跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+92新增 AI 导读

arXiv 最近完成扫描:2026-11-22 21:02 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-22 00:13 — 2026-11-23 00:13(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:2026-11-22 21:02最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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 27 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 21:00(北京时间)
首次观测 · 记录 #1CVF · CVPR 2026:cvf:02a4a089a224d9d3742917254d9635bbCVF · CVPR 2026

CoIn: Coverage and Informativeness-Guided Token Reduction for Efficient Large Multimodal Models

Du, Chenxi, Deng, Yongheng, Liu, Jiani, Zhang, Yujia, Chen, Xi, Ren, Ju

原文摘要

Large Multimodal Models (LMMs) have shown remarkable success in visual understanding tasks. LMMs encode visual and textual inputs into tokens, which are then processed by Large Language Models (LLMs). However, the large number of visual tokens poses a major bottleneck for inference efficiency and memory usage. Reducing visual tokens is a promising training-free solution, but existing methods remain limited. Importance-based approaches suffer from poor generalization, are incompatible with kernel-level inference optimizations, and only consider information from a single modality. Diversity-based strategies typically focus on pairwise token redundancy and treat all tokens as equally important. Recent attempts to sequentially combine importance and diversity criteria still fail to address the intrinsic drawbacks of their underlying metrics. To address these limitations, we reformulate visual token reduction as an optimal subset selection problem jointly guided by two complementary objectives: informativeness and coverage. Informativeness is quantified through per-token intrinsic saliency and visual-textual alignment, while coverage is enforced via a volume-based subset selection criterion that ensures global representativeness in the visual feature space. This joint formulation effectively integrates visual saliency, cross-modal alignment, and global coverage in an end-to-end token selection process, yielding a computationally efficient, model-agnostic framework compatible with modern inference accelerators. Extensive experiments demonstrate that CoIn substantially reduces computation and memory cost while maintaining strong task performance.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:110201523236778bef23f4ef6f86db31CVF · CVPR 2026

NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object Detection

Zhang, Yupeng, Han, Ruize, Chen, Zhiwei, Feng, Wei, Wan, Liang

原文摘要

Despite the remarkable progress in open-vocabulary object detection (OVD), a significant gap remains between the training and testing phases. During training, the RPN and RoI heads often misclassify unlabeled novel-category objects as background, causing some proposals to be prematurely filtered out by the RPN while others are further misclassified by the RoI head. During testing, these proposals again receive low scores and are removed in post-processing, leading to a significant drop in recall and ultimately weakening novel-category detection performance.To address these issues, we propose a novel training framework--NoOVD--which innovatively integrates a self-distillation mechanism grounded in the knowledge of frozen vision-language models (VLMs).Specifically, we design K-FPN, which leverages the pretrained knowledge of VLMs to guide the model in discovering novel-category objects and facilitates knowledge distillation--without requiring additional data--thus preventing forced alignment of novel objects with background.Additionally, we introduce R-RPN, which adjusts the confidence scores of proposals during inference to improve the recall of novel-category objects.Cross-dataset evaluations on OV-LVIS, OV-COCO, and Objects365 demonstrate that our approach consistently achieves superior performance across multiple metrics.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:23db52496d196ddecc55d87a11ead7ebCVF · CVPR 2026

VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models

Yu, Xinlei, Xu, Chengming, Zhang, Guibin, Chen, Zhangquan, Zhang, Yudong, He, Yongbo, Jiang, Peng-Tao, Zhang, Jiangning 等 10 位作者

原文摘要

Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a deficit in contextualized visual experience during prolonged generation. Drawing inspiration from human cognitive memory theory, which distinguishes short-term visually-dominant memory and long-term semantically-dominant memory, we propose VisMem, a cognitively-aligned framework that equips VLMs with dynamic latent vision memories, a short-term module for fine-grained perceptual retention and a long-term module for abstract semantic consolidation. These memories are seamlessly invoked during inference, allowing VLMs to maintain both perceptual fidelity and semantic consistency across thinking and generation. Extensive experiments across diverse visual benchmarks for understanding, reasoning, and generation reveal that VisMem delivers a significant average performance boost of 11.0% relative to the vanilla model and outperforms all counterparts, establishing a new paradigm for latent-space memory enhancement. The code will be available: https://github.com/YU-deep/VisMem.git.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:2ed3d0661b614c00759dd2bde6c61adaCVF · CVPR 2026

GeoCoT: Towards Reliable Remote Sensing Reasoning with Manifold Perspective

Li, Daixun, Li, Zirui, He, Sibo, Tian, Jiayun, Cao, Mingxiang, Xie, Weiying, Wang, Yunke, Zhang, Xin 等 12 位作者

