跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+2471新增论文
+2025其中 AI 相关
+163已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-11 06:59 · 全站最近入库：2026-11-10 15:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-10 08:15 — 2026-11-11 08:15（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-11 06:59最近发现新增版本：2026-11-10 15:22库内论文最新更新时间：2026-11-10 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

20,643 已收录论文17,531 AI 相关5,643 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 4,042 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-11 06:58（北京时间）
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f88095b30a1d2d6792363d090175d1abCVF · CVPR 2026

SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs

Alansari, Mohamad, Suryanto, Naufal, Velayudhan, Divya, Javed, Sajid, Werghi, Naoufel, Naseer, Muzammal

原文摘要

Multimodal large language models (MLLMs) have advanced from image-level reasoning to pixel-level grounding, but extending these capabilities to videos remains challenging as models must achieve spatial precision and temporally consistent reference tracking. Existing video MLLMs often rely on a static segmentation token ([SEG]) for frame-wise grounding, which provides semantics but lacks temporal context, causing spatial drift, identity switches, and unstable initialization when objects move or reappear. We introduce SPARROW, a pixel-grounded video MLLM that unifies spatial accuracy and temporal stability through two key components: (i) Target-Specific Tracked Features (TSF), which inject temporally aligned referent cues during training, and (ii) a dual-prompt design that decodes box ([BOX]) and segmentation ([SEG]) tokens to fuse geometric priors with semantic grounding. SPARROW is supported by a curated referential video dataset of 30,646 videos and 45,231 Q&A pairs and operates end-to-end without external detectors via a class-agnostic SAM2-based proposer. Integrated into three recent open-source video MLLMs (UniPixel, GLUS, and VideoGLaMM), SPARROW delivers consistent gains across six benchmarks, improving up to +8.9 J&F on RVOS, +5 mIoU on visual grounding, and +5.4 CLAIR on GCG. These results demonstrate that SPARROW substantially improves referential stability, spatial precision, and temporal coherence in pixel-grounded video understanding. Project page: https://risys-lab.github.io/SPARROW/

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f8a7e24d7927159f5f058092c2dc3fb2CVF · CVPR 2026

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression

Wang, Yiyu, Liu, Xuyang, Gui, Xiyan, Lin, Xinying, Yang, Boxue, Liao, Chenfei, Chen, Tailai, Zhang, Linfeng

原文摘要

Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of processing dense visual tokens from continuous video streams. In streaming video scenarios, the primary bottleneck lies in the Vision Transformer (ViT) encoding stage, where redundant processing of temporally similar frames leads to inefficiency. Additionally, inflated token sequences during LLM pre-filling further exacerbate latency and memory overhead. To address these challenges, we propose Streaming Token Compression (STC), a plug-and-play hierarchical framework that seamlessly integrates into existing streaming VideoLLMs, optimizing both ViT encoding and LLM pre-filling stages to accelerate processing. STC introduces two token-level accelerators: STC-Cacher, which reduces ViT encoding overhead by caching and reusing features from temporally similar frames, and STC-Pruner, which compresses the visual token sequence before it enters the LLM, preserving only the most salient tokens based on both spatial and temporal relevance. Extensive experiments on four baseline streaming VideoLLMs across five benchmarks demonstrate that STC outperforms other compression methods. Notably, STC retains up to 99% of accuracy on the ReKV framework while reducing ViT encoding latency and LLM pre-filling latency by 24.5% and 45.3%.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f8ae88ae8e5031a5d783ff16328ac861CVF · CVPR 2026

HAMMER: Harnessing MLLMs via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding

Yao, Lei, Chen, Yong, Su, Yuejiao, Wang, Yi, Liu, Moyun, Chau, Lap-Pui

原文摘要

Humans commonly reason about object affordance through observed interactions in images or videos, and once formed, such knowledge can be generically generalized to novel objects. Inspired by this principle, we advocate for a novel framework that leverages emerging multimodal large language models (MLLMs) for interaction intention-driven 3D affordance grounding, namely HAMMER. Instead of generating explicit object attribute descriptions or relying on off-the-shelf 2D segmenters, we alternatively aggregate the interaction intention depicted in the reference image into a contact-aware embedding and guide the model to infer textual affordance labels, ensuring it thoroughly excavates object semantics and contextual cues. We further devise a hierarchical cross-modal integration mechanism to fully exploit the complementary information from the MLLM for 3D representation refinement and introduce a multi-granular geometry lifting module that infuses spatial characteristics into the extracted intention embedding, thus facilitating accurate 3D affordance localization. Extensive experiments on public datasets and our newly constructed corrupted benchmark reveal the superiority and robustness of our method in seen and unseen scenarios compared to existing approaches. The code and models will be made publicly available.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f8ff1b14ad1f5a9ac11c245b3a52a6ffCVF · CVPR 2026

DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment

Cai, Xin, You, Zhiyuan, Zhang, Zhoutong, Xue, Tianfan

原文摘要

Reducing the token count is crucial for efficient training and inference of latent diffusion models, especially at high resolution. A common approach is to build high-compression image tokenizers that store more information by allocating more channels per token. However, when trained solely with reconstruction objectives, high-dimensional latent spaces often fail to maintain meaningful structure, which complicates diffusion training. Existing methods introduce additional objectives, such as semantic alignment or selective dropout, to enforce structure, but typically require costly retraining of the diffusion model. In contrast, pretrained diffusion models already exhibit a structured, lower-dimensional latent space, suggesting a simpler strategy: expand the latent dimensionality while preserving this structure. To this end, we propose Detail-Aligned VAE (DA-VAE), which increases the compression ratio of a pretrained VAE with only lightweight adaptation of the diffusion backbone. DA-VAE imposes an explicit latent layout: the first C channels are inherited from the pretrained VAE at a base resolution, while additional D channels encode high-resolution details. We introduce a simple yet effective detail-alignment mechanism that explicitly regularizes the expanded latent space to preserve the structural properties of the original space defined by the first C channels. Finally, we present a warm-start fine-tuning strategy that enables 1024 x1024 image generation with Stable Diffusion 3.5 using only 32 x32 tokens, 4xfewer than the original model, within a compute budget of 5 H100-days. It further enables 2048 x2048 generation with SD3.5, achieving a 6xspeedup while preserving image quality. We also validate the method and its design choices quantitatively on ImageNet.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f9015ee829852798de7ee11288bf6ea7CVF · CVPR 2026

FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model

Chen, Xiang, Pan, Jinshan, Dong, Jiangxin, Yang, Jian, Tang, Jinhui

原文摘要

Recent studies have witnessed significant advances in image restoration foundation models driven by improvements in the scale and quality of pre-training data. In this work, we find that the data mixture proportions from different restoration tasks are also a critical factor directly determining the overall performance of all-in-one image restoration models. To this end, we propose a high-capacity diffusion-based image restoration foundation model, FoundIR-v2, which adopts a data equilibrium scheduling paradigm to dynamically optimize the proportions of mixed training datasets from different tasks. By leveraging the data mixing law, our method ensures a balanced dataset composition, enabling the model to achieve consistent generalization and comprehensive performance across diverse tasks. Furthermore, we introduce an effective Mixture-of-Experts (MoE)-driven scheduler into generative pre-training to flexibly allocate task-adaptive diffusion priors for each restoration task, accounting for the distinct degradation forms and levels exhibited by different tasks. Extensive experiments demonstrate that our method can address over 50 sub-tasks across a broader scope of real-world scenarios and achieves favorable performance against state-of-the-art approaches.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f91da4dc63bdb69d9050d701cc84f2a6CVF · CVPR 2026

Predicting Spatial Transcriptomics from Histology Images via High-Order Multi-Cell Interaction Modeling

Sun, Youhan, Rao, Jiahua, Du, Kangrui, Xie, Jiancong, Yang, Yuedong

原文摘要

Spatial transcriptomics (ST) links gene expression to tissue architecture and enables predicting spatial expression from H&E-stained whole-slide images (WSIs). However, existing spot- or slide-level predictors focus on single-spot features or pairwise relations, failing to capture high-order, many-to-many cross-cell interactions. As a result, they miss synergistic and antagonistic effects among multiple neighboring cells. Here, we introduce MCToGene, a scalable and accurate framework that explicitly models multi-cell interactions via many-body attention with hierarchical coupling to predict spatial gene expression. MCToGene employs a many-body attention module to encode high-order, many-to-many cross-cell dependencies, enabling context-aware microenvironment modeling. To mitigate the combinatorial burden of many-body modeling, we design a hierarchical interaction module that couples pairwise and many-body representations for feature aggregation and prediction, preserving many-body expressiveness while controlling computation and memory. On HEST-1k and STImage-1K4M, MCToGene surpasses state-of-the-art baselines with 7.85% relative improvement. Ablations confirm that explicit high-order, many-to-many modeling drives these gains, and visualizations demonstrate that multi-cell interactions are essential for biologically coherent spatial predictions.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f92387efa125d46ecee76ca3d520a6d3CVF · CVPR 2026

RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation

Zhu, Kai, Cui, Zhenyu, Zang, Zehua, Zhou, Jiahuan

原文摘要

Recently, state space models have demonstrated efficient video segmentation through linear-complexity state space compression. However, Video Semantic Segmentation (VSS) requires pixel-level spatiotemporal modeling capabilities to maintain temporal consistency in segmentation of semantic objects. While state space models can preserve common semantic information during state space compression, the fixed-size state space inevitably forgets specific information, which limits the models' capability for pixel-level segmentation. To tackle the above issue, we proposed a Refining Specifics State Space Model approach (RS-SSM) for video semantic segmentation, which performs complementary refining of forgotten spatiotemporal specifics. Specifically, a Channel-wise Amplitude Perceptron (CwAP) is designed to extract and align the distribution characteristics of specific information in the state space. Besides, a Forgetting Gate Information Refiner (FGIR) is proposed to adaptively invert and refine the forgetting gate matrix in the state space model based on the specific information distribution. Consequently, our RS-SSM leverages the inverted forgetting gate to complementarily refine the specific information forgotten during state space compression, thereby enhancing the model's capability for spatiotemporal pixel-level segmentation. Extensive experiments on four VSS benchmarks demonstrate that our RS-SSM achieves state-of-the-art performance while maintaining high computational efficiency. The code is available at https://github.com/zhoujiahuan1991/CVPR2026-RS-SSM.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f95e81986657d4d2d48008b7929e6e44CVF · CVPR 2026

