视觉大模型 / VLM - arXivDaily 专题

2511.03332 2025-11-06 cs.CV 83%

Multi-Object Tracking Retrieval with LLaVA-Video: A Training-Free Solution to MOT25-StAG Challenge

Yi Yang, Yiming Xu, Timo Kaiser, Hao Cheng, Bodo Rosenhahn, Michael Ying Yang

机构 * Leibniz University Hannover（莱布尼茨汉诺威大学）； University of Twente（特文特大学）； University of Bath（巴斯大学）

专题命中 VLM训练与架构：LLaVA(title,abstract)；grounding(abstract)；分类 cs.CV

2510.16888 2025-11-05 cs.CV 83%

Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback

Zongjian Li, Zheyuan Liu, Qihui Zhang, Bin Lin, Feize Wu, Shenghai Yuan, Zhiyuan Yan, Yang Ye, Wangbo Yu, Yuwei Niu, Shaodong Wang, Xinhua Cheng, Li Yuan

专题命中 VLM训练与架构：MLLM(title,abstract)；multimodal large language model(abstract)；分类 cs.CV

2505.21375 2025-11-05 cs.CV 83%

GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution

Fengxiang Wang, Mingshuo Chen, Yueying Li, Di Wang, Haotian Wang, Zonghao Guo, Zefan Wang, Boqi Shan, Long Lan, Yulin Wang, Hongzhen Wang, Wenjing Yang, Bo Du, Jing Zhang

机构 * College of Computer Science and Technology, National University of Defense Technology, China（中国国防科技大学计算机科学与技术学院）； Beijing University of Posts and Telecommunications, China（北京邮电大学）； School of Computer Science, Wuhan University, China（武汉大学计算机学院）； Zhongguancun Academy, China（中关村学院）； Tsinghua University, China（清华大学）； Beihang University, China（北航大学）

专题命中 VLM训练与架构：multimodal large language model(title,abstract)；LLaVA(abstract)；分类 cs.CV

Comments NeurlPS 2025 Spotlight

2501.04001 2025-11-04 cs.CV 83%

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Haobo Yuan, Xiangtai Li, Tao Zhang, Yueyi Sun, Zilong Huang, Shilin Xu, Shunping Ji, Yunhai Tong, Lu Qi, Jiashi Feng, Ming-Hsuan Yang

机构 * University of California, Merced（加州大学默塞德分校）； Bytedance Seed（字节跳动种子）； Wuhan University（武汉大学）； Peking University（北京大学）

专题命中 VLM训练与架构：LLaVA(title)；vision-language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments Code: https://github.com/Bytedance/Sa2VA

2510.21757 2025-10-28 cs.CV 83%

Agro-Consensus: Semantic Self-Consistency in Vision-Language Models for Crop Disease Management in Developing Countries

Mihir Gupta, Pratik Desai, Ross Greer

机构 * The Harker School（哈克尔学校）； University of California, Merced（加州大学默塞德分校）

专题命中 VLM训练与架构：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV

2505.23566 2025-10-28 cs.CV 83%

Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition

Yu Li, Jin Jiang, Jianhua Zhu, Shuai Peng, Baole Wei, Yuxuan Zhou, Liangcai Gao

机构 * Wangxuan Institute of Computer Technology, Peking University（计算机技术研究院，北京大学）

专题命中 VLM训练与架构：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2025 as a spotlight

2510.14349 2025-10-24 cs.CV 83%

Vision-Centric Activation and Coordination for Multimodal Large Language Models

Yunnan Wang, Fan Lu, Kecheng Zheng, Ziyuan Huang, Ziqiang Li, Wenjun Zeng, Xin Jin

机构 * MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University（人工智能MoE实验室，上海交通大学）； Ant Group（蚂蚁集团）； Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo（宁波数字孪生研究所，东部技术研究所，宁波）

专题命中 VLM训练与架构：multimodal large language model(title,abstract)；MLLM(abstract)；分类 cs.CV

2509.15235 2025-10-24 cs.CV cs.CL 83%

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding

Jialiang Kang, Han Shu, Wenshuo Li, Yingjie Zhai, Xinghao Chen

机构 * Peking University（北京大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）

专题命中 VLM训练与架构：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV

Comments NeurIPS 2025

2510.19160 2025-10-23 cs.LG 83%

Preliminary Use of Vision Language Model Driven Extraction of Mouse Behavior Towards Understanding Fear Expression

