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

+2新增论文
+2其中 AI 相关
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 02:57 · 全站最近入库：2026-11-12 06:37各信源进度 →

统计口径与数据新鲜度

统计 2026-11-12 03:20 — 2026-11-13 03:20（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：2026-11-13 02:57最近发现新增版本：2026-11-12 06:37库内论文最新更新时间：2026-11-11 08:00

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。

21,675 已收录论文18,323 AI 相关6,056 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 5,654 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-13 02:56（北京时间）
首次观测 · 记录 #1CVF · CVPR 2026:cvf:a896a3ede348319cadf0fa098c7a2a4cCVF · CVPR 2026

MedTVT-R1: A Multimodal LLM Empowering Medical Reasoning and Diagnosis

Zhang, Yuting, Yuan, Kaishen, Lu, Hao, Yue, Yutao, Chen, Jintai, Wu, Kaishun

原文摘要

Accurate and interpretable multi-disease diagnosis remains a critical challenge in medical research, particularly when leveraging heterogeneous multimodal medical data. Current approaches often rely on single-modal data, limiting their ability to comprehensively understand complex diseases. To address this, we propose MedTVT-R1, a novel Multimodal Large Language Model (MLLM) framework designed to integrate clinical multimodal data for reasoning and diagnosing multiple diseases. We construct MedTVT-QA, a curated instruction dataset that provides question-answer pairs for physiological-level interpretations and disease-level diagnoses with a Chain of Evidence approach. MedTVT-R1 incorporates a modality perception layer to capture inter-modal dependencies and adaptively weight modality contributions. Additionally, we employ Group Relative Policy Optimization (GRPO)-based Reinforcement Fine-Tuning with a Jaccard Reward function to enhance diagnostic reasoning. Experimental results demonstrate MedTVT-R1's superiority in multimodal feature utilization and multi-disease diagnosis, offering significant potential for clinical applications such as diagnostic report generation and comorbidity reasoning. The dataset and code will be available on GitHub.

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:a8bd6d77534d950288dfa60984cc404aCVF · CVPR 2026

PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment

Lee, Suhyeon, Ye, Jong Chul

原文摘要

Despite recent progress, reinforcement learning (RL)-based fine-tuning of diffusion models often struggles with generalization, composability, and robustness against reward hacking. Recent studies have explored prompt refinement as a modular alternative, but most adopt a feed-forward approach that applies a single refined prompt throughout the entire sampling trajectory, thereby failing to fully leverage the sequential nature of reinforcement learning. To address this, we introduce PromptLoop, a plug-and-play RL framework that incorporates latent feedback into step-wise prompt refinement. Rather than modifying diffusion model weights, a multimodal large language model (MLLM) is trained with RL to iteratively update prompts based on intermediate latent states of diffusion models. This design achieves a structural analogy to the Diffusion RL approach, while retaining the flexibility and generality of prompt-based alignment. Extensive experiments across diverse reward functions and diffusion backbones demonstrate that PromptLoop (i) achieves effective reward optimization, (ii) generalizes seamlessly to unseen models, (iii) composes orthogonally with existing alignment methods, and (iv) mitigates over-optimization and reward hacking while introducing only a practically negligible inference overhead.

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:a92db2fcada12c721a2c0becff0284b1CVF · CVPR 2026

Video Panels for Long Video Understanding

Doorenbos, Lars, Spurio, Federico, Gall, Juergen

原文摘要

Recent Video-Language Models (VLMs) achieve promising results on long-video understanding, but their performance still lags behind that achieved on tasks involving images or short videos. This has led to great interest in improving the long context modeling of VLMs by introducing novel modules and additional complexity. In this paper, we take a different approach: rather than fine-tuning VLMs with the limited data available, we attempt to maximize the performance of existing models.To this end, we propose a novel visual prompting strategy specifically designed for long-video understanding. By combining multiple frames as panels into one image, we effectively trade off spatial details for temporal resolution.Our approach is training-free, parameter-free, and model-agnostic, and can be seamlessly integrated into existing VLMs.Extensive experiments on five established benchmarks across a wide range of model architectures, sizes, and context windows confirm the consistency of our approach. For the TimeScope (Long) dataset, which has the longest videos, the accuracy for video question answering is improved by up to 19.4%. Overall, our method raises the bar for long video understanding models. The code is available at https://fedespu.github.io/Video-Panels.

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:a968251c0d705ed081ae1f992029edd5CVF · CVPR 2026

BrickNet: Graph-Backed Generative Brick Assembly

Kulits, Peter, Schmid, Cordelia

原文摘要

We train a language model to generate LEGO(r)-brick build sequences. While prior work has been restricted to discrete, voxel-like towers, we consider a much broader set of pieces, encompassing thousands of part types with diverse connection semantics. To enable this, we first collect a large-scale dataset of over 100,000 human-designed LDraw brick objects and scenes. The complexity of our setting makes it challenging to autoregressively assemble structures that satisfy physical constraints. When predicting block pose directly, build sequences quickly become invalid after a small number of steps. Although pieces are placed in 3D space, it is the spatial relationships of the parts which define the whole. With this in mind, we design a graph-based program representation that parametrizes structure through connectivity, improving the physical grounding of generated sequences. To enable future applications, we make our dataset and models available for research purposes. https://kulits.github.io/BrickNet