MooCap: A Multi-View Benchmark for Cow-Object-Human Interaction and Behavior Dynamics

Noronha, Ian, Neave, Heather, Kaur, Upinder

原文摘要

Understanding animal behavior requires modeling how bodies, objects, and other agents interact over time, not simply detecting isolated actions or estimating pose frame by frame. Existing animal video datasets target pose estimation or coarse, passively observed actions, and rarely provide the structured, multi-entity interaction annotations needed to study behavioral dynamics. We introduce MooCap, a multi-view video benchmark for animal-object-human interaction understanding under controlled experimental protocols. MooCap contains 42 hours of synchronized multi-camera video from 43 individually tested cows across seven standardized interaction scenarios, including novel environment, novel object, novel human, human approach, unfamiliar conspecifics (restricted and unrestricted) and Dam reunion (restricted and unrestricted). Recordings are densely annotated with 23 fine-grained behaviors, 39 body keypoints across 157 test sessions, 4 spatial zones, and 43 subjects, describing interactions among subjects, objects, humans, and other cattle. We establish three benchmarks on MooCap: (1) dense temporal action segmentation over 1200-1500-second sequences; (2) pose-based behavior and interaction recognition from keypoint trajectories; and (3) longitudinal behavioral classification linking adult behaviors with rearing conditions. Benchmarking results reveal that state-of-the-art temporal segmentation models achieve only 66.4% frame accuracy and 30.6% F1@0.5, with performance degrading further during interaction-heavy segments. Overall, MooCap bridges multi-view pose estimation, multi-entity tracking, and structured behavioral protocols to enable interaction-aware models for animal behavior analysis.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f967395f92feef14831d937ecae94c70CVF · CVPR 2026

MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration

Zhang, Chenran, Wu, Ruiqi, Zhou, Tao, Zhou, Yi

原文摘要

Medical vision-language pretraining (VLP) models have recently been investigated for their generalization to diverse downstream tasks. However, current medical VLP methods typically force the model to learn simple and complex concepts simultaneously. This anti-cognitive process leads to suboptimal feature representations, especially under distribution shift. To address this limitation, we propose a Knowledge-driven Cognitive Orchestration for Medical VLP (MedKCO) that involves both the ordering of the pretraining data and the learning objective of vision-language contrast. Specifically, we design a two level curriculum by incorporating diagnostic sensitivity and intra-class sample representativeness for the ordering of the pretraining data. Moreover, considering the inter-class similarity of medical images, we introduce a self-paced asymmetric contrastive loss to dynamically adjust the participation of the pretraining objective. We evaluate the proposed pretraining method on three medical imaging scenarios in multiple vision-language downstream tasks, and compare it with several curriculum learning methods. Extensive experiments show that our method significantly surpasses all baselines. https://github.com/Mr-Talon/MedKCO.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f9719c07511a9f32046f96ef22e37f5aCVF · CVPR 2026

Revisiting the Necessity of Full Accuracy: Weakly Supervised Object-Level Offset Correction for Misaligned Building Labels

Xu, Junda, Liu, Yanmeng, Zeng, Xiangqiang, Wu, Jinrong, Qu, Ying, Zhang, Libao

原文摘要

Google Earth imagery, combined with building footprint databases, offers an efficient way to construct localized building datasets. However, the lack of orthorectification in these images leads to spatial misalignments between annotations and their corresponding roof locations. Adopting such misaligned data directly for model training can severely degrade segmentation performance. To address the challenge, we propose an Object-based Multi-stage Alignment Framework (OMAF) that generates high-quality corrected labels with minimal manual intervention. OMAF first employs a prior-regularized self-alignment method to produce high-confidence, object-level offset pseudo-labels, which are then used to train an instance-level offset regression model for label refinement. Experimental results on the challenging datasets demonstrate that OMAF effectively corrects misalignments and consistently boosts the mIoU of all baseline models by up to 40.6%. This work provides a practical and cost-effective solution for large-scale dataset construction and domain adaptation. Our code and dataset are publicly available at https://github.com/dayunyan/OMAF-Building-Alignment.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f99998ba8c935fc320e09f47468b9d02CVF · CVPR 2026

Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection

Yang, Yawen, Li, Feng, Kong, Shuqi, Diao, Yunfeng, Gao, Xinjian, Shi, Zenglin, Wang, Meng

原文摘要

Recent rapid advancement of generative models has significantly improved the fidelity and accessibility of AI-generated synthetic images. While enabling various innovative applications, the unprecedented realism of these synthetics makes them increasingly indistinguishable from authentic photographs, posing serious security risks, such as media credibility and content manipulation. Although extensive efforts have been dedicated to detecting synthetic images, most existing approaches suffer from poor generalization to unseen data due to their reliance on model-specific artifacts or low-level statistical cues. In this work, we identify a previously unexplored distinction that real images maintain consistent semantic attention and structural coherence in their latent representations, exhibiting more stable feature transitions across network layers, whereas synthetic ones present discernible distinct patterns. Therefore, we propose a novel approach termed latent transition discrepancy (LTD), which captures the inter-layer consistency differences of real and synthetic images. LTD adaptively identifies the most discriminative layers and assesses the transition discrepancies across layers. Benefiting from the proposed inter-layer discriminative modeling, our approach exceeds the base model by 14.35% in mean Acc across three datasets containing diverse GANs and DMs. Extensive experiments demonstrate that LTD outperforms recent state-of-the-art methods, achieving superior detection accuracy, generalizability, and robustness.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f99a7046389c224994ade575d5572e18CVF · CVPR 2026

MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization

Huang, Chengyue, Zhang, Mellon M., Azarcon, Robert, Chou, Glen, Kira, Zsolt

原文摘要

Vision-Language-Action (VLA) models inherit strong priors from pretrained Vision-Language Models (VLMs), but naive fine-tuning often disrupts these representations and harms generalization. Existing fixes -- freezing modules or applying uniform regularization -- either overconstrain adaptation or ignore the differing roles of VLA components. We present MAPS (Module-Wise Proximity Scheduling), the first robust fine-tuning framework for VLAs. Through systematic analysis, we uncover an empirical order in which proximity constraints should be relaxed to balance stability and flexibility. MAPS linearly schedules this relaxation, enabling visual encoders to stay close to their pretrained priors while action-oriented language layers adapt more freely. MAPS introduces no additional parameters or data, and can be seamlessly integrated into existing VLAs. Across MiniVLA-VQ, MiniVLA-OFT, OpenVLA-OFT, and challenging benchmarks such as SimplerEnv, CALVIN, LIBERO, as well as real-world evaluations on the Franka Emika Panda platform, MAPS consistently boosts both in-distribution and out-of-distribution performance (up to +30%). Our findings highlight empirically guided proximity to pretrained VLMs as a simple yet powerful principle for preserving generalization in VLM-to-VLA transfer.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f9a2725e5c533f3aafa02a39db898c7bCVF · CVPR 2026

Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions

Ye, Jingtao, Zhang, Kexin, Ma, Xunchi, Li, Yuechan, Zhu, Guangming, Shen, Peiyi, Jiang, Linhua, Zhang, Xiangdong 等 9 位作者

原文摘要

The rapid movements and agile maneuvers of unmanned aerial vehicles (UAVs) induce significant observational challenges for multi-object tracking (MOT). However, existing UAV-perspective MOT benchmarks often lack these complexities, featuring predominantly predictable camera dynamics and linear motion patterns. To address this gap, we introduce DynUAV, a new benchmark for dynamic UAV-perspective MOT, characterized by intense ego-motion and the resulting complex apparent trajectories. The benchmark comprises 42 video sequences with over 1.7 million bounding box annotations, covering vehicles, pedestrians, and specialized industrial categories such as excavators, bulldozers and cranes. Compared to existing benchmarks, DynUAV introduces substantial challenges arising from ego-motion, including drastic scale changes and viewpoint changes, as well as motion blur. Comprehensive evaluations of state-of-the-art trackers on DynUAV reveal their limitations, particularly in managing the intertwined challenges of detection and association under such dynamic conditions, thereby establishing DynUAV as a rigorous benchmark. We anticipate that DynUAV will serve as a demanding testbed to spur progress in real-world UAV-perspective MOT, and we will make all resources available at https://github.com/kxzhang-lab/DynUAV.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f9a98778acdc8527ed9016a4467cc124CVF · CVPR 2026

SpiderCam: Low-Power Snapshot Depth from Differential Defocus

Ferreira, Marcos A., Li, Tianao, Mamish, John, Hester, Josiah, Sangar, Yaman, Guo, Qi, Alexander, Emma

原文摘要

We introduce SpiderCam, an FPGA-based snapshot depth-from-defocus camera which produces 480x400 sparse depth maps in real-time at 32.5 FPS over a working range of 52 cm while consuming 611 mW of power in total. SpiderCam comprises a custom camera which simultaneously captures two differently focused images of the same scene, processed with a SystemVerilog implementation of depth from differential defocus (DfDD) on a low-power FPGA. To achieve state-of-the-art power consumption, we present algorithmic improvements to DfDD that overcome challenges caused by low-power sensors, and design a memory-local implementation for streaming depth computation on a device that is too small to store even a single image pair. We report the first sub-Watt total power measurement for passive FPGA-based 3D cameras in the literature.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f9b5b070eb7226b6fd84818c2563ff46CVF · CVPR 2026

Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements

Kinoshita, Genki, Nakamura, Shu, Kawahara, Ryo, Nobuhara, Shohei, Kawanishi, Yasutomo, Nishino, Ko

原文摘要

Effective human behavior modeling requires a representation of the human body movement that capitalizes on its compositionality. We propose a hierarchical representation consisting of Action Atoms that capture the atomic joint movements and Action Motifs that are formed by their temporal compositions and encode similar body movements found across different overall human actions. We derive A4Mer, a nested latent Transformer to learn this hierarchical representation from human pose data in a fully self-supervised manner. A4Mer splits a 3D pose sequence into variable-length segments and represents each segment as a single latent token (Action Atoms). Through bottom-up representation learning, temporal patterns composed of these Action Atoms, which capture meaningful temporal spans of reusable, semantic segments of body movements, naturally emerge (Action Motifs). A4Mer achieves this with a unified pretext task of masked token prediction in their respective latent spaces. We also introduce Action Motif Dataset (AMD), a large-scale dataset of multi-view human behavior videos with full SMPL annotations. We introduce a novel use of cameras by mounting them on the feet to achieve their frame-wise annotations despite frequent and heavy body occlusions. Experimental results demonstrate the effectiveness of A4Mer for extracting meaningful Action Motifs, which significantly benefit human behavior modeling tasks including action recognition, motion prediction, and motion interpolation.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f9bf8aec080c1ecb230134d5f872753dCVF · CVPR 2026