原文摘要

Multimodal Large Language Models (MLLMs) have shown strong potential in remote sensing (RS) through multi-task reasoning and cross-modal generalization.However, existing RS-MLLMs mainly rely on a single shared expert for all tasks, making it hard to produce reliable results. Meanwhile, the intrinsic redundancy and homogeneity of RS images bring substantial difficulties for both training and inference. These challenges directly conflict with the demands of remote sensing, which values task precision and trustworthy reasoning.To address these limitations, we propose GeoCoT, a manifold-driven mixture-of-experts (MoE) system with Chain-of-Thought (CoT) reasoning. GeoCoT introduces Mani-MoE, a sparse expert architecture grounded in local manifold mapping. It projects high-dimensional tokens onto low-rank subspaces adaptively to eliminate redundancy and uncover intrinsic structure, and then routes them through a sparse expert pathway, where gating decisions are guided by the manifold structure of the input.To optimize this architecture, we adopt a CoT-driven multi-stage training strategy. It leverages a cold-start phase for domain adaptation, followed by our RS Vision Group Relative Policy Optimization (RSV-GRPO) to systematically strengthen structured reasoning from global to objectives. Furthermore, we innovatively build *RS-CoT-20k* dataset for task-specific supervision.Extensive experiments on multi-task datasets demonstrate that GeoCoT outperforms prior approaches, achieving 5.27 \% higher average accuracy than the state-of-the-art method. Our code will be available.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:35e1a7b1cf55e5fb9418d0af07929891CVF · CVPR 2026

See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection

Wu, Zhiheng, Wang, Tong, Wang, Shuning, Liu, Naiming, Zhang, Yumeng

原文摘要

Recent advances in Vision-Language Models (VLMs) have benefited from Reinforcement Learning (RL) for enhanced reasoning. However, existing methods still face critical limitations, including the lack of low-level visual information and effective visual feedback. To address these problems, this paper proposes a unified multimodal interleaved reasoning framework ForeSight, which enables VLMs to See Further with low-level visual cues and Think Deeper with effective visual feedback. First, it introduces a set of low-level visual tools to integrate essential visual information into the reasoning chain, mitigating the neglect of fine-grained visual features. Second, a mask-based visual feedback mechanism is elaborated to incorporate visual reflection into the thinking process, enabling the model to dynamically re-examine and update its answers. Driven by RL, ForeSight learns to autonomously decide on tool invocation and answer verification, with the final answer accuracy as the reward signal. To evaluate the performance of the proposed framework, we construct a new dataset, Character and Grounding SalBench (CG-SalBench), based on the SalBench dataset. Experimental results demonstrate that the ForeSight-7B model significantly outperforms other models with the same parameter scale, and even surpasses the current SOTA closed-source models on certain metrics.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:41eff9ac8e86850c2850eba227b0e7c4CVF · CVPR 2026

The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts

Zhang, Yuchen, Wang, Yaxiong, Wu, Yujiao, Wu, Lianwei, Zhu, Li, Zheng, Zhedong

原文摘要

The detection and grounding of multimedia manipulation has emerged as a critical challenge in combating AI-generated disinformation. While existing methods have made progress in recent years, we identify two fundamental limitations in current approaches: (1) Underestimation of MLLM-driven deception risk: prevailing techniques primarily address rule-based text manipulations, yet fail to account for sophisticated misinformation synthesized by multimodal large language models (MLLMs) that can dynamically generate semantically coherent, contextually plausible yet deceptive narratives conditioned on manipulated images; (2) Unrealistic misalignment artifacts: currently focused scenarios rely on artificially misaligned content that lacks semantic coherence, rendering them easily detectable. To address these gaps holistically, we propose a new adversarial pipeline that leverages MLLMs to generate high-risk disinformation. Our approach begins with constructing the MLLM-Driven Synthetic Multimodal (MDSM) dataset, where images are first altered using state-of-the-art editing techniques and then paired with MLLM-generated deceptive texts that maintain semantic consistency with the visual manipulations. Building upon this foundation, we present the Artifact-aware Manipulation Diagnosis via MLLM (AMD) framework featuring two key innovations: Artifact Pre-perception Encoding strategy and Manipulation-Oriented Reasoning, to tame MLLMs for the MDSM problem. Comprehensive experiments validate our framework's superior generalization capabilities as a unified architecture for detecting MLLM-powered multimodal deceptions. In cross-domain testing on the MDSM dataset, AMD achieves the best average performance, with ACC, mAP, and mIoU scores of 88.18, 60.25, and 61.02, respectively.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:4d607b85ff7ea4220a19f9a957c0e595CVF · CVPR 2026

Gastric-X: A Multimodal Multi-Phase Benchmark Dataset for Advancing Vision-Language Models in Gastric Cancer Analysis