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:a97b7997ffa85ba8f6d5b82aa285b9cdCVF · CVPR 2026

OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning

Kang, Hengrui, Gu, Zhuangcheng, Zhao, Zhiyuan, Wen, Zichen, Wang, Bin, Li, Weijia, He, Conghui

原文摘要

Document AI has advanced rapidly and is attracting increasing attention. Yet, while most efforts have focused on document layout analysis (DLA), its generative counterpart, layout generation, remains underexplored. Distinct from traditional graphic layout design and room layout planning, document layout generation typically involves a larger number of elements per page and exhibits greater structural diversity and complexity. Currently, a major obstacle lies in the scarcity of diverse document layouts: academic papers with Manhattan-style structures dominate existing studies, while open-world genres such as newspapers and magazines remain severely underrepresented. To address this gap, we curate OmniDocLayout-1M, the first million-scale dataset of diverse document layouts, covering six common document types and comprising contemporary layouts collected from multiple sources. Moreover, since existing methods struggle in complex domains and often fail to arrange long sequences coherently, we introduce OmniDocLayout-LLM, a 0.5B model with designed two-stage Coarse-to-Fine learning paradigm: 1) learning universal layout principles from our dataset with coarse category definitions, and 2) transferring the knowledge to a specific domain with few fine-grained annotated samples. Extensive experiments demonstrate that our approach achieves strong performance on multiple domains in M^6Doc dataset, substantially surpassing both existing layout generation experts and several latest general-purpose LLMs. More information can be found at https://github.com/opendatalab/OmniDocLayout.

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:a98797dae1b5671e50c09262e2203917CVF · CVPR 2026

MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models

Xu, Yifan, Zhang, Chao, Ma, Ruifei, Gao, Fei, Yang, Zhifei, Qi, Jiaxing, Chen, Zhipeng

原文摘要

The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackling tasks of video understanding. While current VLMs excel at event- or story-level understanding, their ability to capture fine-grained motion details remains limited, primarily due to their focus on high-level static semantic structures and macro-event logic. In contrast, Video Diffusion Models (VDMs) are adept at modeling dynamic motion patterns, benefiting from large-scale video data and the intrinsic requirement of temporal generation. In this paper, we introduce MotionEnhancer, a novel approach that leverages motion priors distilled from a powerful video diffusion model as auxiliary supervision to enhance the motion understanding capability of a VLM via attention alignment. MotionEnhancer comprises two simple parameter-free modules, Motion-sensitive Head Selection (MHS) and Motion-salient Text Token Identification (MTTI), to directly extract and optimize motion-related attentions from the VDM in a computation-only manner. MotionEnhancer provides a scalable solution for motion understanding without additional training parameters, modifications to existing architectures, or tool calling. Extensive experiments demonstrate that MotionEnhancer can achieve consistent improvements over state-of-the-art VLMs on two motion-level video understanding benchmarks, especially on motion-related metrics.

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:a9a9dca5b50c1fb310042c44a46d8276CVF · CVPR 2026

Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding

Hu, Pengfei, Cao, Meng, Wang, Yingyao, Wang, Yi, Dong, Jiahua, Song, Jun, Cheng, Yu, Zheng, Bo 等 9 位作者

原文摘要

Long video understanding is essential for human-like intelligence, enabling coherent perception and reasoning over extended temporal contexts. While the emerging thinking-with-frames paradigm--which alternates between global temporal reasoning and local frame examination--has advanced the reasoning capabilities of video multi-modal large language models (MLLMs), it suffers from a significant efficiency bottleneck due to the progressively growing and redundant multi-modal context. To address this, we propose SpecTemp, a reinforcement learning-based Speculative Temporal reasoning framework that decouples temporal perception from reasoning via a cooperative dual-model design. In SpecTemp, a lightweight draft MLLM rapidly explores and proposes salient frames from densely sampled temporal regions, while a powerful target MLLM focuses on temporal reasoning and verifies the draft's proposals, iteratively refining its attention until convergence. This design mirrors the collaborative pathways of the human brain, balancing efficiency with accuracy. To support training, we construct the SpecTemp-80K dataset, featuring synchronized dual-level annotations for coarse evidence spans and fine-grained frame-level evidence. Experiments across multiple video understanding benchmarks demonstrate that SpecTemp not only maintains competitive accuracy but also significantly accelerates inference compared with existing thinking-with-frames methods.

