视觉大模型 / VLM - arXivDaily 专题

2505.17670 2025-07-09 cs.LG cs.AI 84%

Towards General Continuous Memory for Vision-Language Models

Wenyi Wu, Zixuan Song, Kun Zhou, Yifei Shao, Zhiting Hu, Biwei Huang

机构 * University of California, San Diego（加州大学圣地亚哥分校）

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

2506.21862 2025-06-30 cs.CV cs.AI cs.HC cs.MM 84%

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

Boyuan Sun, Jiaxing Zhao, Xihan Wei, Qibin Hou

机构 * VCIP, School of Computer Science, Nankai University（南开大学计算机学院）； Tongyi Lab, Alibaba Group（阿里巴巴集团 Tongyi 实验室）

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

Comments 21 pages, 4 figures, 7 tables

2506.17267 2025-06-24 cs.LG cs.AI 84%

CF-VLM:CounterFactual Vision-Language Fine-tuning

Jusheng Zhang, Kaitong Cai, Yijia Fan, Jian Wang, Keze Wang

机构 * Sun Yat-sen University（中山大学）； Snap Inc.（Snap公司）

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

2506.15645 2025-06-19 cs.CV cs.AI 84%

Demystifying the Visual Quality Paradox in Multimodal Large Language Models

Shuo Xing, Lanqing Guo, Hongyuan Hua, Seoyoung Lee, Peiran Li, Yufei Wang, Zhangyang Wang, Zhengzhong Tu

机构 * Texas A&M University（德克萨斯大学）； University of Texas at Austin（德克萨斯大学奥斯汀分校）； University of Toronto（多伦多大学）； Nanyang Technological University（南洋理工大学）

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

Comments 18 pages

2506.09638 2025-06-12 cs.LG cs.CV 84%

FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-Language Models

Weiying Zheng, Ziyue Lin, Pengxin Guo, Yuyin Zhou, Feifei Wang, Liangqiong Qu

机构 * The University of Hong Kong（香港大学）； UC Santa Cruz（圣克拉拉大学）

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

2505.03792 2025-06-04 cs.LG cs.AI 84%

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

Lang Feng, Weihao Tan, Zhiyi Lyu, Longtao Zheng, Haiyang Xu, Ming Yan, Fei Huang, Bo An

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

Comments ICML 2025

2505.23043 2025-05-30 cs.CV cs.AI 84%

Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation

Jihai Zhang, Tianle Li, Linjie Li, Zhengyuan Yang, Yu Cheng

机构 * The Chinese University of Hong Kong（香港中文大学）； Microsoft（微软公司）

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

2505.20405 2025-05-28 cs.CV cs.AI cs.CL cs.MM 84%

What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models

Lorenzo Baraldi, Davide Bucciarelli, Federico Betti, Marcella Cornia, Lorenzo Baraldi, Nicu Sebe, Rita Cucchiara

机构 * University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学）； University of Pisa（比萨大学）； University of Trento（特伦托大学）； IIT-CNR

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

2505.17042 2025-05-26 cs.CL cs.CV cs.IR cs.LG 84%

VLM-KG: Multimodal Radiology Knowledge Graph Generation

Abdullah Abdullah, Seong Tae Kim

机构 * Department of Computer Science and Engineering, Kyung Hee University（计算机科学与工程系，庆熙大学）

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

Comments 10 pages, 2 figures

2505.14646 2025-05-21 cs.CV cs.AI 84%

CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation

Anna C. Doris, Md Ferdous Alam, Amin Heyrani Nobari, Faez Ahmed

机构 * Massachusetts Institute of Technology（麻省理工学院）

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

2503.22577 2025-05-21 cs.CV cs.AI 84%

Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization

Iñigo Pikabea, Iñaki Lacunza, Oriol Pareras, Carlos Escolano, Aitor Gonzalez-Agirre, Javier Hernando, Marta Villegas

机构 * Barcelona Supercomputing Center（巴塞罗那超级计算中心）； Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）

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

Comments v2: Expanded model merging experiments. Fix duplicated subsection on limitations

2505.10526 2025-05-20 cs.LG cs.CL cs.CV 84%

MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models

Mugilan Ganesan, Shane Segal, Ankur Aggarwal, Nish Sinnadurai, Sean Lie, Vithursan Thangarasa

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

Comments Main paper: 11 pages, 4 figures, 3 tables. Supplementary: 1 page

2403.13797 2025-05-20 cs.LG cs.CV 84%

Bridge the Modality and Capability Gaps in Vision-Language Model Selection

Chao Yi, Yu-Hang He, De-Chuan Zhan, Han-Jia Ye

机构 * State Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室）

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

Comments fix typo in figure 2 "Capability Gap"

