视觉大模型 / VLM - arXivDaily 专题

2511.09883 2025-11-14 cs.CV 79%

HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models

Liheng Zhang, Jin Wang, Hui Li, Bingfeng Zhang, Weifeng Liu

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

2509.02615 2025-11-13 astro-ph.IM cs.AI 79%

Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and Adaptation

Mariia Drozdova, Erica Lastufka, Vitaliy Kinakh, Taras Holotyak, Daniel Schaerer, Slava Voloshynovskiy

机构 * University of Geneva（日内瓦大学）

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

Comments Machine Learning and the Physical Sciences Workshop, NeurIPS 2025

2511.07812 2025-11-12 cs.CV 79%

Revisiting MLLM Based Image Quality Assessment: Errors and Remedy

Zhenchen Tang, Songlin Yang, Bo Peng, Zichuan Wang, Jing Dong

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

Comments 13 pages

2507.17088 2025-11-11 cs.CV 79%

FedVLM: Scalable Personalized Vision-Language Models through Federated Learning

Arkajyoti Mitra, Afia Anjum, Paul Agbaje, Mert Pesé, Habeeb Olufowobi

机构 * University of Texas at Arlington（德克萨斯理工大学）； Clemson University（克莱姆森大学）

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

Comments Accepted to ECAI 2025 Main Track

2510.20639 2025-10-24 cs.CV 79%

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

Ibrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit, Hadrien Reynaud, Dong Yang, Pengfei Guo, Marc Edgar, Daguang Xu, Bernhard Kainz, Bjoern Menze

机构 * University of Zurich（苏黎世大学）； NVIDIA ； Imperial College London（伦敦帝国理工学院）； FAU Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）

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

Comments NeurIPS 2025

2510.19802 2025-10-23 cs.CV 79%

Class-Aware Prototype Learning with Negative Contrast for Test-Time Adaptation of Vision-Language Models

Xiaozhen Qiao, Jingkai Zhao, Yuqiu Jiang, Xianda Guo, Zhe Sun, Hongyuan Zhang, Xuelong Li

机构 * School of Information Science and Technology, University of Science and Technology of China（信息科学与技术学院，中国科学技术大学）； Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China（人工智能研究所（TeleAI），中国电信，中华人民共和国）； College of Computer Science, Wuhan University（计算机科学学院，武汉大学）； School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University（人工智能学院，光学与电子学（iOPEN），西北工业大学）

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

2510.14624 2025-10-17 cs.CV 79%

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference

Natan Bagrov, Eugene Khvedchenia, Borys Tymchenko, Shay Aharon, Lior Kadoch, Tomer Keren, Ofri Masad, Yonatan Geifman, Ran Zilberstein, Tuomas Rintamaki, Matthieu Le, Andrew Tao

机构 * NVIDIA

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

2407.20761 2025-10-14 cs.AI 79%

OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance

Yongqiang Yao, Jingru Tan, Feizhao Zhang, Jiahao Hu, Yazhe Niu, Xin Jin, Bo Li, Pengfei Liu, Ruihao Gong, Dahua Lin, Ningyi Xu

机构 * Shanghai Jiao Tong University（上海交通大学）； SenseTime Research（商汤科技研究院）； Central South University（中南大学）； Tongji University（同济大学）； Beihang University（北航）； 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(title)；InternVL(abstract)；分类 cs.AI

Comments Accepted in ICML 2025

2510.09867 2025-10-14 cs.CV 79%

Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptation

Zhi Chen, Xin Yu, Xiaohui Tao, Yan Li, Zi Huang

机构 * University of Southern Queensland（昆士兰南方大学）； University of Queensland（昆士兰大学）

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

Comments Accepted to the journal Pattern Recognition in 2025

2509.07979 2025-10-13 cs.CV 79%

Visual Representation Alignment for Multimodal Large Language Models

Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim

机构 * KAIST AI（韩国科学技术院人工智能研究所）； New York University（纽约大学）； Chung-Ang University（Chung-Ang 大学）； Korea University（韩国大学）； ETH Zürich（苏黎世联邦理工学院）

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

Comments Project Page: https://cvlab-kaist.github.io/VIRAL/

2508.06092 2025-10-10 cs.CV 79%

Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation

Yachun Mi, Yu Li, Yanting Li, Chen Hui, Tong Zhang, Zhixuan Li, Chenyue Song, Wei Yang Bryan Lim, Shaohui Liu