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:a9b5333fbe7a17f33312eebb76d735c6CVF · CVPR 2026

Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning

Li, Xuchen, Li, Xuzhao, Hu, Shiyu, Huang, Kaiqi

原文摘要

Long-form video reasoning remains a major challenge for Video Large Language Models (Video LLMs), as static uniform frame sampling leads to information dilution and obscures critical evidence. Furthermore, existing pixel-space video reasoning agents, which are designed to actively interact with the video to acquire new visual information, remain suboptimal due to their lack of rigorous reward mechanisms to enforce evidence purity and their inability to perform temporal information supplementation beyond pre-sampled frames. To address this critical gap, we propose a novel evidence-prioritized adaptive framework built upon our core philosophy: "Select Less, Reason More." Our core contribution is the evidence-aware reinforcement learning (EARL) framework, which transforms the model into an active interrogator of evidence. EARL is precisely engineered to dynamically select the most relevant frames and, crucially, to perform localized re-sampling around the selected key frames to access fine-grained temporal detail. Extensive experiments on five demanding video reasoning benchmarks demonstrate that our EARL-trained model achieves new state-of-the-art among open-source Video LLMs, simultaneously learning an effective and high-purity visual evidence selection policy. Impressively, our 7B model achieves 59.8% on LongVideoBench, 69.0% on MVBench and 64.9% on VideoMME. These results highlight the importance of prioritizing evidence purity and the effectiveness of our framework.

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:aa08df1c58cdf8c3dafad6d79abdb7a4CVF · CVPR 2026

DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning

Liu, Zhe, Huang, Runhui, Yang, Rui, Yan, Siming, Wang, Zining, Hou, Lu, Lin, Di, Bai, Xiang 等 9 位作者

原文摘要

Although multi-modal large language models (MLLMs) have shown strong capabilities across diverse domains, their application in generating fine-grained 3D perception and prediction outputs in autonomous driving remains underexplored. In this paper, we propose DrivePI, a novel spatial-aware 4D MLLM that serves as a unified Vision-Language-Action (VLA) framework that is also compatible with vision-action (VA) models. Our method jointly performs spatial understanding, 3D perception (i.e., 3D occupancy), prediction (i.e., occupancy flow), and planning (i.e., action outputs) in parallel through end-to-end optimization. To obtain both precise geometric information and rich visual appearance, our approach integrates point clouds, multi-view images, and language instructions within a unified MLLM architecture. We further develop a data engine to generate text-occupancy and text-flow QA pairs for 4D spatial understanding. Remarkably, with only a 0.5B Qwen2.5 model as MLLM backbone, DrivePI as a single unified model matches or exceeds both existing VLA models and specialized VA models. Specifically, compared to VLA models, DrivePI outperforms OpenDriveVLA-7B by 2.5% mean accuracy on nuScenes-QA and reduces collision rate by 70% over ORION (from 0.37% to 0.11%) on nuScenes. Against specialized VA models, DrivePI surpasses FB-OCC by 10.3 RayIoU for 3D occupancy on OpenOcc, reduces the mAVE from 0.591 to 0.509 for occupancy flow on OpenOcc, and achieves 32% lower L2 error than VAD (from 0.72m to 0.49m) for planning on nuScenes. Code will be available at https://github.com/happinesslz/DrivePI.

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:aa2e3445b6e0e94316b59832cf5e9633CVF · CVPR 2026

Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models

Ma, Ji, Suo, Wei, Wang, Peng, Zhang, Yanning

原文摘要

Multimodal Chain-of-Thought (MCoT) models have demonstrated impressive capability in complex visual reasoning tasks. Unfortunately, recent studies reveal that they suffer from severe hallucination problems due to diminished visual attention during the generation process.However, visual attention decay is a well-studied problem in Large Vision-Language Models (LVLMs). Considering the fundamental differences in reasoning processes between MCoT models and traditional LVLMs, we raise a basic question: Whether MCoT models have unique causes of hallucinations? To answer this question, we systematically investigate the hallucination patterns of MCoT models and find that fabricated texts are primarily generated in associative reasoning steps, which we term divergent thinking. Leveraging these insights, we introduce a simple yet effective strategy that can effectively localize divergent thinking steps and intervene in the decoding process to mitigate hallucinations. Extensive experiments show that our method outperforms existing methods by a large margin. More importantly, our proposed method can be conveniently integrated with other hallucination mitigation methods and further boost their performance. The code is publicly available at https://github.com/ASGO-MM/MCoT-hallucination.

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:aa98e5fdb63780af6f48a3f9f2db6ef8CVF · CVPR 2026

Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision

Jin, Yizhou, Feng, Yuezhu, Zhang, Jinjin, Wang, Peng, Liu, Qingjie, Wang, Yunhong

原文摘要

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to image-level anomaly detection and textual reasoning, while pixel-level localization still relies on external vision modules and dense annotations. In this work, we activate the intrinsic reasoning potential of MLLMs to perform anomaly detection, pixel-level localization, and interpretable reasoning solely from image-level supervision, without any auxiliary components or pixel-wise labels. Specifically, we propose Reasoning-Driven Anomaly Localization (ReAL), which extracts anomaly-related tokens from the autoregressive reasoning process and aggregates their attention responses to produce pixel-level anomaly maps. We further introduce a Consistency-Guided Reasoning Optimization (CGRO) module that leverages reinforcement learning to align reasoning tokens with visual attentions, resulting in more coherent reasoning and accurate anomaly localization. Extensive experiments on four public benchmarks demonstrate that our method significantly improves anomaly detection, localization, and interpretability. Remarkably, despite relying solely on image-level supervision, our approach achieves performance competitive with MLLM-based methods trained under dense pixel-level supervision. Code is available at https://github.com/YizhouJin313/ReADL.

