. If we evaluate each activation against an identical downstream benchmarking protocol, we can plot an inverted-U-shaped curve as the depth profile: the activation's performance goes up first and then down as we go into deeper layers. This is common knowledge in the
diffusion model community, which inspires many applications including the widely-adopted REPA. However, the common interpretation of this depth profile may be inaccurate and incomplete: (i) The cause of this curve has long been treated as signal granularity changing from coarse to fine, but there has been little evidence in DiT backbones. (ii) The community has been mainly studying this phenomenon in a static way, without investigating how it changes across different training setups. In this work, we show a different mechanism picture for the profile, where the prediction target (e.g., $\epsilon$, $u$, $x_0$) sits at the center. The semantically meaningful signal is only an intermediate by-product for predicting the target, while the prediction target is the real goal for the backbone. Furthermore, the choice of prediction targets as part of the training setup can predictably affect the curve's shape. With this updated interpretation, many applications of this depth profile can be better grounded and predicted. As an example, we show how to predict the near-optimal placement of REPA based on the prediction target of the training setup. The code is at https://github.com/Darkbblue/dit-compare.
Read the full abstract ▾
All authors Benyuan Meng, Longtao Huang, Yang Liu, Liang Lin
Computer Vision
Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning
Yang Xiao, Kaiyuan Deng, Gen Li et al. (+4 more)
Diffusion models pose significant risks regarding the generation of illicit content and copyright violations. This has catalyzed the development of machine unlearning to erase harmful concepts or copyrighted styles from a model's generative repertoire without compromising its general performance. However, previous unlearning approaches on
diffusion models have largely focused on either object-level or style-level removal and failed to address the challenge of object-style combination unlearning. At the same time, multiple unlearning requests often lead to catastrophic forgetting. To address these challenges, we propose Domain
Manifold Unlearning (DMU), which uses an EMA-updated feature proxy extracted from intermediate
diffusion features to represent the retained target-object direction. As a lightweight estimating representation of an object, DMU enables selective unlearning of domain-specific components in a specific object while preserving other semantic representations, thereby significantly enhancing robustness in multiple combination unlearning scenarios. Extensive experiments show that DMU significantly mitigates catastrophic forgetting, outperforming state-of-the-art methods of batch unlearning and sequential unlearning.
Read the full abstract ▾
All authors Yang Xiao, Kaiyuan Deng, Gen Li, Zinan Ling, Zhiwen Fan, Xiaolong Ma, Bo Hui
Computer Vision
TartanMatch: Towards Universal Dense Correspondence Across Modalities
Hyeokjoon Kwon, Jiting Cai, Ruogu Li et al. (+7 more)
Robotic platforms combine multi-modal sensors to operate across diverse conditions, but most dense correspondence methods are limited to RGB-RGB or a small set of modality pairs. Training a model for each modality pair scales poorly with the number of sensors and forgoes potential positive transfer across modality pairs. We introduce TartanMatch, a unified model for dense correspondence across all 25 ordered pairs among RGB, event, thermal, depth, and projected
LiDAR. TartanMatch adapts an RGB-pretrained correspondence model to all modality pairs within one shared network using lightweight modality adaptation and a mixture of real and synthetic data. On zero-shot real-world
benchmarks, TartanMatch reduces Endpoint Error (EPE) over the strongest baselines by 61.9% for cross-modal matching and 49.6% for same-modal matching. We further show that joint training across all modality pairs improves average matching accuracy over pair-specific training, especially on challenging cross-modal pairs. These results demonstrate that a single model achieves broad multi-modal coverage and state-of-the-art matching accuracy.
Read the full abstract ▾
All authors Hyeokjoon Kwon, Jiting Cai, Ruogu Li, Kritan Bhandari, Geethika Hemkumar, Parv Maheshwari, Yuheng Qiu, Yuchen Zhang, Sebastian Scherer, Wenshan Wang
Computer Vision
Spatiotemporal Recognition of Abdominal Wall Layers During Optical Trocar Entry
Shreeram Athreya, Andrew Melehy, Carter Prentice et al. (+4 more)
Objective. To evaluate whether spatial context and temporal modeling improve tissue recognition during optical trocar entry, where multiple abdominal-wall tissues may be visible simultaneously. Methods. We retrospectively analyzed 71 recordings with 1,516 annotated keyframes and 29,151 clinician-annotated sectors. Each frame was divided into 28 polar-grid sectors assigned to nine tissue classes. Color, neighboring-sector, and positional features were used by a gradient-boosted emission classifier. The full pipeline added learned temporal smoothing, spatial regularization, an anatomically ordered hidden Markov model, and posterior blending. Five-fold cross-validation was grouped by recording, with cross-fitting to prevent within-recording leakage. Primary evaluation used clinician-derived targets; ablations assessed classification, probability quality, spatial consistency, and peritoneum-or-deeper onset timing. Results. The complete pipeline achieved accuracy 0.646, macro-F1 0.507, and macro-AUROC 0.882, versus 0.600, 0.440, and 0.861 for emissions alone. Macro-F1 improved by 0.066 across all five folds. Label changes decreased from 66.2 to 19.5 per sector-minute, and median onset error decreased from 15.58 to 2.45 seconds. Frames with a tissue-depth-code span of at least three decreased from 53% to 26%, versus 22% for clinician annotations. Performance remained limited for preperitoneal fat and bowel, and the full model retained a 44% premature-onset proportion. Conclusions. Combining appearance, spatial context, and temporal constraints improved retrospective tissue recognition and onset localization. Tissue-specific limitations, residual timing errors, and reliance on future observations warrant external validation and prospective evaluation of causal models before clinical use.
Read the full abstract ▾
All authors Shreeram Athreya, Andrew Melehy, Carter Prentice, Michael Robinson, Corey Arnold, James Wu, William Speier