视觉大模型 / VLM - arXivDaily 专题

2504.00502 2025-11-04 cs.CV cs.CL 85%

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

Qianhao Yuan, Qingyu Zhang, Yanjiang Liu, Jiawei Chen, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun

机构 * Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）； University of Chinese Academy of Sciences（中国科学院大学）

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

Comments Published as a conference paper at ICCV 2025. Project page: https://github.com/icip-cas/ShortV

2511.00821 2025-11-04 cs.CV 85%

OMEGA: Optimized Multimodal Position Encoding Index Derivation with Global Adaptive Scaling for Vision-Language Models

Ruoxiang Huang, Xindian Ma, Rundong Kong, Zhen Yuan, Peng Zhang

机构 * Tianjin University（天津大学）

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

2506.07416 2025-11-04 cs.LG cs.AI 84%

LiteVLM: A Low-Latency Vision-Language Model Inference Pipeline for Resource-Constrained Environments

Jin Huang, Yuchao Jin, Le An, Josh Park

机构 * NVIDIA（英伟达）

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

2511.00120 2025-11-04 cs.CV cs.AI 76%

VLM6D: VLM based 6Dof Pose Estimation based on RGB-D Images

Md Selim Sarowar, Sungho Kim

专题命中 VLM训练与架构：VLM(title)；分类 cs.CV、cs.AI

Comments This paper has been accepted to IEIE( The Institute Of Electronics and Information Engineering, South Korea) Fall,2025 Conference

2504.21344 2025-11-04 cs.CV cs.AI q-bio.QM 76%

Vision-Language Model-Based Semantic-Guided Imaging Biomarker for Lung Nodule Malignancy Prediction

Luoting Zhuang, Seyed Mohammad Hossein Tabatabaei, Ramin Salehi-Rad, Linh M. Tran, Denise R. Aberle, Ashley E. Prosper, William Hsu

机构 * organization= Medical \& Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA , city= Los Angeles , postcode= 90095 , state= CA , country= USA ； organization= Department of Medicine, Division of Pulmonology ； Critical Care, David Geffen School of Medicine at UCLA , city= Los Angeles , postcode= 90095 , state= CA , country= USA

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

Journal ref Journal of Biomedical Informatics 172 (2025) 104947

2511.01082 2025-11-04 cs.CV cs.AI cs.LG 75%

GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction

Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr, Cyrus Shahabi

机构 * of Computer Science, University of Southern California, Los Angeles, CA, USA ； Computer Engineering, University of Southern California, Los Angeles, CA, USA

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

Comments Accepted to IEEE International Conference on Data Mining (ICDM) 2025

2504.03724 2025-11-04 cs.CV cs.CL 74%

CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward

Zhiqiang Wang, Pengbin Feng, Yanbin Lin, Shuzhang Cai, Zongao Bian, Jinghua Yan, Xingquan Zhu

机构 * Florida Atlantic University（佛罗里达大学）； University of Southern California（南加州大学）； University of Texas at Dallas（德克萨斯大学达拉斯分校）； Georgia Institute of Technology（佐治亚理工学院）； University of Utah（犹他大学）

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

Comments 10 pages, 6 figures and 4 tables

Journal ref 2025 IEEE International Conference on Big Data (IEEE BigData 2025)

2511.01791 2025-11-04 cs.RO cs.AI 70%

GenDexHand: Generative Simulation for Dexterous Hands

Feng Chen, Zhuxiu Xu, Tianzhe Chu, Xunzhe Zhou, Li Sun, Zewen Wu, Shenghua Gao, Zhongyu Li, Yanchao Yang, Yi Ma

机构 * The University of Hong Kong（香港大学）； Transcengram ； Shanghai Jiao Tong University（上海交通大学）； The Chinese University of Hong Kong（香港中文大学）

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

2511.00076 2025-11-04 cs.LG 70%

Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with Bézier Curves

Zihao Wan, Pau Tong Lin Xu, Fuwen Luo, Ziyue Wang, Peng Li, Yang Liu

机构 * Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China（计算机科学与技术系，人工智能研究院，清华大学，北京，中国）； Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China（人工智能产业研究院（AIR），清华大学，北京，中国）

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

2511.00041 2025-11-04 cs.RO cs.AI 70%

Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World

Yingzhao Jian, Zhongan Wang, Yi Yang, Hehe Fan

机构 * College of Computer Science and Technology（计算机科学与技术学院）； Zhejiang University（浙江大学）

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

2511.01463 2025-11-04 cs.CV cs.AI cs.GR 62%

HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA

Lei Hu, Yongjing Ye, Shihong Xia

机构 * Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）； University of Chinese Academy of Sciences（中国科学院大学）

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

Comments 10 pages, 5figures. The Thirty-Ninth Annual Conference on Neural Information Processing Systems

2511.00419 2025-11-04 cs.CV cs.AI 62%

LGCA: Enhancing Semantic Representation via Progressive Expansion

Thanh Hieu Cao, Trung Khang Tran, Gia Thinh Pham, Tuong Nghiem Diep, Thanh Binh Nguyen

机构 * University of Science, Vietnam National University Ho Chi Minh City, Vietnam（越南胡志明市国家大学科学大学）； National University of Singapore, Singapore（新加坡国立大学）； AISIA Lab, Ho Chi Minh City, Vietnam（越南胡志明市AISIA实验室）

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

Comments 15 pages, 5 figures, to appear in SoICT 2025

2511.01645 2025-11-04 cs.CV 57%

Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward

Xiaogang Xu, Ruihang Chu, Jian Wang, Kun Zhou, Wenjie Shu, Harry Yang, Ser-Nam Lim, Hao Chen, Liang Lin

机构 * The Chinese University of Hong Kong（香港中文大学）； Tsinghua University（清华大学）； Snap Research ； Shenzhen University（深圳大学）； HKUST（香港科技大学）； University of Central Florida（佛罗里达大学）； UC Davis（加州大学戴维斯分校）； Sun Yat-Sen University（孙中山大学）

专题命中 VLM训练与架构：MLLM(abstract)；分类 cs.CV

2511.01550 2025-11-04 cs.AI 57%

Analyzing Sustainability Messaging in Large-Scale Corporate Social Media

Ujjwal Sharma, Stevan Rudinac, Ana Mićković, Willemijn van Dolen, Marcel Worring

机构 * University of Amsterdam（阿姆斯特丹大学）

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

2508.06350 2025-11-04 cs.CV 57%

Aligning Effective Tokens with Video Anomaly in Large Language Models

Yingxian Chen, Jiahui Liu, Ruidi Fan, Yanwei Li, Chirui Chang, Shizhen Zhao, Wilton W. T. Fok, Xiaojuan Qi, Yik-Chung Wu

机构 * The University of Hong Kong（香港大学）； The Chinese University of Hong Kong（香港中文大学）