视觉大模型 / VLM - arXivDaily 专题

2511.15633 2025-11-20 cs.CV cs.LG 62%

Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning

基于CLIP的层次语义树锚定的类增量学习

Tao Hu, Lan Li, Zhen-Hao Xie, Da-Wei Zhou

机构 * School of Artificial Intelligence, Nanjing University（人工智能学院，南京大学）； State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.LG

AI总结 HASTEN通过层次语义树锚定方法，有效解决CLIP类增量学习中的灾难性遗忘问题，提升模型对层次化类别结构的保持能力。

2510.26125 2025-11-14 cs.CV cs.AI 62%

WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios

Runsheng Xu, Hubert Lin, Wonseok Jeon, Hao Feng, Yuliang Zou, Liting Sun, John Gorman, Ekaterina Tolstaya, Sarah Tang, Brandyn White, Ben Sapp, Mingxing Tan, Jyh-Jing Hwang, Dragomir Anguelov

机构 * Waymo LLC（Waymo公司）

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

2511.08075 2025-11-12 cs.CV cs.AI 62%

CLIP is All You Need for Human-like Semantic Representations in Stable Diffusion

Cameron Braunstein, Mariya Toneva, Eddy Ilg

机构 * Saarland University, Saarbrücken Germany（萨尔兰州大学）； MPI for Software Systems, Saarbrücken Germany（软件系统研究所）； University of Technology Nuremberg, Nuremberg Germany（纽伦堡技术大学）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.AI

Comments 28 pages, 8 figures, 2 tables

2504.13231 2025-11-12 cs.CV cs.AI 62%

WildFireCan-MMD: A Multimodal Dataset for Classification of User-Generated Content During Wildfires in Canada

Braeden Sherritt, Isar Nejadgholi, Efstratios Aivaliotis, Khaled Mslmani, Marzieh Amini

机构 * Carleton University（卡尔顿大学）； National Research Council Canada（加拿大国家研究委员会）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.AI

2504.18800 2025-11-11 cs.CV cs.AI 62%

Video CLIP Model for Multi-View Echocardiography Interpretation

Ryo Takizawa, Satoshi Kodera, Tempei Kabayama, Ryo Matsuoka, Yuta Ando, Yuto Nakamura, Haruki Settai, Norihiko Takeda

机构 * The University of Tokyo Hospital（东京大学医院）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.AI

2511.02720 2025-11-05 cs.CV cs.AI 62%

LLEXICORP: End-user Explainability of Convolutional Neural Networks

Vojtěch Kůr, Adam Bajger, Adam Kukučka, Marek Hradil, Vít Musil, Tomáš Brázdil

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

2511.02358 2025-11-05 cs.CL cs.AI cs.IR cs.LG cs.MM 62%

Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation

Wongyu Kim, Hochang Lee, Sanghak Lee, Yoonsung Kim, Jaehyun Park

机构 * NC AI（NC人工智能）

专题命中其他VLM ：MLLM(abstract)；分类 cs.AI、cs.LG

Comments Accepted to MMGenSR Workshop (CIKM 2025)

2503.08221 2025-11-04 cs.CV cs.AI cs.MM 62%

EgoBlind: Towards Egocentric Visual Assistance for the Blind

Junbin Xiao, Nanxin Huang, Hao Qiu, Zhulin Tao, Xun Yang, Richang Hong, Meng Wang, Angela Yao

机构 * National University of Singapore（新加坡国立大学）； Communication University of China（中国传媒大学）； University of Science and Technology of China（中国科学技术大学）； Hefei University of Technoloy（合肥工业大学）

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments NeurIPS'25 (D&B Track)

2511.00480 2025-11-04 cs.CV cs.LG 62%

FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts

Weihao Bo, Yanpeng Sun, Yu Wang, Xinyu Zhang, Zechao Li

机构 * Nanjing University of Science and Technology（南京理工大学）； National University of Singapore（新加坡国立大学）； Baidu VIS（百度视觉部）； University of Auckland（奥克兰大学）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.LG

2410.08478 2025-11-04 cs.IR cs.AI cs.LG 62%

Federated Vision-Language-Recommendation with Personalized Fusion

Zhiwei Li, Guodong Long, Jing Jiang, Chengqi Zhang, Qiang Yang

专题命中其他VLM ：vision-language model(abstract)；分类 cs.AI、cs.LG

Comments 15 pages, 10 figures, 7 tables, conference

2510.24321 2025-10-29 cs.CV cs.AI 62%

Few-Shot Remote Sensing Image Scene Classification with CLIP and Prompt Learning

Ivica Dimitrovski, Vlatko Spasev, Ivan Kitanovski

机构 * Faculty of Computer Science and Engineering（计算机科学与工程学院）； University Ss Cyril and Methodius（西里尔与美多西乌斯大学）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.AI