Li, Yuanzhe, Chen, Hao, Yin, Rui, Ba, Juyan, Zhang, Yu, Lu, Sheng

原文摘要

Recent vision-language models (VLMs) have shown strong generalization and multimodal reasoning abilities in natural domains. However, their application to medical diagnosis remains limited by the lack of comprehensive and structured datasets that capture real clinical workflows. To advance the development of VLMs for clinical applications, particularly in gastric cancer, we introduce Gastric-X, a large-scale multimodal benchmark for gastric cancer analysis providing 1.7K cases. Each case in Gastric-X includes paired resting and dynamic CT scans, endoscopic image, a set of structured biochemical indicators, expert-authored diagnostic notes, and bounding box annotations of tumor regions, reflecting realistic clinical conditions. We systematically examine the capability of recent VLMs on five core tasks: Visual Question Answering (VQA), report generation, cross-modal retrieval, disease classification, and lesion localization. These tasks simulate critical stages of clinical workflow, from visual understanding and reasoning to multimodal decision support. Through this evaluation, we aim not only to assess model performance but also to probe the nature of VLM understanding: Can current VLMs meaningfully correlate biochemical signals with spatial tumor features and textual reports? We envision Gastric-X as a step toward aligning machine intelligence with the cognitive and evidential reasoning processes of physicians, and as a resource to inspire the development of next-generation medical VLMs.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:4d7c456cc7631ead2610720978453d7eCVF · CVPR 2026

GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation

Deng, Tianchen, Chen, Xuefeng, Chen, Yi, Chen, Qu, Xu, Yuyao, Yang, Lijin, Xu, Le, Zhang, Yu 等 11 位作者

原文摘要

Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding capabilities and can only generate content conditioned on input data, without the ability to interpret or reason about the driving environment. Moreover, current approaches represent 3D spatial information with point cloud or BEV features do not accurately align textual information with the underlying 3D scene. To address these limitations, we propose a novel unified DWM framework based on 3D Gaussian scene representation, which enables both 3D scene understanding and multi-modal scene generation, while also enabling contextual enrichment for understanding and generation tasks. Our approach directly aligns textual information with the 3D scene by embedding rich linguistic features into each Gaussian primitive, thereby achieving early modality alignment. In addition, we design a novel task-aware language-guided sampling strategy that removes redundant 3D Gaussians and injects accurate and compact 3D tokens into LLM. Furthermore, we design a dual-condition multi-modal generation model, where the information captured by our vision-language model is leveraged as a high-level language condition in combination with a low-level image condition, jointly guiding the multi-modal generation process. We conduct comprehensive studies on the nuScenes, and NuInteract datasets to validate the effectiveness of our framework. Our method achieves state-of-the-art performance. We will release the code publicly on GitHub.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:5cecb6420f8c9c148f85c4d697bfb852CVF · CVPR 2026

3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience

Xiao, Hongcan, Xiao, Xinyue, Wang, Yilin, Zhang, Yue, Qi, Yonggang

原文摘要

Sketching in 3D space enables expressive reasoning about shape, structure, and spatial relationships, yet generating 3D sketches through natural language remains a major challenge. In this work, we introduce 3DrawAgent, a training-free, language-driven framework for 3D sketch generation that leverages large language models (LLMs) to sequentially draw 3D Bezier curves under geometric feedback. Unlike prior 2D sketch agents, our method introduces a relative experience optimization strategy that adapts the recently proposed Group Reward Policy Optimization (GRPO) paradigm. Instead of relying on explicit ground-truth supervision, we construct pairwise comparisons among generated sketches, with each pair consisting of a relatively better and a worse result based on CLIP-based perceptual rewards and LLM-based fine-grained qualitative assessment. These experiences are then used to iteratively refine the prior knowledge of 3D drawing, enabling black-box reinforcement of the model's 3D awareness. This design allows our model to self-improve its spatial understanding and drawing quality without parameter updates. Experiments show that 3DrawAgent can generate complex and coherent 3D Bezier sketches from diverse textual prompts, exhibit emergent geometric reasoning, and generalize to novel shapes, establishing a new paradigm for advancing the field of training-free 3D sketch intelligence.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:611a54e10f7f9cd45b8de19ab9e34169CVF · CVPR 2026

DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding

Yan, Hao, Liu, Yuliang, Liu, Xingchen, Zhang, Yuyi, Liao, Minghui, Wu, Jihao, Chen, Wei, Bai, Xiang