Paimon Goulart, Jordan Steinhauser, Kylene Shuler, Edward Korzus, Jia Chen, Evangelos E. Papalexakis

机构 * University of California, Riverside（加州大学河滨分校）

专题命中 VLM训练与架构：vision language model(title)；vision-language model(abstract)；VLM(abstract)；分类 cs.LG

2412.01822 2025-10-23 cs.CV 83%

VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models

Byung-Kwan Lee, Ryo Hachiuma, Yu-Chiang Frank Wang, Yong Man Ro, Yueh-Hua Wu

机构 * NVIDIA ； KAIST（韩国科学技术院）； National Taiwan University（国立台湾大学）

专题命中 VLM训练与架构：vision language model(title)；vision-language model(abstract)；VLM(abstract)；分类 cs.CV

Comments CVPR 2025, Project page: https://byungkwanlee.github.io/VLsI-page/

2411.12783 2025-10-22 cs.CV 83%

Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model

Yiming Shi, Xun Zhu, Kaiwen Wang, Ying Hu, Chenyi Guo, Miao Li, Ji Wu

机构 * Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）； College of AI, Tsinghua University（清华大学人工智能学院）； Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）

专题命中 VLM训练与架构：multimodal large language model(title,abstract)；MLLM(abstract)；分类 cs.CV

2510.17777 2025-10-21 cs.CV 83%

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

Samir Khaki, Junxian Guo, Jiaming Tang, Shang Yang, Yukang Chen, Konstantinos N. Plataniotis, Yao Lu, Song Han, Zhijian Liu

机构 * NVIDIA ； MIT（麻省理工学院）； UC San Diego（南加州大学圣地亚哥分校）； University of Toronto（多伦多大学）

专题命中 VLM训练与架构：VLM(title,abstract)；vision language model(abstract)；分类 cs.CV

2510.16870 2025-10-21 cs.CV 83%

Uncovering Brain-Like Hierarchical Patterns in Vision-Language Models through fMRI-Based Neural Encoding

Yudan Ren, Xinlong Wang, Kexin Wang, Tian Xia, Zihan Ma, Zhaowei Li, Xiangrong Bi, Xiao Li, Xiaowei He

专题命中 VLM训练与架构：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV

Comments 14 pages, 7 figures

2502.10090 2025-10-21 cs.RO cs.AI 83%

Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models

Chenrui Tie, Shengxiang Sun, Jinxuan Zhu, Yiwei Liu, Jingxiang Guo, Yue Hu, Haonan Chen, Junting Chen, Ruihai Wu, Lin Shao

机构 * National University of Singapore（新加坡国立大学）； University of Toronto（多伦多大学）； Peking University（北京大学）； Sichuan University（四川大学）； Zhejiang University（浙江大学）

专题命中 VLM训练与架构：vision-language model(title,abstract)；VLM(abstract)；分类 cs.AI

Journal ref Robotics: Science and Systems 2025

2510.09607 2025-10-20 cs.CV 83%

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation

Shaoqi Dong, Chaoyou Fu, Haihan Gao, Yi-Fan Zhang, Chi Yan, Chu Wu, Xiaoyu Liu, Yunhang Shen, Jing Huo, Deqiang Jiang, Haoyu Cao, Yang Gao, Xing Sun, Ran He, Caifeng Shan

机构 * Nanjing University（南京大学）； Tencent Youtu Lab（腾讯优图实验室）； CASIA（中国科学院自动化研究所）

专题命中 VLM训练与架构：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV

Comments Homepage: https://ltbai.github.io/VITA-VLA/

2510.12287 2025-10-15 cs.CV cs.CL 83%

Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector

Sifan Li, Hongkai Chen, Yujun Cai, Qingwen Ye, Liyang Chen, Junsong Yuan, Yiwei Wang

机构 * University of California, Merced（加州大学梅尔德分校）； vivo Mobile Communication Co., Ltd.（vivo移动通信有限公司）； University of Queensland（昆士兰大学）； UCLA（加州大学洛杉矶分校）； University at Buffalo（布法罗大学）

专题命中 VLM训练与架构：vision language model(title,abstract)；LLaVA(abstract)；分类 cs.CV

2506.07961 2025-10-15 cs.RO cs.AI 83%

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

Peiyan Li, Yixiang Chen, Hongtao Wu, Xiao Ma, Xiangnan Wu, Yan Huang, Liang Wang, Tao Kong, Tieniu Tan

机构 * CASIA（中国科学院自动化研究所）； ByteDance Seed（字节跳动种子实验室）； UCAS（中国科学院大学）； FiveAges ； NJU（南京大学）