2510.22141 2025-10-28 cs.CV cs.CL cs.LG cs.RO eess.IV 62%

LOC: A General Language-Guided Framework for Open-Set 3D Occupancy Prediction

Yuhang Gao, Xiang Xiang, Sheng Zhong, Guoyou Wang

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.LG

2510.16448 2025-10-21 cs.LG cs.AI 62%

Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts

Yongxiang Hua, Haoyu Cao, Zhou Tao, Bocheng Li, Zihao Wu, Chaohu Liu, Linli Xu

机构 * University of Science and Technology of China（科学技术大学）； State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.AI、cs.LG

Comments ACM MM25

2510.13364 2025-10-16 cs.CV cs.AI 62%

Language as a Label: Zero-Shot Multimodal Classification of Everyday Postures under Data Scarcity

MingZe Tang, Jubal Chandy Jacob

机构 * Department of Computing Science University of Aberdeen（计算科学系阿伯丁大学）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.AI

2504.13211 2025-10-16 cs.CV cs.AI 62%

MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance

Subin Kim, Hoonrae Kim, Jihyun Lee, Yejin Jeon, Gary Geunbae Lee

机构 * KT Corporation, Republic of Korea（韩国KT公司）； Graduate School of Artificial Intelligence, POSTECH, Republic of Korea（POSTECH人工智能研究生院）； Computer Science and Engineering, POSTECH, Republic of Korea（POSTECH计算机科学与工程系）

专题命中其他VLM ：vision language model(abstract)；分类 cs.CV、cs.AI

Comments EMNLP 2025 Main

2508.10315 2025-10-14 cs.LG cs.AI 62%

A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning

Keke Gai, Dongjue Wang, Jing Yu, Liehuang Zhu, Qi Wu

机构 * School of Cyberspace Science and Technology, Beijing Institute of Technology（信息空间科学与技术学院，北京理工大学）； School of Information Engineering, Minzu University of China（信息工程学院，民族大学）； Australian Institute of Machine Learning, The University of Adelaide（澳大利亚机器学习研究所，阿德莱德大学）

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.AI、cs.LG

2510.10100 2025-10-14 cs.CV cs.LG 62%

Cooperative Pseudo Labeling for Unsupervised Federated Classification

Kuangpu Guo, Lijun Sheng, Yongcan Yu, Jian Liang, Zilei Wang, Ran He

机构 * University of Science and Technology of China（中国科学技术大学）； NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

专题命中其他VLM ：vision language model(abstract)；分类 cs.CV、cs.LG

Comments Accepted by ICCV 2025

2506.08894 2025-10-10 cs.CV cs.AI 62%

Product of Experts for Visual Generation

Yunzhi Zhang, Carson Murtuza-Lanier, Zizhang Li, Yilun Du, Jiajun Wu

机构 * Stanford University（斯坦福大学）； Harvard University（哈佛大学）

专题命中其他VLM ：visual language model(abstract)；分类 cs.CV、cs.AI

Comments Project page: https://product-of-experts.github.io/

2510.00046 2025-10-02 cs.CV cs.AI 62%

Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image Models

Xiaotian Zou

机构 * Xiaotian Zou

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments 10 pages, 3 figures

2509.25818 2025-10-01 cs.CV cs.AI cs.CL 62%

VELA: An LLM-Hybrid-as-a-Judge Approach for Evaluating Long Image Captions

Kazuki Matsuda, Yuiga Wada, Shinnosuke Hirano, Seitaro Otsuki, Komei Sugiura

机构 * Keio University（庆应大学）

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments EMNLP 2025 Main Conference

2504.08727 2025-09-24 cs.CV cs.AI cs.CY 62%

Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images

Boyang Deng, Songyou Peng, Kyle Genova, Gordon Wetzstein, Noah Snavely, Leonidas Guibas, Thomas Funkhouser

机构 * Stanford University（斯坦福大学）； Google DeepMind（谷歌DeepMind）

专题命中其他VLM ：MLLM(abstract)；分类 cs.CV、cs.AI

Comments ICCV 2025, Project page: https://boyangdeng.com/visual-chronicles , second and third listed authors have equal contributions

2509.17024 2025-09-23 cs.CV cs.AI 62%

When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration

Wenxuan Fang, Jili Fan, Chao Wang, Xiantao Hu, Jiangwei Weng, Ying Tai, Jian Yang, Jun Li