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:ab28918737ccc03ea4fec54a9c3b0cf1CVF · CVPR 2026

TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding

Xu, Boshen, Xiao, Zihan, Li, Jiaze, Ju, Jianzhong, Luo, Zhenbo, Luan, Jian, Jin, Qin

原文摘要

We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal contexts. To this end, TimeViper adopts a hybrid Mamba-Transformer backbone that combines the efficiency of state-space models with the expressivity of attention mechanisms. Through this hybrid design, we reveal the vision-to-text information aggregation phenomenon, where information progressively flows from vision tokens to text tokens across increasing LLM depth, resulting in severe vision token redundancy. Motivated by this observation, we propose TransV, a token information transfer module that transfers and compresses vision tokens into instruction tokens while maintaining multimodal understanding capabilities. This design enables TimeViper to process hour-long videos exceeding thousands of frames. Extensive experiments across multiple benchmarks demonstrate that TimeViper competes with state-of-the-art models while reducing inference cost. We further analyze attention behaviors of both Mamba and Transformer layers, offering new insights into hybrid model interpretability. This work represents an initial step towards developing, interpreting, and compressing hybrid Mamba-Transformer architectures.

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:ab2d78967e988b2893183639b42bb6cbCVF · CVPR 2026

WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation

Ibn Sultan, Rafi, Zhu, Hui, Zhou, Xiangyu, Li, Chengyin, Khanduri, Prashant, Brocanelli, Marco, Zhu, Dongxiao

原文摘要

Ensuring accessible pedestrian navigation requires reasoning about both semantic and spatial aspects of complex urban scenes, a challenge that existing Large Vision-Language Models (LVLMs) struggle to meet. Although these models can describe visual content, their lack of explicit grounding leads to object hallucinations and unreliable depth reasoning, limiting their usefulness for accessibility guidance. We introduce WalkGPT, a pixel-grounded LVLM for the new task of Grounded Navigation Guide, unifying language reasoning and segmentation within a single architecture for depth-aware accessibility guidance. Given a pedestrian-view image and a navigation query, WalkGPT generates a conversational response with segmentation masks that delineate accessible and harmful features along with relative depth estimation. The model incorporates a Multi-Scale Query Projector (MSQP) that shapes the final image tokens by aggregating them along text tokens across spatial hierarchies, and a Calibrated Text Projector (CTP), guided by a Region Alignment Loss, that maps language embeddings into segmentation-aware representations. These components enable fine-grained grounding and depth inference without user-provided cues or anchor points, allowing the model to generate complete and realistic navigation guidance. We also introduce PAVE, a large-scale benchmark of 41k pedestrian-view images paired with accessibility-aware questions and depth-grounded answers. Experiments show that WalkGPT achieves strong grounded reasoning and segmentation performance. The source code and dataset are available on the project website.

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:ab3ccab2fcb96327fc1fb41900837ee8CVF · CVPR 2026

GenSplat: Bridging the Generalization Gap in 3DGS Language Comprehension

Liu, Fang, Liu, Yuhao, Xu, Ke, Hancke, Gerhard Petrus, Lau, Rynson W. H.

原文摘要

In this paper, we propose GenSplat, a novel approach for language comprehension in 3D Gaussian Splatting (3DGS). Unlike previous methods that either achieve cross-scene generalization by being bounded to a predefined vocabulary or handle free-form language by overfitting to individual scenes, GenSplat is robust to free-form language queries and generalizable across 3DGS scene representations. Our key insight for this problem is to formulate a structured learning process to progressively align linguistic concepts with 3D Gaussians. It contains two novel technical contributions. First, we propose a Progressive Language Grounding Curriculum that structurally guides the model through learning category-level semantics to instance-level concepts and free-form language, preventing overfitting by building a generalizable language feature space. Second, we design a Multi-modal Large Language Models (MLLM)-guided Reasoning Module that leverages MLLM's semantic and spatial priors to enhance 3D localization and reasoning. To further improve spatial alignment and computational efficiency, we introduce a GeometryAware Frame Selector (GAFS), which adaptively selects the most informative views based on Gaussian and textural cues. Extensive cross-task evaluations (including 3D referring segmentation, 3D visual question answering, and 3D open-vocabulary understanding) demonstrate state-of-the-art performances and strong generalization capability of GenSplat. We will release the codes.

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:ab4282c41e6153c84fb7a2d85edbe76eCVF · CVPR 2026

Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration

Chen, Weile, Miao, Bingchen, Yu, Qifan, Bu, Wendong, Wang, Guoming, Zhang, Wenqiao, Zhang, Shengyu, Li, Juncheng 等 9 位作者

原文摘要

Recent advances in Multimodal Large Language Models (MLLMs) have led to promising progress in web agents. However, existing web agents often rely on handcrafted execution pipelines or expensive expert trajectories, limiting their adaptability to complex, dynamic environments. To address these challenges, we propose SCALE (Self-Cognitive-Aware Learning and Exploration), which leverages three adversarial roles--Selector, Predictor, and Judger to autonomously discover the agent's limitations and expand its cognitive boundaries through environmental exploration. Moreover, we propose SCALE-Hop, a graph exploration strategy that facilitates global planning and helps agents avoid local exploration traps. To further support learning, we construct SCALE-20k, a large-scale dataset collected from 19 real-world websites, containing diverse task types and structured demonstrations generated from SCALE's exploration traces. Experimental results show that our approach significantly improves the performance and generalization of multiple MLLMs in various web environments. Our framework offers a scalable and generalizable solution for building truly autonomous and adaptive web agents.