CD-Buffer: Complementary Dual-Buffer Framework for Test-Time Adaptation in Adverse Weather Object Detection

Song, Youngjun, Kim, Hyeongyu, Hwang, Dosik

原文摘要

Test-Time Adaptation (TTA) enables real-time adaptation to domain shifts without offline retraining. Recent TTA methods have predominantly explored additive approaches that introduce lightweight modules for feature refinement. Recently, a subtractive approach that removes domain-sensitive channels has emerged as an alternative direction. We observe that these paradigms exhibit complementary effectiveness patterns: subtractive methods excel under severe shifts by removing corrupted features, while additive methods are effective under moderate shifts requiring refinement. However, each paradigm operates effectively only within limited shift severity ranges, failing to generalize across diverse corruption levels. This leads to the following question: can we adaptively balance both strategies based on measured feature-level domain shift? We propose CD-Buffer, a novel complementary dual-buffer framework where subtractive and additive mechanisms operate in opposite yet coordinated directions, driven by a unified discrepancy metric. Our key innovation lies in discrepancy-driven coupling, which unifies removal and refinement through a shared metric and automatically balances both strategies based on feature-level shift severity. This establishes channel-wise adaptive balancing that enables differentiated treatment for heterogeneous shift magnitudes without manual tuning. Extensive experiments on KITTI, Cityscapes, and ACDC datasets demonstrate state-of-the-art performance, consistently achieving superior results across diverse weather conditions and severity levels.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f9e3f7614649b5f4ae05b7be541d614bCVF · CVPR 2026

MVInverse: Feed-forward Multiview Inverse Rendering in Seconds

Wu, Xiangzuo, Ren, Chengwei, Zhou, Jun, Li, Xiu, Liu, Yuan

原文摘要

Multi-view inverse rendering aims to recover geometry, materials, and illumination consistently across multiple viewpoints. Existing single-view approaches often ignore cross-view relationships, leading to inconsistent results, while multi-view optimization methods rely on slow differentiable rendering and per-scene refinement, making them computationally expensive and hard to scale. To address these limitations, we introduce a feed-forward multi-view inverse rendering framework that directly predicts spatially varying albedo, metallicity, roughness, diffuse shading, and surface normals from sequences of RGB images. By alternating attention across views, our model captures both intra-view long-range lighting interactions and inter-view material consistency, enabling coherent scene-level reasoning within a single forward pass. Due to the scarcity of real-world training data, models trained on existing synthetic datasets often struggle to generalize to real-world scenes. To overcome this limitation, we propose a consistency-based finetuning strategy that leverages unlabeled real-world videos to enhance both multi-view coherence and robustness under in-the-wild conditions. Extensive experiments on benchmark datasets demonstrate that our method achieves state-of-the-art performance in terms of multi-view consistency, material and normal estimation quality, and generalization to real-world imagery.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f9e75af253e8ac330d33f5b4660af303CVF · CVPR 2026

OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data

Zhao, Yan, Cheng, Zhengxue, Zhang, Junxuan, Zhou, Dajiang, Gu, Qunshan, Wang, Qi, Song, Li

原文摘要

Lossless compression is essential for efficient data storage and transmission. Although learning-based lossless compressors achieve strong results, most of them are designed for a single modality, leading to redundant compressor deployments in multi-modal settings. Designing a unified multi-modal compressor is critical yet challenging, as different data types vary largely in format, dimension, and statistics. Multi-modal large language models offer a promising resolution but remain too complex for practical use. Thus, we propose OmniZip, a unified and lightweight lossless compressor for multi-modal data (like image, text, speech, tactile, database, and gene sequence). Built on a lightweight backbone, OmniZip incorporates three key components to enable efficient multi-modal lossless compression: a modality-unified tokenizer that reversibly transforms diverse data into tokens, a modality-routing context learning mechanism that enables flexible multi-modal context modeling, and a modality-routing feedforward design that further enhances the model's nonlinear representation flexibility. A reparameterization training strategy is used to enhance model capacity. It outperforms or matches other state-of-the-art compressors on multiple modalities, achieving 42%, 57%, 62% and 42%, 53% higher compression efficiency than gzip on CLIC-M, TouchandGo, enwik9, LibriSpeech, and WikiSQL datasets, respectively. It also supports near real-time inference on resource-constrained edge devices, reaching up to 1MB/s on MacBook CPUs and iPhone NPUs. Our code will be released upon acceptance.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:f9ef5aa823c91384287f9ffb42b2f436CVF · CVPR 2026

Obstruction Reasoning for Robotic Grasping

Jiao, Runyu, Bortolon, Matteo, Giuliari, Francesco, Fasoli, Alice, Povoli, Sergio, Mei, Guofeng, Wang, Yiming, Poiesi, Fabio

