多模态大模型 - arXivDaily 专题

2506.05061 2025-06-06 cs.CV 57%

A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions

Anh Le, Thanh Lam, Dung Nguyen

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

2506.04501 2025-06-06 cs.CV 57%

AuthGuard: Generalizable Deepfake Detection via Language Guidance

Guangyu Shen, Zhihua Li, Xiang Xu, Tianchen Zhao, Zheng Zhang, Dongsheng An, Zhuowen Tu, Yifan Xing, Qin Zhang

机构 * Purdue University（普渡大学）； AWS AI Labs（AWS人工智能实验室）

专题命中图文多模态：image-text(abstract)；分类 cs.CV

2506.03569 2025-06-05 cs.CL 57%

MiMo-VL Technical Report

Core Team, Zihao Yue, Zhenru Lin, Yifan Song, Weikun Wang, Shuhuai Ren, Shuhao Gu, Shicheng Li, Peidian Li, Liang Zhao, Lei Li, Kainan Bao, Hao Tian, Hailin Zhang, Gang Wang, Dawei Zhu, Cici, Chenhong He, Bowen Ye, Bowen Shen, Zihan Zhang, Zihan Jiang, Zhixian Zheng, Zhichao Song, Zhenbo Luo, Yue Yu, Yudong Wang, Yuanyuan Tian, Yu Tu, Yihan Yan, Yi Huang, Xu Wang, Xinzhe Xu, Xingchen Song, Xing Zhang, Xing Yong, Xin Zhang, Xiangwei Deng, Wenyu Yang, Wenhan Ma, Weiwei Lv, Weiji Zhuang, Wei Liu, Sirui Deng, Shuo Liu, Shimao Chen, Shihua Yu, Shaohui Liu, Shande Wang, Rui Ma, Qiantong Wang, Peng Wang, Nuo Chen, Menghang Zhu, Kangyang Zhou, Kang Zhou, Kai Fang, Jun Shi, Jinhao Dong, Jiebao Xiao, Jiaming Xu, Huaqiu Liu, Hongshen Xu, Heng Qu, Haochen Zhao, Hanglong Lv, Guoan Wang, Duo Zhang, Dong Zhang, Di Zhang, Chong Ma, Chang Liu, Can Cai, Bingquan Xia

机构 * LLM-Core ； Xiaomi（小米）

专题命中图文多模态：multimodal(abstract)；分类 cs.CL

Comments 32 pages

2411.11479 2025-06-04 cs.CL 57%

Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts

Jingxuan Li, Yuning Yang, Shengqi Yang, Linfan Zhang, Ying Nian Wu

机构 * University of California, Los Angeles（加州大学洛杉矶分校）； Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

专题命中图文多模态：multimodal(abstract)；分类 cs.CL

Comments ACL 2025 main

2506.01366 2025-06-03 cs.CV 57%

CLIP-driven rain perception: Adaptive deraining with pattern-aware network routing and mask-guided cross-attention

Cong Guan, Osamu Yoshie

机构 * Graduate School of Information, Production and Systems, Waseda University（信息、生产与系统研究生院，早稻田大学）

专题命中图文多模态：cross-modal(abstract)；分类 cs.CV

2505.18022 2025-06-03 cs.CV 57%

RemoteSAM: Towards Segment Anything for Earth Observation

Liang Yao, Fan Liu, Delong Chen, Chuanyi Zhang, Yijun Wang, Ziyun Chen, Wei Xu, Shimin Di, Yuhui Zheng

机构 * Hohai University（河海大学）； HKUST（香港科技大学）； Southeast University（东南大学）

专题命中图文多模态：image-text(abstract)；分类 cs.CV

2504.07934 2025-06-02 cs.CV 57%

SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Xiyao Wang, Zhengyuan Yang, Chao Feng, Hongjin Lu, Linjie Li, Chung-Ching Lin, Kevin Lin, Furong Huang, Lijuan Wang

机构 * University of Maryland College Park（马里兰大学学院公园分校）； Microsoft（微软）； University of Michigan（密歇根大学）

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

Comments 27 pages, 5 figures

2505.23766 2025-05-30 cs.CV 57%

Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought

Yunze Man, De-An Huang, Guilin Liu, Shiwei Sheng, Shilong Liu, Liang-Yan Gui, Jan Kautz, Yu-Xiong Wang, Zhiding Yu