专题命中 VLM训练与架构：vision-language model(title,abstract)；VLM(abstract)；分类 cs.AI

Comments NeurIPS 2025

2510.11456 2025-10-14 cs.CV 83%

Coupled Degradation Modeling and Fusion: A VLM-Guided Degradation-Coupled Network for Degradation-Aware Infrared and Visible Image Fusion

Tianpei Zhang, Jufeng Zhao, Yiming Zhu, Guangmang Cui

专题命中 VLM训练与架构：VLM(title,abstract)；vision-language model(abstract)；分类 cs.CV

2510.08565 2025-10-10 cs.CV 83%

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

Changyao Tian, Hao Li, Gen Luo, Xizhou Zhu, Weijie Su, Hanming Deng, Jinguo Zhu, Jie Shao, Ziran Zhu, Yunpeng Liu, Lewei Lu, Wenhai Wang, Hongsheng Li, Jifeng Dai

机构 * Shanghai AI Laboratory（上海人工智能实验室）； The Chinese University of Hong Kong（香港中文大学）； Tsinghua University（清华大学）； Sensetime Research（商汤科技研究院）； Nanjing University（南京大学）

专题命中 VLM训练与架构：multimodal large language model(title,abstract)；MLLM(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2025. 22 pages, link: https://github.com/OpenGVLab/NaViL

2503.16965 2025-10-07 cs.CL cs.CV 83%

Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning

Zhe Hu, Jing Li, Zhongzhu Pu, Hou Pong Chan, Yu Yin

机构 * The Hong Kong Polytechnic University（香港理工大学）； Tsinghua University（清华大学）； InspireOmni AI ； Alibaba Group（阿里巴巴集团）； Case Western Reserve University（凯斯西储大学）

专题命中 VLM训练与架构：VLM(title,abstract)；vision language model(abstract)；分类 cs.CV

Comments Accepted at NeurIPS 2025

2510.03978 2025-10-07 cs.CV cs.CL 83%

No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language Models

Min Woo Sun, Alejandro Lozano, Javier Gamazo Tejero, Vishwesh Nath, Xiao Xiao Sun, James Burgess, Yuhui Zhang, Kun Yuan, Robert Tibshirani, Sean Huver, Serena Yeung-Levy

机构 * Stanford University（斯坦福大学）； NVIDIA USA（NVIDIA公司）

专题命中 VLM训练与架构：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV

2509.25413 2025-10-02 cs.CV 83%

DepthLM: Metric Depth From Vision Language Models

Zhipeng Cai, Ching-Feng Yeh, Hu Xu, Zhuang Liu, Gregory Meyer, Xinjie Lei, Changsheng Zhao, Shang-Wen Li, Vikas Chandra, Yangyang Shi

机构 * Meta ； Princeton University（普林斯顿大学）

专题命中 VLM训练与架构：vision language model(title,abstract)；VLM(abstract)；分类 cs.CV

2503.17349 2025-10-02 cs.CV 83%

Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models

Jianing Qi, Jiawei Liu, Hao Tang, Zhigang Zhu

机构 * CUNY Graduate Center（纽约大学研究生中心）； Borough of Manhattan Community College（曼哈顿社区学院）； The City College of New York（纽约城市学院）

专题命中 VLM训练与架构：vision-language model(title)；vision language model(abstract)；LLaVA(abstract)；分类 cs.CV

2509.23828 2025-09-30 cs.CV 83%

Uni4D-LLM: A Unified SpatioTemporal-Aware VLM for 4D Understanding and Generation

Hanyu Zhou, Gim Hee Lee

机构 * School of Computing, National University of Singapore（计算学院，新加坡国立大学）

专题命中 VLM训练与架构：VLM(title,abstract)；vision-language model(abstract)；分类 cs.CV

2502.11360 2025-09-29 cs.CV cs.CL 83%

GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder

Seunghyuk Cho, Zhenyue Qin, Yang Liu, Youngbin Choi, Seungbeom Lee, Dongwoo Kim

机构 * Graduate School of Artificial Intelligence, POSTECH（POSTECH人工智能研究生院）； Department of Computer Science and Engineering, POSTECH（POSTECH计算机科学与工程系）； Australian National University（澳大利亚国立大学）