原文摘要

Successful robotic grasping in cluttered environments not only requires a model to visually ground a target object but also to reason about obstructions that must be cleared beforehand. While current vision-language embodied reasoning models show emergent spatial understanding, they remain limited in terms of obstruction reasoning and accessibility planning. To bridge this gap, we present UNOGrasp, a learning-based vision-language model capable of performing visually-grounded obstruction reasoning to infer the sequence of actions needed to unobstruct the path and grasp the target object. We devise a novel multi-step reasoning process based on obstruction paths originated by the target object. We anchor each reasoning step with obstruction-aware visual cues to incentivize reasoning capability. UNOGrasp combines supervised and reinforcement finetuning through verifiable reasoning rewards. Moreover, we construct UNOBench, a large-scale dataset for both training and benchmarking, based on MetaGraspNetV2, with over 100k obstruction paths annotated by humans with obstruction ratios, contact points, and natural-language instructions. Extensive experiments and real-robot evaluations show that UNOGrasp significantly improves obstruction reasoning and grasp success across both synthetic and real-world environments, outperforming generalist and proprietary alternatives.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fa2c285aae2f1c0449f7f8dbd4df6dd3CVF · CVPR 2026

LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models

Huang, Guolei, Peng, Qinzhi, Xu, Gan, Huang, Yao, Lu, Yuxuan, Shen, Yongjun

原文摘要

As Vision-Language Models (VLMs) move into interactive, multi-turn use, safety concerns intensify for multimodal multi-turn dialogue, which is characterized by concealment of malicious intent, contextual risk accumulation, and cross-modal joint risk. These characteristics limit the effectiveness of content moderation approaches designed for single-turn or single-modality settings. To address these limitations, we first construct the Multimodal Multi-turn Dialogue Safety (MMDS) dataset, comprising 4,484 annotated dialogues and a comprehensive risk taxonomy with 8 primary and 60 subdimensions. As part of MMDS construction, we introduce Multimodal Multi-turn Red Teaming (MMRT), an automated framework for generating unsafe multimodal multi-turn dialogues. We further propose LLaVAShield, which audits the safety of both user inputs and assistant responses under specified policy dimensions in multimodal multi-turn dialogues. Extensive experiments show that LLaVAShield significantly outperforms state-of-the-art VLMs and existing content moderation tools while demonstrating strong generalization and flexible policy adaptation. Additionally, we analyze vulnerabilities of mainstream VLMs to harmful inputs and evaluate the contribution of key components, advancing understanding of safety mechanisms in multimodal multi-turn dialogues.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fa35be641507dfcd4e09391b49d2fc51CVF · CVPR 2026

CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion

Hu, James Jincheng, Wu, Yuxiao, Cai, Youcheng, Liu, Ligang

原文摘要

Controllable, high-fidelity mesh editing remains a significant challenge in the domain of 3D content creation. Existing generative methods often struggle with complex geometries and fail to preserve fine-scale details. We propose CraftMesh, a novel framework for high-fidelity generative mesh manipulation based on Poisson Seamless Fusion. We decompose mesh editing into a pipeline that leverages the strengths of 2D image editing and 3D generation models: we first edit a 2D reference image, then generate a 3D mesh corresponding to the edited region, and fuse it seamlessly into the original mesh through a Geometry and Texture Fusion method. We introduce two core techniques: Poisson Geometric Fusion, which utilizes a hybrid SDF/Mesh representation with normal blending to achieve harmonious geometric integration, and Poisson Texture Harmonization for visually consistent texture blending. We demonstrate state-of-the-art structural consistency, geometric fidelity, and texture quality in challenging editing scenarios.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fa64739b4ee897ff7420b1cc6bc9be2cCVF · CVPR 2026

Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding

Jeon, Yerim, Lee, Miso, Moon, WonJun, Heo, Jae-Pil

原文摘要

Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal contexts. However, existing methods typically adopt standard decoders from language modeling, which rely on a causal attention mask. This design introduces two fundamental conflicts in 3D scene understanding: sequential bias among order-agnostic 3D objects and restricted object-instruction attention, hindering task-specific reasoning. To overcome these limitations, we propose 3D Spatial Language Instruction Mask (3D-SLIM), an effective masking strategy that replaces the causal mask with an adaptive attention mask tailored to the spatial structure of 3D scenes. Our 3D-SLIM introduces two key components: a Geometry-adaptive Mask that constrains attention based on spatial density rather than token order, and an Instruction-aware Mask that enables object tokens to directly access instruction context. This design allows the model to process objects based on their spatial relationships while being guided by the user's task. 3D-SLIM is simple, requires no architectural modifications, and adds no extra parameters, yet it yields substantial performance improvements across diverse 3D scene-language tasks. Extensive experiments across multiple benchmarks and LLM baselines validate its effectiveness and underscore the critical role of decoder design in 3D multi-modal reasoning.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fa722694e31e5ad55036de2335dfcf4cCVF · CVPR 2026

Reliable Policy Transfer for Safety-Aware End-to-End Driving with Deep Reinforcement Learning