原文摘要

Existing Multimodal Large Language Models (MLLMs) suffer from significant performance degradation on the long document understanding task as document length increases. This stems from two fundamental challenges: 1) a low Signal-to-Noise Ratio (SNR), with crucial evidence buried in irrelevant pages; and 2) supervision scarcity, as datasets offering only final short answers provide a weak learning signal. In this paper, we address these challenges by proposing a paradigm that requires the model to execute a structured "Analysis, Localization and Reasoning" workflow. To instill this capability, we design a two-stage training framework: we first perform Supervised Fine-Tuning on high-quality data generated via an efficient knowledge distillation strategy. Subsequently, we employ an Evidence-aware Group Relative Policy Optimization which jointly optimizes for both evidence localization and answer accuracy. Additionally, we introduce a Evidence-Guided Resolution Allocation strategy to mitigate memory constraints of training on multi-pages documents. Extensive experiments demonstrate that DocSeeker achieves superior performance on both in-domain and out-of-domain tasks. We show it robustly generalizes from short-page training to ultra-long documents and is naturally synergistic with visual Retrieval-Augmented Generation systems, serving as an ideal foundation for their implementation.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:6d1c4105d7e9e86e5e729af4dd9b4ec4CVF · CVPR 2026

Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark

Chen, Seng Nam, Chen, Hao, Ho, Chenglam, Mao, Xinyu, Wang, Jinping, Zhang, Yu, Li, Chao

原文摘要

Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding over long contexts. In this work, we define a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent, aligning with human perception. This leads us to a key question: Can current VLMs reason effectively over long, scene-level contexts? To answer this, we introduce a new benchmark, SceneBench, designed to provide scene-level challenges. Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context. To further validate these findings, we propose Scene Retrieval-Augmented Generation (Scene-RAG), which constructs a dynamic scene memory by retrieving and integrating relevant context across scenes. Scene-RAG improves VLM performance by +2.50%, confirming that current models still struggle with long-context retention. We hope SceneBench will encourage future research toward VLMs with more robust, human-like video comprehension.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:7596eb77843d57da386eda9a6a8219beCVF · CVPR 2026

Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR

Zhang, Yulong, Liang, Tianyi, Cui, Erfei, Wang, Guoqing, Guo, Xu, Li, Chenhui, Liu, Gongshen

原文摘要

Optical Character Recognition (OCR) is fundamental to Vision-Language Models (VLMs) and high-quality data generation for LLM training. Yet, despite progress in average OCR accuracy, state-of-the-art VLMs still struggle with detecting sample-level errors and lack effective unsupervised quality control.We introduce Consensus Entropy (CE), a training-free, model-agnostic metric that estimates output reliability by measuring inter-model agreement entropy. The core insight is that correct predictions converge in output space, while errors diverge. Based on CE, we develop CE-OCR, a lightweight multi-model framework that verifies outputs by ensemble agreement, selects the best outputs, and further improves efficiency through adaptive routing. Experiments demonstrate that CE is robust for quality verification, improving F1 scores by 42.1% over VLM-as-Judge. CE-OCR achieves consistent OCR gains, outperforming self-consistency and single-model baselines at the same cost. Notably, CE requires no training or supervision, enabling plug-and-play integration.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:88d761b99916621fed4669dab1b23b6bCVF · CVPR 2026

HandX: Scaling Bimanual Motion and Interaction Generation

Zhang, Zimu, Zhang, Yucheng, Xu, Xiyan, Wang, Ziyin, Xu, Sirui, Zhou, Kai, Zhou, Bing, Guo, Chuan 等 11 位作者

原文摘要

Synthesizing human motion has advanced rapidly, yet realistic hand motion and bimanual interaction remain underexplored. Whole-body models often miss the fine-grained cues that drive dexterous behavior, finger articulation, contact timing, and inter-hand coordination, and existing resources lack high-fidelity bimanual sequences that capture nuanced finger dynamics and collaboration. To fill this gap, we present HandX, a unified foundation spanning data, annotation, and evaluation. We consolidate and filter existing datasets for quality, and collect a new motion-capture dataset targeting underrepresented bimanual interactions with detailed finger dynamics. For scalable annotation, we introduce a decoupled paradigm that extracts representative motion features, e.g., contact events and finger flexion, and then leverages reasoning from large language models to produce fine-grained, semantically rich descriptions aligned with these features. Building on the resulting data and annotations, we benchmark diffusion and autoregressive models with versatile conditioning modes. Experiments demonstrate high-quality dexterous motion generation, supported by our newly proposed hand-focused metrics. We further observe clear scaling trends: larger models trained on larger, higher-quality datasets produce more semantically coherent bimanual motion. Our dataset is released to support future research.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:8b503d83c15074f8a4e04aa385b9346bCVF · CVPR 2026

MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent

Fu, Yuxia, Zhang, Zhizhen, Zhang, Yuqi, Wang, Zijian, Huang, Zi, Luo, Yadan

原文摘要

Recent Vision-Language-Action (VLA) models reformulate vision-language models by tuning them with millions of robotic demonstrations. While they perform well when fine-tuned for a single embodiment or task family, extending them to multi-skill settings remains challenging: directly merging VLA experts trained on different tasks results in near-zero success rates. This raises a fundamental question: what prevents VLAs from mastering multiple skills within one model? With an empirical decomposition of learnable parameters during VLA fine-tuning, we identify two key sources of non-mergeability:(1) Finetuning drives LoRA adapters in the VLM backbone toward divergent, task-specific directions beyond the capacity of existing merging methods to unify.(2) Action experts develop inter-block dependencies through self-attention feedback, causing task information to spread across layers and preventing modular recombination.To address these challenges, we present MergeVLA, a merging-oriented VLA architecture that preserves mergeability by design.MergeVLA introduces sparsely activated LoRA adapters via task masks to retain consistent parameters and reduce irreconcilable conflicts in the VLM.Its action expert replaces self-attention with cross-attention-only blocks to keep specialization localized and composable.When the task is unknown, it uses a test-time task router to adaptively select the appropriate task mask and expert head from the initial observation, enabling unsupervised task inference.Across LIBERO, LIBERO-Plus, RoboTwin, and multi-task experiments on the real SO101 robotic arm, MergeVLA achieves performance comparable to or even exceeding individually finetuned experts, demonstrating robust generalization across tasks, embodiments, and environments. Project page: https://mergevla.github.io/

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:9a7ed9eb4ed374cfb816000e0ce8b82cCVF · CVPR 2026

Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress

Zhang, Yuelin, Cheng, Sijie, Li, Chen, Li, Zongzhao, Huang, Yuxin, Liu, Yang, Huang, Wenbing

原文摘要

Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video understanding capabilities, while neglecting their complex reasoning potential. Furthermore, processing long video trajectories with VLMs is computationally prohibitive for real-world deployment. To address these challenges, we propose the Recurrent Reasoning Vision-Language Model (\text R ^2VLM). Our model features a recurrent reasoning framework that processes local video snippets iteratively, maintaining a global context through an evolving Chain of Thought (CoT). This CoT explicitly records task decomposition, key steps, and their completion status, enabling the model to reason about complex temporal dependencies. This design avoids the high cost of processing long videos while preserving essential reasoning capabilities. We train \text R ^2VLM on large-scale, automatically generated datasets from ALFRED and Ego4D. Extensive experiments on progress estimation and downstream applications, including progress-enhanced policy learning, reward modeling for reinforcement learning, and proactive assistance, demonstrate that \text R ^2VLM achieves strong performance and generalization, achieving a new state-of-the-art in long-horizon task progress estimation. The models and benchmarks are publicly available at https://huggingface.co/collections/zhangyuelin/r2vlm.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:a5c859f3d6aaefbd2bf88aa611d133b0CVF · CVPR 2026

DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs

Wei, Yanbin, Yan, Jiangyue, Kang, Chun, Chen, Yang, Liu, Hua, Kwok, James, Zhang, Yu

原文摘要

Vision-Language Models (VLMs) have emerged as versatile solutions for zero-shot question answering (QA) across various domains. However, enabling VLMs to effectively comprehend structured graphs and perform accurate, efficient QA remains challenging. Existing approaches typically rely on a single type of graph topology representation (GTR) of graphs, such as fixed-style visual images or unified text descriptions. This "one-size-fits-all" strategy often neglects model-specific and task-specific preferences, resulting in inaccurate or overly lengthy responses to graph-related queries. To address this, we propose the DynamicGTR framework, which dynamically selects the optimal GTR for each query during inference, thereby enhancing the zero-shot graph QA capabilities of VLMs with a customizable accuracy and brevity trade-off. Extensive experiments show that DynamicGTR not only improves VLM-based graph algorithm QA performance but also successfully transfers the experience trained from synthetic graph algorithm tasks to real-world applications like link prediction and node classification, without any additional training. Additionally, DynamicGTR demonstrates strong transferability across tasks, domains, and models, suggesting its potential as a flexible solution for broad graph scenarios.

cs.CV · cs.CL

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

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b14a5c6e7ea2e7c849db056496f875aaCVF · CVPR 2026

Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions

Sun, Xiaoxiao, Li, Mingyang, Yuan, Kun, Sun, Min Woo, Endo, Mark, Wu, Shengguang, Li, Changlin, Zhang, Yuhui 等 10 位作者