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； NVIDIA

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

Comments CVPR 2025. Project Page: https://yunzeman.github.io/argus/

2505.23040 2025-05-30 cs.CV 57%

Deep Modeling and Optimization of Medical Image Classification

Yihang Wu, Muhammad Owais, Reem Kateb, Ahmad Chaddad

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

Comments Accepted in ISBI2025

2505.18686 2025-05-30 cs.CV 57%

WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation

Yang Liu, Silin Cheng, Xinwei He, Sebastien Ourselin, Lei Tan, Gen Luo

专题命中图文多模态：image-text(abstract)；分类 cs.CV

Comments Accepted by CVPR2025

2503.24129 2025-05-30 cs.CV cs.LG 57%

It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data

Dominik Schnaus, Nikita Araslanov, Daniel Cremers

机构 * TU Munich（慕尼黑技术大学）； Munich Center for Machine Learning（慕尼黑机器学习中心）

专题命中图文多模态：image-text(abstract)；分类 cs.CV

Comments Accepted to CVPR 2025, Project page: https://dominik-schnaus.github.io/itsamatch/

2505.22209 2025-05-29 cs.CV 57%

A Survey on Training-free Open-Vocabulary Semantic Segmentation

Naomi Kombol, Ivan Martinović, Siniša Šegvić

机构 * Sveučilište u Zagrebu（扎格雷布大学）

专题命中图文多模态：multi-modal(abstract)；分类 cs.CV

2505.22079 2025-05-29 cs.CV 57%

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis

Hanbin Ko, Chang-Min Park

机构 * Interdisciplinary Program in Bioengineering, Seoul National University Graduate School（生物工程跨学科项目，首尔国立大学研究生院）； Integrated Major in Innovative Medical Science, Seoul National University Graduate School（创新医学联合专业，首尔国立大学研究生院）； Department of Radiology, Seoul National University Hospital（放射科，首尔国立大学医院）

专题命中图文多模态：image-text(abstract)；分类 cs.CV

Comments 16 pages (8 main, 2 references, 6 appendix), 13 figures. Accepted to CVPR 2025. This author-accepted manuscript includes an expanded ethics/data user agreement section. The final version will appear in the Proceedings of CVPR 2025

2505.21967 2025-05-29 cs.CL 57%

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack

Juan Ren, Mark Dras, Usman Naseem

机构 * School of Computing, Macquarie University（计算机学院，麦考瑞大学）

专题命中图文多模态：multimodal(abstract)；分类 cs.CL

Comments Preprint

2505.20362 2025-05-28 cs.IR cs.AI 57%

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration

Jiahui Geng, Qing Li, Zongxiong Chen, Yuxia Wang, Derui Zhu, Zhuohan Xie, Chenyang Lyu, Xiuying Chen, Preslav Nakov, Fakhri Karray

机构 * Mohamed bin Zayed University of Artificial Intelligence（莫扎德·本·扎耶德人工智能大学）； Fraunhofer Institute for Open Communication Systems（弗劳恩霍夫开放通信系统研究所）； Technical University of Munich（慕尼黑技术大学）； Alibaba International Digital Commerce（阿里巴巴国际数字商务）

专题命中图文多模态：image-text(abstract)；分类 cs.AI

2502.12635 2025-05-28 cs.CV 57%

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning

Yunhao Gou, Hansi Yang, Zhili Liu, Kai Chen, Yihan Zeng, Lanqing Hong, Zhenguo Li, Qun Liu, Bo Han, James T. Kwok, Yu Zhang

机构 * Southern University of Science and Technology（南方科技大学）； The Hong Kong University of Science and Technology（香港科技大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）； Hong Kong Baptist University（香港 Baptist 大学）

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

2505.20236 2025-05-27 cs.CV 57%

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models

Weihao Xuan, Qingcheng Zeng, Heli Qi, Junjue Wang, Naoto Yokoya

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

2505.19373 2025-05-27 cs.CV 57%

DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models

Niloufar Alipour Talemi, Hossein Kashiani, Hossein R. Nowdeh, Fatemeh Afghah

机构 * Clemson University（克莱姆森大学）

专题命中图文多模态：cross-modal(abstract)；分类 cs.CV

Comments Accepted at the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025)

2505.19242 2025-05-27 cs.CV 57%

Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Model

Alaa Dalaq, Muzammil Behzad

专题命中图文多模态：cross-modal(abstract)；分类 cs.CV

2505.19139 2025-05-27 cs.CV 57%

The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework

Feiran Liu, Yuzhe Zhang, Xinyi Huang, Yinan Peng, Xinfeng Li, Lixu Wang, Yutong Shen, Ranjie Duan, Simeng Qin, Xiaojun Jia, Qingsong Wen, Wei Dong

机构 * Nanyang Technological University（南洋理工大学）； Beijing University of Technology（北京理工大学）； Hengxin Tech（恒心科技）； Alibaba Group（阿里巴巴集团）； Squirrel Ai Learning（squirrel AI 学习）

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

2505.18719 2025-05-27 cs.RO cs.AI 57%

VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning

Guanxing Lu, Wenkai Guo, Chubin Zhang, Yuheng Zhou, Haonan Jiang, Zifeng Gao, Yansong Tang, Ziwei Wang