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

2504.01444 2025-10-10 cs.CR cs.AI 79%

PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualization

Aofan Liu, Lulu Tang, Ting Pan, Yuguo Yin, Bin Wang, Ao Yang

机构 * School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）； School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）； Beijing Academy of Artificial Intelligence（北京人工智能研究院）

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

Comments Accepted to IEEE International Conference on Multimedia and Expo (ICME) 2025

2506.00534 2025-10-07 cs.CR cs.AI 79%

The Security Threat of Compressed Projectors in Large Vision-Language Models

Yudong Zhang, Ruobing Xie, Xingwu Sun, Jiansheng Chen, Zhanhui Kang, Di Wang, Yu Wang

机构 * Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）； Large Language Model Department, Tencent（腾讯大语言模型部门）； School of Computer and Communication Engineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）； Faculty of Science and Technology, University of Macau（澳门大学科技学院）

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

Comments Accepted by EMNLP 2025 findings

2510.00088 2025-10-02 cs.AI cs.CY 79%

Judging by Appearances? Auditing and Intervening Vision-Language Models for Bail Prediction

Sagnik Basu, Shubham Prakash, Ashish Maruti Barge, Siddharth D Jaiswal, Abhisek Dash, Saptarshi Ghosh, Animesh Mukherjee

机构 * Indian Institute of Technology Kharagpur（印度理工学院Khargapur分校）； Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）

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

2509.25568 2025-10-01 cs.CL cs.AI 79%

Probing the Limits of Stylistic Alignment in Vision-Language Models

Asma Farajidizaji, Akash Gupta, Vatsal Raina

机构 * Imperial College London（伦敦帝国学院）； Apta AI

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

Comments 5 pages, 1 figure, 3 tables

2509.13067 2025-09-30 cs.CV 79%

HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models

Xu Li, Yuxuan Liang, Xiaolei Chen, Yi Zheng, Haotian Chen, Bin Li, Xiangyang Xue

机构 * College of Computer Science and Artificial Intelligence, Fudan University（计算机科学与人工智能学院，复旦大学）

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

2509.22524 2025-09-29 cs.CV 79%

Color Names in Vision-Language Models

Alexandra Gomez-Villa, Pablo Hernández-Cámara, Muhammad Atif Butt, Valero Laparra, Jesus Malo, Javier Vazquez-Corral

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

2509.21102 2025-09-26 cs.CV 79%

Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language Models

Suaiba Amina Salahuddin, Teresa Dorszewski, Marit Almenning Martiniussen, Tone Hovda, Antonio Portaluri, Solveig Thrun, Michael Kampffmeyer, Elisabeth Wetzer, Kristoffer Wickstrøm, Robert Jenssen

机构 * UiT The Arctic University of Norway（乌塔大学极地大学）； Technical University of Denmark（技术大学）； Østfold Hospital Trust（奥斯fold医院信托）； Vestre Viken Hospital Trust（维斯特维肯医院信托）； Radboud University Nijmegen Medical Centre（拉德堡德大学奈梅亨医疗中心）； The Netherlands Cancer Institute（荷兰癌症研究所）； Antoni van Leeuwenhoek Hospital（安东尼·弗莱明医院）； University of Copenhagen（哥本哈根大学）

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

2508.13739 2025-09-25 cs.CV 79%

Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector

Yiming Cao, Yanjie Li, Kaisheng Liang, Bin Xiao

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

2509.19524 2025-09-25 cs.AI cs.RO 79%

Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation

Ramy ElMallah, Krish Chhajer, Chi-Guhn Lee

机构 * University of Toronto（多伦多大学）

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

Comments Accepted to the CoRL 2025 Eval&Deploy Workshop

2501.01346 2025-09-24 cs.CV cs.CL 79%

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability

Dong Shu, Haiyan Zhao, Jingyu Hu, Weiru Liu, Ali Payani, Lu Cheng, Mengnan Du

机构 * Northwestern University（西北大学）； New Jersey Institute of Technology（新泽西理工学院）； University of Bristol（布里斯托大学）； Cisco Research（思科研究）； University of Illinois Chicago（伊利诺伊大学芝加哥分校）

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

Comments EMNLP 2025 Findings

2509.09064 2025-09-12 cs.CV 79%

Enhancing 3D Medical Image Understanding with Pretraining Aided by 2D Multimodal Large Language Models