原文摘要

Large Vision-Language Models (VLMs) often answer classic visual illusions "correctly" on original images, yet persist with the same responses when illusion factors are inverted, even though the visual change is obvious to humans. This raises a fundamental question: do VLMs perceive visual changes or merely recall memorized patterns? While several studies have noted this phenomenon, the underlying causes remain unclear. To move from observations to systematic understanding, this paper introduces VI-Probe, a controllable visual-illusion framework with graded perturbations and matched visual controls (without illusion inducer) that disentangles visually grounded perception from language-driven recall. Unlike prior work that focuses on averaged accuracy, we measure stability and sensitivity using Polarity-Flip Consistency, Template Fixation Index, and an illusion multiplier normalized against matched controls. Experiments across different families reveal that response persistence arises from heterogeneous causes rather than a single mechanism. For instance, GPT-5 exhibits memory override, Claude-Opus-4.1 shows perception-memory competition, while Qwen variants suggest visual-processing limits. Our findings challenge single-cause views and motivate probing-based evaluation that measures both knowledge and sensitivity to controlled visual change. Data and code are available at https://sites.google.com/view/vi-probe/.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b18f486952070c46f671b73ec6b7494aCVF · CVPR 2026

Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document Retrieval

Li, Weiqing, Guo, Jinyue, Wang, Yaqi, Xiao, Haiyang, Zhang, Yuewei, Liu, Guohua, Wang, Hao Henry

原文摘要

Visual-language models (VLMs) excel at data mappings, but real-world document heterogeneity and unstructuredness disrupt the consistency of cross-modal embeddings. Recent late-interaction methods enhance image-text alignment through multi-vector representations, yet traditional training with limited samples and static strategies cannot adapt to the model's dynamic evolution, causing cross-modal retrieval confusion. To overcome this, we introduce Evo-Retriever, a retrieval framework featuring an LLM-guided curriculum evolution built upon a novel Viewpoint-Pathway collaboration. First, we employ multi-view image alignment to enhance fine-grained matching via multi-scale and multi-directional perspectives. Then, a bidirectional contrastive learning strategy generates "hard queries" and establishes complementary learning paths for visual and textual disambiguation to rebalance supervision. Finally, the model-state summary from the above collaboration is fed into an LLM meta-controller, which adaptively adjusts the training curriculum using expert knowledge to promote the model's evolution. On ViDoRe V2 and MMEB (VisDoc), Evo-Retriever achieves state-of-the-art performance, with nDCG@5 scores of 65.2 % and 77.1 %.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:d8a82ac8fc5c5a508badd002f70f8966CVF · CVPR 2026

WeaveTime: Streaming from Earlier Frames into Emergent Memory in VideoLLMs

Zhang, Yulin, Shi, Cheng, Yang, Sibei

原文摘要

Recent advances in Multimodal Large Language Models have greatly improved visual understanding and reasoning, yet their quadratic attention and offline training protocols make them ill-suited for streaming settings where frames arrive sequentially and future observations are inaccessible. We diagnose a core limitation of current Video-LLMs, namely Time-Agnosticism, in which videos are treated as an unordered bag of evidence rather than a causally ordered sequence, yielding two failures in streams: temporal order ambiguity, in which the model cannot follow or reason over the correct chronological order, and past-current focus blindness where it fails to distinguish present observations from accumulated history. We present WeaveTime, a simple, efficient, and model-agnostic framework that first teaches order and then uses order. We introduce a lightweight Temporal Reconstruction objective--our Streaming Order Perception enhancement--that instills order-aware representations with minimal finetuning and no specialized streaming data. At inference, a Past-Current Dynamic Focus Cache performs uncertainty-triggered, coarse-to-fine retrieval, expanding history only when needed. Plugged into exsiting Video-LLM without architectural changes, WeaveTime delivers consistent gains on representative streaming benchmarks, improving accuracy while reducing latency. These results establish WeaveTime as a practical path toward time-aware stream Video-LLMs under strict online, time-causal constraints. Code and weights 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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:daac897085efc3353833290cea813834CVF · CVPR 2026

Monet: Reasoning in Latent Visual Space Beyond Image and Language

Wang, Qixun, Shi, Yang, Wang, Yifei, Zhang, Yuanxing, Wan, Pengfei, Gai, Kun, Ying, Xianghua, Wang, Yisen

原文摘要

Thinking with images has emerged as an effective paradigm for advancing visual reasoning, extending beyond text-only chains of thought by injecting visual evidence into intermediate reasoning steps. However, existing methods fall short of human-like abstract visual thinking, as their flexibility is fundamentally limited by external tools. In this work, we introduce Monet, a training framework that enables multimodal large language models (MLLMs) to reason directly within the latent visual space by generating continuous embeddings that function as intermediate visual thoughts. We identify two core challenges in training MLLMs for latent visual reasoning--high computational cost in latent-vision alignment and insufficient supervision over latent embeddings, and address them with a three-stage distillation-based supervised fine-tuning (SFT) pipeline. We further reveal a limitation of applying GRPO to latent reasoning: it primarily enhances text-based reasoning rather than latent reasoning. To overcome this, we propose VLPO (Visual-latent Policy Optimization), a reinforcement learning method that explicitly incorporates latent embeddings into policy gradient updates.To support SFT, we construct Monet-SFT-125K, a high-quality text-image interleaved CoT dataset containing 125K real-world, chart, OCR, and geometry CoTs. Our model, Monet-7B, shows consistent gains across real-world perception and reasoning benchmarks and exhibits strong out-of-distribution generalization on challenging abstract visual reasoning tasks. We also empirically analyze the role of each training component and discuss our early unsuccessful attempts, providing insights for future developments in visual latent reasoning.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:dcd5de55ff95002bb6d9592c7ccb2d6fCVF · CVPR 2026

PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks

Cui, Cheng, Zhang, Yubo, Sun, Ting, Wang, Xueqing, Liu, Hongen, Lin, Manhui, Zhang, Yue, Gao, Tingquan 等 14 位作者

原文摘要

The advent of "OCR 2.0" and large-scale vision-language models (VLMs) has set new benchmarks in text recogni- tion. However, these unified architectures often come with significant computational demands, challenges in precise text localization within complex layouts, and a propen- sity for textual hallucinations. Revisiting the prevailing notion that model scale is the sole path to high accu- racy, this paper introduces PP-OCRv5, a meticulously op- timized, lightweight OCR system with merely 5 million pa- rameters. We demonstrate that PP-OCRv5 achieves per- formance competitive with many billion-parameter VLMs on standard OCR benchmarks, while offering superior lo- calization precision and reduced hallucinations. The cor- nerstone of our success lies not in architectural expansion but in a data-centric investigation. We systematically dis- sect the role of training data by quantifying three critical dimensions: data difficulty, data accuracy, and data diver- sity. Our extensive experiments reveal that with a sufficient volume of high-quality, accurately labeled, and diverse data, the performance ceiling for traditional, efficient two- stage OCR pipelines is far higher than commonly assumed. This work provides compelling evidence for the viability of lightweight, specialized models in the large-model era and offers practical insights into data curation for OCR. The source code and models are publicly available at https: //github.com/PaddlePaddle/PaddleOCR.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:e9677eaece50842fd9c5e52047611ef5CVF · CVPR 2026

Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling

Yu, Xinlei, Xu, Chengming, Chen, Zhangquan, Zhang, Yudong, Lu, Shilin, Yang, Cheng, Zhang, Jiangning, Yan, Shuicheng 等 9 位作者

原文摘要

The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles with the inherent need of this domain for document-based procedural reasoning, cognitive complexity, and factual accuracy. To this end, we introduce MACT, a Multi-Agent Collaboration framework with agent-wise adaptive Test-time scaling that pioneers a paradigm shift to procedural scaling, adapting dynamically to the functional entities of visual documents understanding and reasoning. MACT decomposes the visual document processing flow into four specialized agents, i.e., planning, execution, judgment, and answer, to resolve cognitive overload and introduce a critical self-correction loop for factual grounding. This collaborative architecture is amplified by an agent-wise adaptive test-time scaling strategy that intelligently allocates computational resources based on the complexity and redundancy of each functionality. Evaluated on multiple visual document understanding benchmarks, MACT achieves superior performance with a smaller parameter scale, adapting effectively to various document scenarios without compromising its general or mathematical reasoning capabilities. The three variants consistently attain top-three average performance rankings, with average performance enhancements of 9.9-11.5% over the base models.

cs.CV · cs.CL · cs.MA

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:eca05a35c486243da581fefbdb4011c4CVF · CVPR 2026

Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness

Hu, Xin, Ni, Haomiao, Zhang, Yunbei, Hamm, Jihun, Li, Zechen, Ding, Zhengming

原文摘要

Vision language models (VLMs) have achieved remarkable success in broad visual understanding, yet they remain challenged by object-centric reasoning on rare objects due to the scarcity of such instances in pretraining data. While prior efforts alleviate this issue by retrieving additional data or introducing stronger vision encoders, these methods are still computationally intensive during finetuning VLMs and don't fully exploit the original training data. In this paper, we introduce an efficient plug-and-play module that substantially improves VLMs' reasoning over rare objects by refining visual tokens and enriching input text prompts, without VLMs finetuning. Specifically, we propose to learn multi-modal class embeddings for rare objects by leveraging prior knowledge from vision foundation models and synonym-augmented text descriptions, compensating for limited training examples. These embeddings refine the visual tokens in VLMs through a lightweight attention-based enhancement module that improves fine-grained object details. In addition, we use the learned embeddings as object-aware detectors to generate informative hints, which are injected into the text prompts to help guide the VLM's attention toward relevant image regions. Experiments on two benchmarks show consistent and substantial gains for pretrained VLMs in rare object recognition and reasoning. Further analysis reveals how our method strengthens the VLM's ability to focus on and reason about rare objects. Code is available at https://github.com/XinHu98/seeing