Borhan, Uddin Md., Raza, Arif, Lin, Zhiliang, Wang, Lu, Li, Jianqiang, Chen, Jie

原文摘要

End-to-End (E2E) Reinforcement Learning (RL) for autonomous driving still struggles with safety and generalization under distribution shift, as perception-heavy encoders, sparse rewards, and ad hoc uncertainty handling yield brittle closed-loop behavior. This work introduces a unified Deep RL (DRL) framework built around a control-layer reliability interface where the same uncertainty signal informs relational attention, gates policy entropy, and regularizes transfer alignment. An ego-centric relational graph encodes agent influence via uncertainty-weighted attention over kinematics, lane geometry, and semantics, producing a compact control state. A multi-objective differentiable reward shapes safety, progress, and comfort with an uncertainty term. Aleatoric and epistemic uncertainty, captured through per-edge heteroscedastic variance and a critic ensemble, modulate policy entropy for risk-aware exploration. A causal-semantic transfer objective aligns actions, attention, and uncertainty statistics across domains with meta-learned initialization for few-shot adaptation. In closed-loop urban driving across varied towns, traffic, and weather, the framework improves success rate, reduces infractions, and achieves higher time-to-conflict combined with lower lateral deviation over strong baselines.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fa771119edf30fd77084bf9c6dfd6f8cCVF · CVPR 2026

Motus: A Unified Latent Action World Model

Bi, Hongzhe, Tan, Hengkai, Xie, Shenghao, Wang, Zeyuan, Huang, Shuhe, Liu, Haitian, Zhao, Ruowen, Feng, Yao 等 16 位作者

原文摘要

While a general embodied agent must function as a unified system, current methods are built on isolated models for understanding, world modeling, and control. This fragmentation prevents unifying multimodal generative capabilities and hinders learning from large-scale, heterogeneous data. In this paper, we propose Motus, a unified latent action world model that leverages existing general pretrained models and rich, sharable motion information. Motus introduces a Mixture-of-Transformer (MoT) architecture to integrate three experts (ie, understanding, video generation, and action) and adopts a UniDiffuser-style scheduler to enable flexible switching between different modeling modes (ie, world models, vision-language-action models, inverse dynamics models, video generation models, and video-action joint prediction). Motus further leverages the optical flow to learn latent actions and adopts a recipe with three-phase training pipeline and six-layer data pyramid, thereby extracting pixel-level "delta action" and enabling large-scale action pretraining. Experiments show that Motus achieves superior performance against state-of-the-art methods in both simulation (a +15% improvement over X-VLA and a +45% improvement over Pi-0.5) and real-world scenarios(improved by +11 48%), demonstrating unified modeling of all functionalities and priors significantly benefits downstream robotic tasks.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fa81802281770b22e3a30653a95bd7d2CVF · CVPR 2026

Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval

Li, Jun, Lou, Xuhang, Wang, Jinpeng, Wang, Yuting, Wang, Yaowei, Xia, Shu-Tao, Chen, Bin

原文摘要

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos based on text queries that describe only partial events. Existing methods suffer from incomplete global contextual perception, struggling with query ambiguity and local noise induced by spurious responses. To address these issues, we propose DreamPRVR, which adopts a coarse-to-fine representation learning paradigm. The model first generates global contextual semantic registers as coarse-grained highlights spanning the entire video and then concentrates on fine-grained similarity optimization for precise cross-modal matching. Concretely, these registers are generated by initializing from the video-centric distribution produced by a probabilistic variational sampler and then iteratively refined via a text-supervised truncated diffusion model. During this process, textual semantic structure learning constructs a well-formed textual latent space, enhancing the reliability of global perception. The registers are then adaptively fused with video tokens through register-augmented Gaussian attention blocks, enabling context-aware feature learning. Extensive experiments show that DreamPRVR outperforms state-of-the-art methods. Code is released at https://github.com/lijun2005/CVPR26-DreamPRVR.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fa86ed99b72e364a5b5448841eba434cCVF · CVPR 2026

HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning

Zhang, Xuerui, Wang, Xuehao, Zhuang, Zhan, Zhao, Linglan, Li, Ziyue, Zhang, Xinmin, Song, Zhihuan, Zhang, Yu

原文摘要

Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (*e.g.*, only classification tasks) and neglects the scenario of learning across heterogeneous tasks that possess different structures of outputs. In this work, we formalize this broader setting as lifelong heterogeneous learning (LHL).Departing from conventional lifelong learning, the task sequence of LHL spans different task types, and the learner needs to retain heterogeneous knowledge for different output space structures.To instantiate the LHL, we focus on LHL in the context of dense prediction (LHL4DP), a realistic and challenging scenario.To this end, we propose the Heterogeneity-Aware Distillation (HAD) method, an exemplar-free approach that preserves previously gained heterogeneous knowledge by self-distillation in each training phase.The proposed HAD comprises two complementary components, including a distribution-balanced heterogeneity-aware distillation loss to alleviate the global imbalance of prediction distribution and a salience-guided heterogeneity-aware distillation loss that concentrates learning on informative edge pixels extracted with the Sobel operator.Extensive experiments demonstrate that the proposed HAD method significantly outperforms existing methods in this new scenario.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fa88e860374c7bef0164dd807b185525CVF · CVPR 2026

EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation

Li, Bingxuan, Cui, Yiming, He, Yicheng, Wang, Yiwei, Zhang, Shu, Wen, Longyin, Niu, Yulei