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:abc12723d25e36c1f137724ef7cbc87bCVF · CVPR 2026

AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation

Guo, Wenxuan, Xu, Xiuwei, Liu, Yichen, Li, Xiangyu, Yin, Hang, Chen, Huangxing, Zheng, Wenzhao, Feng, Jianjiang 等 10 位作者

原文摘要

Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of-the-art methods leverage the reasoning capabilities of Vision-Language Models (VLMs) for end-to-end action prediction, they often lack an explicit and explainable understanding of the relationships between the agent, the instruction, and the scene. Conversely, explicitly building a scene map for heuristic planning is intuitively appealing but relies on additional 3D sensors and hinders large-scale vision-language pre-training. To bridge this gap, we propose AwareVLN, a novel framework that equips the navigation model with a self-aware reasoning mechanism, enabling it to understand the agent's state and task progress in a fully end-to-end and data-driven manner. Our approach features two key innovations: (1) a structural reasoning module that fosters spatial and task-oriented self-awareness, and (2) an automatic data engine with progress division for effective training. Extensive experiments on various datasets in Habitat simulator show our AwareVLN significantly outperforms previous state-of-the-art vision-language navigation methods. Project page: https://gwxuan.github.io/AwareVLN/.

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:ac1b0ffdc4234c01cf546ceaef8224e7CVF · CVPR 2026

Unsafe2Safe: Controllable Image Anonymization for Downstream Utility

Dinh, Minh, Jin, SouYoung

原文摘要

Large-scale image datasets frequently contain identifiable or sensitive content, raising privacy risks when training models that may memorize and leak such information. We present Unsafe2Safe, a fully automated pipeline that detects privacy-prone images and rewrites only their sensitive regions using multimodally guided diffusion editing. Unsafe2Safe operates in two stages. Stage 1 uses a vision-language model to (i) inspect images for privacy risks, (ii) generate paired private and public captions that respectively include and omit sensitive attributes, and (iii) prompt a large language model to produce structured, identity-neutral edit instructions conditioned on the public caption. Stage 2 employs instruction-driven diffusion editors to apply these dual textual prompts, producing privacy-safe images that preserve global structure and task-relevant semantics while neutralizing private content. To measure anonymization quality, we introduce a unified evaluation suite covering Quality, Cheating, Privacy, and Utility dimensions. Across MS-COCO, Caltech101 and MIT Indoor67, Unsafe2Safe reduces face similarity, text similarity, and demographic predictability by large margins, while maintaining downstream model accuracy comparable to training on raw data. Fine-tuning diffusion editors on our automatically generated triplets (private caption, public caption, edit instruction) further improves both privacy protection and semantic fidelity. Unsafe2Safe provides a scalable, principled solution for constructing large, privacy-safe datasets without sacrificing visual consistency or downstream utility.

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:ac2ebbeefcc5bb12b15a0a0b57c94454CVF · CVPR 2026

Foundation Encoders Are All You Need for Preference-Aware Personalization

Kim, Hyungjin, Ahn, Seokho, Seo, Young-Duk

原文摘要

Personalized image generation based on user behavior reflects individual preferences with minimal user intervention. However, existing studies often rely on inaccurate profiling, high resource costs, and model-specific designs, which jointly restrict creativity, diversity, and generality. To address these limitations, we propose FAN, a novel approach that enables preference-aware personalization using only foundation encoders, without additional structures. FAN performs tailored profiling to capture user preferences and reconstructs transformer-based encoders to integrate them while preserving target fidelity. Experiments show that FAN achieves robust personalization across various foundation text-to-image models. It also extends to applications such as CLIP retrieval, unCLIP, and vision-language models, seamlessly integrating into diverse encoders without fine-tuning.

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:ac314b74535258aaa160d451baf2c68eCVF · CVPR 2026

DocPrune: Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning

Choi, Joonmyung, Lee, Sanghyeok, Kim, Jongha, Kim, Sehyung, Ko, Dohwan, Kil, Jihyung, Kim, Hyunwoo J.

原文摘要

Recent advances in vision-language models have shown strong performance across diverse multimodal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike natural images, document images contain large backgrounds and only sparse supporting evidence, leading to the waste of substantial computational resources, especially for long documents. We observe that existing token reduction methods for natural images and videos fall short in utilizing the structural sparsity unique to documents. To address this, we propose DOCPRUNE, a training-free document token pruning framework designed for efficient long document understanding. The proposed method preserves only the essential tokens for the task while removing unnecessary ones, such as background or question-irrelevant tokens. Moreover, it automatically selects the appropriate layers to initiate token pruning based on the model's level of comprehension. Our experiments on the M3DocRAG benchmark show that DOCPRUNE improves throughput by 3.0x and 3.3x in the encoder and decoder, respectively, while boosting the F1 score by +1.0, achieving both higher accuracy and efficiency without any additional training.