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）； School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院）

专题命中图文多模态：multi-modal(abstract)；分类 cs.AI

2505.18594 2025-05-27 cs.CV cs.IR 57%

EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models

GuangHao Meng, Sunan He, Jinpeng Wang, Tao Dai, Letian Zhang, Jieming Zhu, Qing Li, Gang Wang, Rui Zhang, Yong Jiang

专题命中图文多模态：image-text(abstract)；分类 cs.CV

Comments 9 pages, 6 figures

2502.00965 2025-05-27 cs.CV cs.LG 57%

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling

Xinze Wang, Chen Chen, Yinfei Yang, Hong-You Chen, Bowen Zhang, Aditya Pal, Xiangxin Zhu, Xianzhi Du

机构 * Apple（苹果公司）

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

2505.18039 2025-05-26 cs.CV 57%

Clip4Retrofit: Enabling Real-Time Image Labeling on Edge Devices via Cross-Architecture CLIP Distillation

Li Zhong, Ahmed Ghazal, Jun-Jun Wan, Frederik Zilly, Patrick Mackens, Joachim E. Vollrath, Bogdan Sorin Coseriu

专题命中图文多模态：cross-modal(abstract)；分类 cs.CV

2505.17835 2025-05-26 cs.CV 57%

VLM Models and Automated Grading of Atopic Dermatitis

Marc Lalonde, Hamed Ghodrati

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

Comments 10 pages

2312.14999 2025-05-23 cs.CV 57%

Leveraging Habitat Information for Fine-grained Bird Identification

Tin Nguyen, Peijie Chen, Anh Totti Nguyen

机构 * Auburn University（阿伯拉罕大学）

专题命中图文多模态：multi-modal(abstract)；分类 cs.CV

2505.13426 2025-05-20 cs.CV 57%

G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning

Liang Chen, Hongcheng Gao, Tianyu Liu, Zhiqi Huang, Flood Sung, Xinyu Zhou, Yuxin Wu, Baobao Chang

机构 * Peking University（北京大学）； UCAS（中国科学院大学）； Moonshot AI

专题命中图文多模态：multimodal(abstract)；分类 cs.CV

Comments 21 pages, 14 figures, code released at https://github.com/chenllliang/G1

2505.12670 2025-05-20 cs.CV 57%

TS-VLM: Text-Guided SoftSort Pooling for Vision-Language Models in Multi-View Driving Reasoning

Lihong Chen, Hossein Hassani, Soodeh Nikan

机构 * Department of Electrical and Computer Engineering, Western University（电气与计算机工程系，西方大学）

专题命中图文多模态：multi-modal(abstract)；分类 cs.CV

2502.09120 2025-05-20 cs.CL 57%

Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues

Ye-eun Cho, Yunho Maeng

机构 * Sungkyunkwan University（顺天妇女大学）； Ewha Womans University & LLM Experimental Lab, MODULABS（成均馆大学及LLM实验实验室，MODULABS）

专题命中图文多模态：multimodal(abstract)；分类 cs.CL

Comments 11 pages, 4 figures, 7 tables

2505.11121 2025-05-19 cs.CV 57%

Redundancy-Aware Pretraining of Vision-Language Foundation Models in Remote Sensing

Mathis Jürgen Adler, Leonard Hackel, Gencer Sumbul, Begüm Demir

机构 * TU Berlin（柏林技术大学）； BIFOLD（BIFOLD机构）； EPFL（苏黎世联邦理工学院）

专题命中图文多模态：image-text(abstract)；分类 cs.CV

Comments Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2025. Our code is available at https://git.tu-berlin.de/rsim/redundacy-aware-rs-vlm

1. 图文多模态 4657 篇

A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions

AuthGuard: Generalizable Deepfake Detection via Language Guidance

MiMo-VL Technical Report

Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts

CLIP-driven rain perception: Adaptive deraining with pattern-aware network routing and mask-guided cross-attention

RemoteSAM: Towards Segment Anything for Earth Observation

SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought

Deep Modeling and Optimization of Medical Image Classification

WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation

It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data

A Survey on Training-free Open-Vocabulary Semantic Segmentation

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models

DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models

Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Model

The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework

VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning

EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling

Clip4Retrofit: Enabling Real-Time Image Labeling on Edge Devices via Cross-Architecture CLIP Distillation

VLM Models and Automated Grading of Atopic Dermatitis

Leveraging Habitat Information for Fine-grained Bird Identification

G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning

TS-VLM: Text-Guided SoftSort Pooling for Vision-Language Models in Multi-View Driving Reasoning

Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues

Redundancy-Aware Pretraining of Vision-Language Foundation Models in Remote Sensing