原文摘要

Sound effects build an essential layer of multimodal storytelling, shaping the emotional atmosphere and the narrative semantics of videos. Despite recent advancement in video-text-to-audio (VT2A), the current formulation faces three key limitations: (1) an imbalance between visual and textual conditioning that leads to visual dominance; (2) the absence of a concrete definition for fine-grained controllable generation; (3) weak instruction understanding and following, as existing datasets rely on brief categorical tags. To address these limitations, we introduce EchoFoley (Event-Centric Hierarchical cOntrol Foley), a new task designed for video-grounded sound generation with both event-level local control and hierarchical semantic control. Our symbolic representation for sounding events specifies when, what, and how each sound is produced within a video or instruction, enabling fine-grained controls like sound generation, insertion, and editing. To support this task, we construct EchoFoley-6k, a large-scale, expert-curated benchmark containing over 6,000 video-instruction-annotation triplets and 42,000 fine-grained sounding event annotations.Building upon this foundation, we propose EchoVidia, a sounding-event-centric agentic generation framework with slow-fast thinking strategy. Experiments show that EchoVidia surpasses recent VT2A models by 40.7% in controllability and 12.5% in perceptual quality.

cs.CV · cs.AI

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fa9123575c37d32ed1ae7c52dd4ee71eCVF · CVPR 2026

Temporal Representation Enhancement (TRE): Learning to Forget Dominant Patterns for Enhanced Temporal Spiking Features

Liu, Wei, Yang, Li, Wang, Yufei, Xiao, Han, Cai, Boyu, Hu, Weiming

原文摘要

Spiking Neural Networks (SNNs) naturally process visual inputs across multiple timesteps, offering rich temporal dynamics and energy-efficient computation. However, the temporally invariant supervision commonly used in training tends to reinforce the same dominant response patterns across timesteps, leading to redundant representations and limiting temporal discriminability. To overcome this limitation, we introduce Temporal Representation Enhancement(TRE), a novel learning-to-forget paradigm that encourages more diverse and complementary temporal representations. TRE identifies high-contribution semantic patterns through class-specific contribution estimation and temporal accumulation, and selectively suppresses them using a dynamic modulation strategy. By redirecting the model's attention toward alternative yet informative semantic cues, TRE promotes the learning of complementary features across timesteps. This approach not only strengthens the temporal discriminative capacity of SNNs but also enables more effective multi-timestep learning by leveraging richer semantic information. Extensive experiments on both static image datasets and dynamic neuromorphic datasets demonstrate that TRE consistently improves classification accuracy and feature diversity across different SNN backbones.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:faab9c8db7078640c58f791c3353d8e1CVF · CVPR 2026

An Empirical Study on How Video-LLMs Answer Video Questions

Gou, Chenhui, Ma, Ziyu, Duan, Zicheng, He, Haoyu, Chen, Feng, Liu, Akide, Zhuang, Bohan, Cai, Jianfei 等 9 位作者

原文摘要

Taking advantage of large-scale data and pretrained language models, Video Large Language Models (Video-LLMs) have shown strong capabilities in answering video questions. However, most existing efforts focus on improving performance, with limited attention to understanding their internal mechanisms. This paper aims to bridge this gap through a systematic empirical study. To interpret existing VideoLLMs, we adopt attention knockouts as our primary analytical tool and design three variants: Video Temporal Knockout, Video Spatial Knockout, and Language-to-Video Knockout. Then, we apply these three knockouts on different numbers of layers (window of layers). By carefully controlling the window of layers and types of knockouts, we provide two settings: a global setting and a fine-grained setting. Our study reveals three key findings: (1) Global setting indicates Video information extraction primarily occurs in early layers, forming a clear two-stage process--lower layers focus on perceptual encoding, while higher layers handle abstract reasoning; (2) In the fine-grained setting, certain intermediate layers exert an outsized impact on video question answering, acting as critical outliers, whereas most other layers contribute minimally; (3) In both settings, we observe that spatial-temporal modeling relies more on language-guided retrieval than on intra- and inter-frame self-attention among video tokens, despite the latter's high computational cost. Finally, we demonstrate that these insights can be leveraged to reduce attention computation in Video-LLMs. To our knowledge, this is the first work to systematically uncover how Video-LLMs internally process and understand video content, offering interpretability and efficiency perspectives for future research.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:fac7df2b603ef8b746e8d292f6612a8fCVF · CVPR 2026

Transform to Transfer: Boosting Adversarial Attack Transferability on Vision-Language Pre-training Models

Li, Yang, Yin, Jia-Li, Lin, Luojun, Lin, Wei

原文摘要

Vision-Language Pre-training (VLP) models, while achieving state-of-the-art performance on various multimodal tasks, exhibit significant vulnerability to multimodal adversarial examples. In black-box attack scenarios of VLP models, a key challenge lies in the limited transferability of these adversarial examples. Existing methods to enhance transferability often suffer from an excessive dependence on the source model and a reliance on limited and fixed transformation techniques. To overcome these limitations, we propose a novel Transform to Transfer Attack (TTA) method. Our approach introduces a learnable transformation mechanism that adaptively selects optimal combinations of transformations to maximize input diversity, and incorporates integrated gradients to mitigate over-reliance on the source model, thereby refining the attack optimization process. Extensive experiments demonstrate that TTA achieves outstanding attack performance in downstream tasks, outperforming current state-of-the-art attack methods across different VLP architectures.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