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:ac4a6a555b6771a9f33dcf37c84d10f7CVF · CVPR 2026

DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles

Ma, Yiming, Yang, Hongkun, Wang, Lionel Z., Chen, Bin, Xian, Weizhi, Teng, Jianzhi

原文摘要

Prompt learning is a dominant paradigm for adapting pre-trained Vision-Language Models (VLMs) to downstream tasks. However, existing methods often rely on a simplistic, layer-centric view, assuming shallow layers capture general features while deep layers handle task-specific knowledge. This assumption results in uncontrolled interactions between learnable tokens and original tokens. Task-specific knowledge could degrade the model's core generalization and creates a trade-off between task adaptation and the preservation of zero-shot generalization. To address this, we challenge the layer-centric view and propose **DeAR**, a framework that achieves fine-grained VLM adaptation by **De**composing **A**ttention head **R**oles. We posit that the functional specialization within VLMs occurs not between layers, but at the finer-grained level of individual attention heads in the deeper layers. Based on this insight, we introduce a novel metric, Concept Entropy, to systematically classify attention heads into distinct functional roles: *Attribute*, *Generalization*, and *Mixed*. Guided by these roles, we introduce specialized attribute tokens and a Role-Based Attention Mask mechanism to precisely control information flow, ensuring generalization heads remain isolated from task-specific knowledge. We further incorporate a Task-Adaptive Fusion Strategy for inference. Extensive experiments on fifteen datasets show that DeAR achieves a strong balance between task adaptation and generalization, outperforming previous methods across various tasks.

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:accaf11ad12d0b504fcb5770f7621757CVF · CVPR 2026

SCoRe: Salience-Coverage Reduction for Vision Token Pruning in Vision-Language Models

Xu, Tong, Shi, Hailong, Gao, Xingyu

原文摘要

The heavy computational burden of Large Vision-Language Models (LVLMs) stems primarily from the lengthy visual token sequences generated by their vision encoders. To mitigate this, recent work has shifted towards pruning tokens within the vision encoder. However, we observe that these methods predominantly rely on a suboptimal decoupled heuristic method. This strategy is conceptually flawed: it is prone to sampling collapse, fails to fundamentally eliminate token redundancy, and tends to systematically discard secondary yet important semantic clusters. Addressing this limitation, this paper proposes to formalize visual token pruning as a unified Representativeness Optimization Problem. We introduce SCoRe (Salience-Coverage Reduction), a unified optimization method theoretically grounded in the Weighted k-Center Problem. SCoRe constructs the final token set greedily: at each iteration, it selects the token that maximizes the unified representativeness score, thereby optimizing global representativeness. Extensive experiments demonstrate that SCoRe achieves State-of-the-Art (SOTA) performance across multiple benchmarks. Notably, with negligible computational overhead, our method reduces tokens by 94.4% while retaining 95% of the full performance.

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:acd49512739a4e0189d93aac1e7476e8CVF · CVPR 2026

RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation

Li, Linfei, Zhang, Lin, Shen, Ying

原文摘要

Visual-language grounding aims to establish semantic correspondences between natural language and visual entities, enabling models to accurately identify and localize target objects based on textual instructions. Existing VLG approaches focus on coarse-grained, object-level localization, while traditional robotic grasping methods rely predominantly on geometric cues and lack language guidance, which limits their applicability in language-driven manipulation scenarios. To address these limitations, we propose the RealVLG framework, which integrates the RealVLG-11B dataset and the RealVLG-R1 model to unify real-world visual-language grounding and grasping tasks. RealVLG-11B dataset provides multi-granularity annotations including bounding boxes, segmentation masks, grasp poses, contact points, and human-verified fine-grained language descriptions, covering approximately 165,000 images, over 800 object instances, 1.3 million segmentation, detection, and language annotations, and roughly 11 billion grasping examples. Building on this dataset, RealVLG-R1 employs Reinforcement Fine-tuning on pretrained large-scale vision-language models to predict bounding boxes, segmentation masks, grasp poses, and contact points in a unified manner given natural language instructions. Experimental results demonstrate that RealVLG supports zero-shot perception and manipulation in real-world unseen environments, establishing a unified semantic-visual multimodal benchmark that provides a comprehensive data and evaluation platform for language-driven robotic perception and grasping policy learning. All data and code are publicly available at https://github.com/lif314/RealVLG-R1.