机构 * School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学）； School of Electrical Engineering, Southeast University（电气工程学院，东南大学）； School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院，南京大学）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.AI

2506.05439 2025-09-22 cs.CV cs.AI cs.CL 62%

LLMs Can Compensate for Deficiencies in Visual Representations

Sho Takishita, Jay Gala, Abdelrahman Mohamed, Kentaro Inui, Yova Kementchedjhieva

机构 * Fujitsu Limited（富士通有限公司）； MBZUAI ； Tohoku University（东北大学）； RIKEN（日本研究机构）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.AI

Comments EMNLP 2025 Findings

2509.10704 2025-09-16 cs.AI cs.CV 62%

Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration

Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Rajarishi Sinha, Sercan Ö. Arık

机构 * Google（谷歌）

专题命中其他VLM ：MLLM(abstract)；分类 cs.CV、cs.AI

Comments 15 pages, 7 figures, 2 tables (22 pages, 9 figures and 3 tables including references and appendices)

2502.09507 2025-09-15 cs.LG cs.CV 62%

When and How Does CLIP Enable Domain and Compositional Generalization?

Elias Kempf, Simon Schrodi, Max Argus, Thomas Brox

机构 * University of Freiburg（弗赖堡大学）

专题命中其他VLM ：vision-language model(abstract)；分类 cs.CV、cs.LG

Comments ICML 2025 (Spotlight)

2509.09307 2025-09-12 cs.CV cs.AI cs.CL cs.MM 62%

Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization

Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jinpu Yang, Hongqing Liang, Yan Hu, Benyou Wang

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

2504.21831 2025-09-12 cs.CV cs.AI 62%

Early Exit and Multi Stage Knowledge Distillation in VLMs for Video Summarization

Anas Anwarul Haq Khan, Utkarsh Verma, Ganesh Ramakrishnan

机构 * Department of Computer Science and Engineering, IIT Bombay（印度理工学院班加罗尔计算机科学与工程系）； Center of Machine Intelligence and Data Science (C-MInDS), IIT Bombay（印度理工学院班加罗尔人工智能与数据科学中心）

专题命中其他VLM ：vision language model(abstract)；分类 cs.CV、cs.AI

2508.06585 2025-09-10 cs.AI cs.CV 62%

CountQA: How Well Do MLLMs Count in the Wild?

Jayant Sravan Tamarapalli, Rynaa Grover, Nilay Pande, Sahiti Yerramilli

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

2509.05714 2025-09-09 cs.AI cs.CV 62%

Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs

Zhaoyu Fan, Kaihang Pan, Mingze Zhou, Bosheng Qin, Juncheng Li, Shengyu Zhang, Wenqiao Zhang, Siliang Tang, Fei Wu, Yueting Zhuang

机构 * Zhejiang University（浙江大学）

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments 15 pages, 6 figures

2509.04757 2025-09-08 cs.CV cs.AI 62%

MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Damage Assessment using UAV Imagery

Zhangding Liu, Neda Mohammadi, John E. Taylor

专题命中其他VLM ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments 34 pages, 7 figures

1. 其他VLM 1565 篇

Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning

WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios

CLIP is All You Need for Human-like Semantic Representations in Stable Diffusion

WildFireCan-MMD: A Multimodal Dataset for Classification of User-Generated Content During Wildfires in Canada

Video CLIP Model for Multi-View Echocardiography Interpretation

LLEXICORP: End-user Explainability of Convolutional Neural Networks

Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation

EgoBlind: Towards Egocentric Visual Assistance for the Blind

FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts

Federated Vision-Language-Recommendation with Personalized Fusion

Few-Shot Remote Sensing Image Scene Classification with CLIP and Prompt Learning

LOC: A General Language-Guided Framework for Open-Set 3D Occupancy Prediction

Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts

Language as a Label: Zero-Shot Multimodal Classification of Everyday Postures under Data Scarcity

MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance

A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning

Cooperative Pseudo Labeling for Unsupervised Federated Classification

Product of Experts for Visual Generation

Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image Models

VELA: An LLM-Hybrid-as-a-Judge Approach for Evaluating Long Image Captions

Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images

When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration

LLMs Can Compensate for Deficiencies in Visual Representations

Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration

When and How Does CLIP Enable Domain and Compositional Generalization?

Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization

Early Exit and Multi Stage Knowledge Distillation in VLMs for Video Summarization

CountQA: How Well Do MLLMs Count in the Wild?

Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs

MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Damage Assessment using UAV Imagery