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:ed47db53f9b2dd449d92c8092d631c31CVF · CVPR 2026

Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation

Zhang, Lingfeng, Zhang, Yuchen, Li, Hongsheng, Fu, Haoxiang, Tang, Yingbo, Ye, Hangjun, Chen, Long, Liang, Xiaojun 等 10 位作者

原文摘要

Vision-Language Models (VLMs), leveraging their powerful visual perception and reasoning capabilities, have been widely applied in Unmanned Aerial Vehicle (UAV) tasks.However, the spatial intelligence capabilities of existing VLMs in UAV scenarios remain largely unexplored, raising concerns about their effectiveness in navigating and interpreting dynamic environments.To bridge this gap, we introduce SpatialSky-Bench, a comprehensive benchmark specifically designed to evaluate the spatial intelligence capabilities of VLMs in UAV navigation. Our benchmark comprises two categories--Environmental Perception and Scene Understanding--divided into 13 subcategories, including bounding boxes, color, distance, height, and landing safety analysis, among others.Extensive evaluations of various mainstream open-source and closed-source VLMs reveal unsatisfactory performance in complex UAV navigation scenarios, highlighting significant gaps in their spatial capabilities.To address this challenge, we developed the SpatialSky-Dataset, a comprehensive dataset containing 1 M samples with diverse annotations across various scenarios. Leveraging this dataset, we introduce Sky-VLM, a specialized VLM designed for UAV spatial reasoning across multiple granularities and contexts.Extensive experimental results demonstrate that Sky-VLM achieves state-of-the-art performance across all benchmark tasks, paving the way for the development of VLMs suitable for drone scenarios.The source code is available at https://github.com/linglingxiansen/SpatialSKy .

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f036c6ca82d59c93ec0eb9ef8183c3b6CVF · CVPR 2026

Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

Cui, Cheng, Sun, Ting, Liang, Suyin, Gao, Tingquan, Zhang, Zelun, Liu, Jiaxuan, Wang, Xueqing, Zhou, Changda 等 18 位作者

原文摘要

Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to a quadratic increase in the number of vision tokens and significantly raises computational costs. We attribute this inefficiency to substantial visual regions redundancy in document images, like background. To tackle this, we propose PaddleOCR-VL, a novel coarse-to-fine architecture that focuses on semantically relevant regions while suppressing redundant ones, thereby improving both efficiency and performance. Specifically, we introduce a lightweight Valid Region Focus Module (VRFM) which leverages localization and contextual relationship prediction capabilities to identify valid vision tokens. Subsequently, we design and train a compact yet powerful 0.9B vision-language model (PaddleOCR-VL-0.9B) to perform detailed recognition, guided by VRFM outputs to avoid direct processing of the entire large image. Extensive experiments demonstrate that PaddleOCR-VL achieves state-of-the-art performance in both page-level parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference while utilizing substantially fewer vision tokens and parameters, highlighting the effectiveness of targeted coarse-to-fine parsing for accurate and efficient document understanding. The source code and models are publicly available at https://github.com/PaddlePaddle/PaddleOCR.

cs.CV · cs.CL

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

首次观测 · 记录 #1CVF · CVPR 2026:cvf:fcf28201ff00a815dfc1ef96be524ad2CVF · CVPR 2026

OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios

Gao, Hong, Wu, Jingyu, Xu, Xiangkai, Xie, Kangni, Zhang, Yunchen, Zhong, Bin, Gao, Xurui, Zhang, Min-Ling

原文摘要

Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. While Multimodal Large Language Models have shown promise, a significant gap remains between current models and real-world demands involving diverse objects and complex queries. We attribute this to limited benchmark scope, causing models to exhibit category bias, oversimplified reasoning, and poor linguistic robustness.To address these limitations, we introduce OmniGround, a comprehensive benchmark with 3,475 videos spanning 81 categories and complex real-world queries. We propose the Forward-Backward-Refinement (FBR) annotation pipeline for high-quality labels and DeepSTG, a systematic evaluation framework quantifying dataset quality beyond superficial statistics. Evaluations reveal performance average drops of 10.4% on complex real-world scenes, particularly with small/occluded objects and intricate spatial relations. Motivated by these, we propose PG-TAF, a training-free two-stage framework decomposing STVG into high-level temporal grounding and fine-grained spatio-temporal propagation. Experiments demonstrate PG-TAF achieves 25.6% and 35.6% improvements in m_tIoU and m_vIoU on OmniGround with consistent gains across four benchmarks.

cs.CV · cs.CL

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