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:ad99703b072e1cb54d63acdeb3a0f982CVF · CVPR 2026

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness

Elisha, Yehonatan, Barkan, Oren, Koenigstein, Noam

原文摘要

Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features. Existing regularization methods, typically relying on simple foreground-background masks, which fail to capture the fine-grained semantic concepts that define an object (e.g., "long beak" and "wings" for a "bird"). As a result, these methods provide limited robustness to distribution shifts. To address this limitation, we introduce a novel finetuning framework that steers model reasoning toward concept-level semantics. Our approach optimizes the model's internal relevance maps to align with spatially grounded concept masks. These masks are generated automatically, without manual annotation: class-relevant concepts are first proposed using an LLM-based, label-free method, and then segmented using a VLM. The finetuning objective aligns relevance with these concept regions while simultaneously suppressing focus on spurious background areas. Notably, this process requires only a minimal set of images and uses half of the dataset classes. Extensive experiments on five out-of-distribution benchmarks demonstrate that our method improves robustness across multiple ViT-based models. Furthermore, we show that the resulting relevance maps exhibit stronger alignment with semantic object parts, offering a scalable path toward more robust and interpretable vision models. Finally, we confirm that concept-guided masks provide more effective supervision for model robustness than conventional segmentation maps, supporting our central hypothesis.

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:addcc910eb79f97e1053d4c8f572b767CVF · CVPR 2026

Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models

Zhu, Xingyu, Zhu, Beier, Wang, Shuo, Fang, Junfeng, Zhao, Kesen, Zhang, Hanwang, He, Xiangnan

原文摘要

As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to generate harmful content, posing serious risks to model safety and trustworthy usage.Recent activation steering methods inject directional vectors into model activations during inference to induce refusal behaviors and have demonstrated effectiveness.However, a steering vector may both enhance refusal ability and cause over-refusal, thereby degrading model performance on benign inputs.Moreover, due to the lack of theoretical interpretability, these methods still suffer from limited robustness and effectiveness.To better balance safety and utility, we propose \texttt NullSteer , a null-space projected activation defense framework.Our method constructs refusal directions within model activations through a linear transformation: it maintains zero perturbation within the benign subspace while dynamically inducing refusal along potentially harmful directions, thereby theoretically achieving safety enhancement without impairing the model's general capabilities.Extensive experiments show that \texttt NullSteer significantly reduces harmful outputs under various jailbreak attacks (average ASR reduction over 15% on MiniGPT-4) while maintaining comparable performance to the original model on general benchmarks.

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:ae235f3e57e46dfbb1e096718a9ff754CVF · CVPR 2026

MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models

Yao, Xincheng, Qian, Zefeng, Shi, Chao, Song, Jiayang, Zhang, Chongyang

原文摘要

In the progress of industrial anomaly detection, general anomaly detection (GAD) is an emerging trend and also the ultimate goal. Unlike the conventional single- and multi-class AD, general AD aims to train a general AD model that can directly detect anomalies in diverse novel classes without any retraining or fine-tuning on the target data. Recently, Multimodal Large Language Models (MLLMs) have shown great promise in achieving general anomaly detection due to their revolutionary visual understanding and language reasoning capabilities. However, MLLM's general AD ability remains underexplored due to: (1) MLLMs are pretrained on amounts of data sourced from the Web, these data still have significant gaps with the data in AD scenarios. Moreover, the image-text pairs during pretraining are also not specifically for AD tasks. (2) The current mainstream AD datasets are image-based and not yet suitable for post-training MLLMs. To facilitate MLLM-based general AD research, we present MMR-AD, which is a comprehensive benchmark for both training and evaluating MLLM-based AD models. With MMR-AD, we reveal that the AD performance of current SOTA generalist MLLMs still falls far behind the industrial requirements. Based on MMR-AD, we also propose a baseline model, Anomaly-R1, which is a reasoning-based AD model that learns from the CoT data in MMR-AD and is further enhanced by reinforcement learning. Extensive experiments show that our Anomaly-R1 achieves remarkable improvements over generalist MLLMs in both anomaly detection and localization.

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:aed0f81b49a35b728047f0f8dc26b75fCVF · CVPR 2026

Dynamic Logits Adjustment and Exploration for Test-Time Adaptation in Vision Language Models

Wu, Haoyan, Liu, Yahao, Lei, Yinjie, Duan, Lixin, Li, Wen

原文摘要

Existing Test-Time Adaptation (TTA) methods for Vision-Language Models (VLMs), focusing on designing efficient adaptation parameters (eg. prompts or residual prototypes), predominantly rely on high-confidence samples obtained via entropy-based filtering. However, this prevailing paradigm implicitly inherits the VLM's class-wise prediction biases and leads to insufficient coverage of the test distribution, rendering the adaptation process biased and insufficiently exploratory.To overcome these limitations, we propose Dynamic Logits Adjustment and Exploration (DLAE), a novel framework that integrates Dynamic Logit Adjustment (DLA) with a Consistency-Guided Exploratory Cache (CGEC). DLA dynamically recalibrates model logits based on test prediction statistics, thereby mitigating class-wise prediction inconsistencies. Different from traditional cache mechanisms, our CGEC actively identifies additional samples near decision boundaries whose predicted labels are sensitive to the logit adjustment, thereby exploring beyond only high-confidence samples. By enforcing semantic and temporal consistency, the cache preserves the reliability of selected samples while enabling cautious yet effective exploration of low-confidence regions, ultimately yielding stable and reliable adaptation.Extensive experiments across multiple vision-language benchmarks demonstrate that our approach consistently surpasses state-of-the-art TTA methods, showing superior stability, adaptability, and generalization.