专题命中 VLM训练与架构：VLM(title,abstract)；vision-language model(abstract)；分类 cs.CV

Comments Accepted to EMNLP-Findings 2025

2509.18839 2025-09-24 cs.CV 83%

Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconography

Gianmarco Spinaci, Lukas Klic, Giovanni Colavizza

机构 * Gianmarco Spinaci Department of Classical Philology and Italian Studies, University of Bologna, Italy Villa i Tatti, The Harvard University Center for Italian Renaissance Studies, Florence, Italy（Gianmarco Spinaci 文艺复兴研究系，博洛尼亚大学，意大利塔蒂别墅，哈佛大学意大利文艺复兴研究中心，佛罗伦萨，意大利）； Lukas Klic Villa i Tatti, The Harvard University Center for Italian Renaissance Studies, Florence, Italy（Lukas Klic 塔蒂别墅，哈佛大学意大利文艺复兴研究中心，佛罗伦萨，意大利）； Giovanni Colavizza Department of Classical Philology and Italian Studies, University of Bologna, Italy Department of Communication, University of Copenhagen, Denmark（Giovanni Colavizza 文艺复兴研究系，博洛尼亚大学，意大利传播系，哥本哈根大学，丹麦）

专题命中 VLM训练与架构：multimodal large language model(title,abstract)；vision language model(abstract)；分类 cs.CV

Comments 11 pages, 2 figures

2509.17418 2025-09-23 cs.CL cs.CV 83%

Vision Language Models Are Not (Yet) Spelling Correctors

Junhong Liang, Bojun Zhang

机构 * MBZUAI ； Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院）

专题命中 VLM训练与架构：vision language model(title,abstract)；InternVL(abstract)；分类 cs.CV

2504.04653 2025-09-23 cs.CV cs.CL 83%

LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts

Yimu Wang, Mozhgan Nasr Azadani, Sean Sedwards, Krzysztof Czarnecki

机构 * University of Waterloo（滑铁卢大学）

专题命中 VLM训练与架构：multimodal large language model(title)；visual reasoning(abstract)；MLLM(abstract)；分类 cs.CV

Comments To appear at EMNLP 2025

2509.08266 2025-09-11 cs.CV 83%

Examining Vision Language Models through Multi-dimensional Experiments with Vision and Text Features

Saurav Sengupta, Nazanin Moradinasab, Jiebei Liu, Donald E. Brown

机构 * School of Data Science, University of Virginia（数据科学学院，弗吉尼亚大学）

专题命中 VLM训练与架构：vision language model(title,abstract)；VLM(abstract)；分类 cs.CV

2506.18407 2025-09-10 cs.GR cs.CV 83%

IntuiTF: MLLM-Guided Transfer Function Optimization for Direct Volume Rendering

Yiyao Wang, Bo Pan, Ke Wang, Han Liu, Jinyuan Mao, Yuxin Liu, Minfeng Zhu, Xiuqi Huang, Weifeng Chen, Bo Zhang, Wei Chen

机构 * State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD与CG国家重点实验室）； Laboratory of Art and Archaeology Image (Zhejiang University), Ministry of Education, China（浙江大学艺术与考古图像实验室（教育部，中国））； Zhejiang University of Finance&Economics（浙江财经大学）； Zhejiang University（浙江大学）

专题命中 VLM训练与架构：MLLM(title,abstract)；multimodal large language model(abstract)；分类 cs.CV

1. VLM训练与架构 5030 篇

Multi-Object Tracking Retrieval with LLaVA-Video: A Training-Free Solution to MOT25-StAG Challenge

Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback

GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Agro-Consensus: Semantic Self-Consistency in Vision-Language Models for Crop Disease Management in Developing Countries

Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition

Vision-Centric Activation and Coordination for Multimodal Large Language Models

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding

Preliminary Use of Vision Language Model Driven Extraction of Mouse Behavior Towards Understanding Fear Expression

VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models

Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

Uncovering Brain-Like Hierarchical Patterns in Vision-Language Models through fMRI-Based Neural Encoding

Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation

Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

Coupled Degradation Modeling and Fusion: A VLM-Guided Degradation-Coupled Network for Degradation-Aware Infrared and Visible Image Fusion

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning

No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language Models

DepthLM: Metric Depth From Vision Language Models

Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models

Uni4D-LLM: A Unified SpatioTemporal-Aware VLM for 4D Understanding and Generation

GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder

Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconography

Vision Language Models Are Not (Yet) Spelling Correctors

LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts

Examining Vision Language Models through Multi-dimensional Experiments with Vision and Text Features

IntuiTF: MLLM-Guided Transfer Function Optimization for Direct Volume Rendering