Qiuhui Chen, Xuancheng Yao, Huping Ye, Yi Hong

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）

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

Comments Accepted by IEEE Journal of Biomedical and Health Informatics (JBHI)

2502.06130 2025-09-11 cs.CV cs.CL 79%

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models

Ce Zhang, Zifu Wan, Zhehan Kan, Martin Q. Ma, Simon Stepputtis, Deva Ramanan, Russ Salakhutdinov, Louis-Philippe Morency, Katia Sycara, Yaqi Xie

机构 * School of Computer Science, Carnegie Mellon University（计算机科学系，卡内基梅隆大学）

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

Comments Accepted by ICLR 2025. Project page: https://zhangce01.github.io/DeGF/

2509.05000 2025-09-08 cs.CV 79%

Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework

Tianpei Zhang, Jufeng Zhao, Yiming Zhu, Guangmang Cui

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

2509.03895 2025-09-05 cs.CV 79%

Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model

Phuoc-Nguyen Bui, Khanh-Binh Nguyen, Hyunseung Choo

机构 * Sungkyunkwan University（顺天大学）； Deakin University（德金大学）

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

Comments ICCV 2025 - LIMIT Workshop

2504.20860 2025-09-03 cs.CV 79%

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models

Mainak Singha, Subhankar Roy, Sarthak Mehrotra, Ankit Jha, Moloud Abdar, Biplab Banerjee, Elisa Ricci

机构 * University of Trento（特伦托大学）； University of Bergamo（贝拉姆奥大学）； Indian Institute of Technology Bombay（印度班加罗尔理工学院）； LNMIIT Jaipur（斋普尔LNMIIT）； The University of Queensland（昆士兰大学）； Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）

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

Comments Accepted in ICCV 2025

2501.15144 2025-09-03 cs.CV 79%

Exploring Primitive Visual Measurement Understanding and the Role of Output Format in Learning in Vision-Language Models

Ankit Yadav, Lingqiao Liu, Yuankai Qi

机构 * The University of Adelaide（阿德莱德大学）； Macquarie University（麦考瑞大学）

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

Comments 25 Pages Accepted in DICTA 2025

2508.16188 2025-08-29 cs.CL cs.CV cs.MM cs.SD eess.AS 79%

Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation

Weiting Tan, Jiachen Lian, Hirofumi Inaguma, Paden Tomasello, Philipp Koehn, Xutai Ma

机构 * Johns Hopkins University（约翰霍普金斯大学）； Meta AI Research（Meta AI 研究）

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

Comments EMNLP 2025 (Findings)

2508.18886 2025-08-27 cs.CV 79%

Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models

Yuexuan Xia, Benteng Ma, Jiang He, Zhiyong Wang, Qi Dou, Yong Xia

机构 * National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（集成空天地海大数据应用技术国家工程实验室）； Northwestern Polytechnical University（西北工业大学）； Huiying Medical Technology Company Ltd.（慧影医疗技术有限公司）； The School of Computer Science（计算机学院）； The University of Sydney（悉尼大学）； Department of Computer Science and Engineering（计算机科学与工程系）； 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(title,abstract)；分类 cs.CV

2508.17417 2025-08-26 cs.CV 79%

Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models

Xiaojie Yin, Qilong Wang, Qinghua Hu

机构 * Tianjin University（天津大学）

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

1. VLM训练与架构 5039 篇

HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models

Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and Adaptation

Revisiting MLLM Based Image Quality Assessment: Errors and Remedy

FedVLM: Scalable Personalized Vision-Language Models through Federated Learning

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

Class-Aware Prototype Learning with Negative Contrast for Test-Time Adaptation of Vision-Language Models

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference

OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance

Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptation

Visual Representation Alignment for Multimodal Large Language Models

Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation

PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualization

The Security Threat of Compressed Projectors in Large Vision-Language Models

Judging by Appearances? Auditing and Intervening Vision-Language Models for Bail Prediction

Probing the Limits of Stylistic Alignment in Vision-Language Models

HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models

Color Names in Vision-Language Models

Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language Models

Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector

Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability

Enhancing 3D Medical Image Understanding with Pretraining Aided by 2D Multimodal Large Language Models

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models

Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework

Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models

Exploring Primitive Visual Measurement Understanding and the Role of Output Format in Learning in Vision-Language Models

Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation

Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models

Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models