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:af2bf5c42a6ef2448d24b2c6d912cf62CVF · CVPR 2026

CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions

Wang, Chonghuinan, Chen, Zihan, Wei, Yuxiang, Jiang, Tianyi, Wu, Xiaohe, Li, Fan, Zuo, Wangmeng, Yao, Hongxun

原文摘要

Instruction-based multimodal image manipulation has recently made rapid progress. However, existing evaluation methods lack a systematic and human-aligned framework for assessing model performance on complex and creative editing tasks. To address this gap, we propose CREval, a fully automated question-answer (QA)-based evaluation pipeline that overcomes the incompleteness and poor interpretability of opaque Multimodal Large Language Models (MLLMs) scoring. Simultaneously, we introduce CREval-Bench, a comprehensive benchmark specifically designed for creative image manipulation under complex instructions. CREval-Bench covers three categories and nine creative dimensions, comprising over 800 editing samples and 13K evaluation queries. Leveraging this pipeline and benchmark, we systematically evaluate a diverse set of state-of-the-art open and closed-source models. The results reveal that while closed-source models generally outperform open-source ones on complex and creative tasks, all models still struggle to complete such edits effectively. In addition, user studies demonstrate strong consistency between CREval's automated metrics and human judgments. Therefore, CREval provides a reliable foundation for evaluating image editing models on complex and creative image manipulation tasks, and highlights key challenges and opportunities 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:af48ff8dcb265c9e043d380d3244334aCVF · CVPR 2026

Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding

Kwon, Mincheol, Lee, Minseung, Choi, Seonga, Choi, Miso, Oh, Kyeongjin, Lee, Hyunyoung, Park, Cheonyoung, Song, Yongho 等 10 位作者

原文摘要

Large Vision-Language Models (LVLMs) have shown strong performance across various multimodal tasks by leveraging the reasoning capabilities of Large Language Models (LLMs). However, processing visually complex and information-rich images, such as infographics or document layouts, requires these models to generate a large number of visual tokens, leading to significant computational overhead. To address this, we propose PinPoint, a novel two-stage framework that first identifies instruction-relevant image regions and then refines them to extract fine-grained visual features for improved reasoning and efficiency. Central to our approach is the Instruction-Region Alignment, which localizes relevant regions using both visual input and textual instructions. We further introduce new annotations that provide richer ground-truth supervision for instruction-relevant regions across challenging VQA benchmarks: InfographicVQA, MultiPageDocVQA, and SinglePageDocVQA. Experimental results show that PinPoint not only achieves superior accuracy compared to existing methods but also reduces computational overhead by minimizing irrelevant visual tokens.

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:af60c5dec9528de009ae0ded855c05dbCVF · CVPR 2026

Self-Corrected Image Generation with Explainable Latent Rewards

Luo, Yinyi, Gokhale, Hrishikesh, Savvides, Marios, Wang, Jindong, He, Shengfeng

原文摘要

Despite significant progress in text-to-image generation, aligning outputs with complex prompts remains challenging, particularly for fine-grained semantics and spatial relations. This difficulty stems from the feed-forward nature of generation, which requires anticipating alignment without fully understanding the output. In contrast, evaluating generated images is more tractable. Motivated by this asymmetry, we propose xLARD, a self-correcting framework that uses multimodal large language models to guide generation through Explainable Latent Rewards. xLARD introduces a lightweight corrector that refines latent representations based on structured feedback from model-generated references. A key component is a differentiable mapping from latent edits to interpretable reward signals, enabling continuous latent-level guidance from non-differentiable image-level evaluations. This mechanism allows the model to understand, assess, and correct itself during generation. Experiments across diverse generation and editing tasks show that xLARD improves semantic alignment and visual fidelity while maintaining generative priors, offering a data-efficient and generalizable solution to bridging the gap between comprehension and synthesis.

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:afd0e7611c2158af2b19abe2a4305183CVF · CVPR 2026

EarlyTom: Early Token Compression Completes Fast Video Understanding

Wang, Hesong, Jin, Xin, Lu, Lu, Li, Chenhaowen, Chen, Jian, Liu, Qiang, Wang, Huan

原文摘要

Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is still hindered by the inefficiency introduced by processing massive amounts of visual tokens. Although recent approaches achieve extremely low token retention ratios while maintaining accuracy comparable to full-token baselines, most of them perform compression only at the late stage of prefilling, leaving the efficiency of the vision encoder unoptimized. In this paper, we first show that vision encoding contributes a large portion to the time-to-first-token (TTFT). Therefore, instead of compressing visual tokens only after the vision encoder, performing compression inside the encoder still leaves substantial room for exploration. Based on this insight, we propose EarlyTom, a training-free token compression framework that performs early-stage visual token compression inside the vision encoder, enabling significantly better TTFT reduction and higher throughput. In addition, we introduce a decoupled spatial token selection strategy that improves the overall compression effectiveness. EarlyTom reduces TTFT by up to 2.65x and FLOPs by up to 61% on a single NVIDIA A100 GPU for the LLaVA-OneVision-7B model, while maintaining accuracy comparable to the full-token baseline. These improvements substantially enhance the practicality of deploying Video-LLMs in real-world production scenarios.

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 ↗