2505.09498 2025-05-15 cs.CV cs.AI 84%

Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput

Bo Zhang, Shuo Li, Runhe Tian, Yang Yang, Jixin Tang, Jinhao Zhou, Lin Ma

机构 * Meituan（美团）

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

Comments 18 pages, 7 figures

2505.08818 2025-05-15 cs.CY cs.AI cs.LG 84%

Position: Restructuring of Categories and Implementation of Guidelines Essential for VLM Adoption in Healthcare

Amara Tariq, Rimita Lahiri, Charles Kahn, Imon Banerjee

机构 * Amara Tariq, Ph.D（博士）； Rimita Lahiri, Ph.D（博士）； Charles Kahn, M.D（医学博士）； Imon Banerjee, Ph.D（博士）

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

Comments 15 pages, 2, tables, 3 figures

2505.05318 2025-05-09 cs.CV cs.AI cs.CY cs.HC cs.RO 84%

Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects

Agnese Chiatti, Sara Bernardini, Lara Shibelski Godoy Piccolo, Viola Schiaffonati, Matteo Matteucci

机构 * Politecnico di Milano, Italy（米兰理工学院，意大利）； University of Oxford, UK（牛津大学，英国）； CODE University of Applied Sciences, Germany（德国应用科学大学）

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

2410.22330 2025-05-08 cs.CV cs.CL cs.LG 84%

Vision-Language Models Create Cross-Modal Task Representations

Grace Luo, Trevor Darrell, Amir Bar

机构 * University of California, Berkeley, USA（加州大学伯克利分校）

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

Comments ICML 2025

2501.18271 2025-05-08 cs.LG cs.AI 84%

Vision-Language Model Selection and Reuse for Downstream Adaptation

Hao-Zhe Tan, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo

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

Comments Accepted by ICML 2025

2505.03242 2025-05-07 cs.CV cs.AI 84%

Seeing the Abstract: Translating the Abstract Language for Vision Language Models

Davide Talon, Federico Girella, Ziyue Liu, Marco Cristani, Yiming Wang

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

Comments Accepted to CVPR25. Project page: https://davidetalon.github.io/fashionact-page/

2504.18027 2025-04-28 cs.CV cs.AI cs.RO 84%

A Large Vision-Language Model based Environment Perception System for Visually Impaired People

Zezhou Chen, Zhaoxiang Liu, Kai Wang, Kohou Wang, Shiguo Lian

机构 * AI Innovation Center, China Unicom（中国unicom人工智能创新中心）； Unicom Digital Technology, China Unicom（中国unicom数字技术）

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

Comments Accepted by IROS2024(9 pages, 8 figures)

2504.17826 2025-04-28 cs.CV cs.AI 84%

FashionM3: Multimodal, Multitask, and Multiround Fashion Assistant based on Unified Vision-Language Model

Kaicheng Pang, Xingxing Zou, Waikeung Wong

机构 * Laboratory for Artificial Intelligence in Design（人工智能设计实验室）； School of Fashion and Textiles（时尚与纺织学院）

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

2504.09620 2025-04-15 cs.CL cs.AI cs.CV cs.MA 84%

Metropolis-Hastings Captioning Game: Knowledge Fusion of Vision Language Models via Decentralized Bayesian Inference

Yuta Matsui, Ryosuke Yamaki, Ryo Ueda, Seitaro Shinagawa, Tadahiro Taniguchi

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

2504.05141 2025-04-10 cs.CV cs.AI 84%

EffOWT: Transfer Visual Language Models to Open-World Tracking Efficiently and Effectively

Bingyang Wang, Kaer Huang, Bin Li, Yiqiang Yan, Lihe Zhang, Huchuan Lu, You He

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

Comments 11 pages, 5 figures

2504.02862 2025-04-08 cs.CV cs.LG 84%

Towards Understanding How Knowledge Evolves in Large Vision-Language Models

Sudong Wang, Yunjian Zhang, Yao Zhu, Jianing Li, Zizhe Wang, Yanwei Liu, Xiangyang Ji

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

Comments Accepted by CVPR 2025

2410.10114 2025-04-02 cs.LG cs.CL cs.CV 84%

Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models

Jun Luo, Chen Chen, Shandong Wu

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

Comments ICLR 2025

2411.16761 2025-04-01 cs.CV cs.AI 84%

Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning

Ji Hyeok Jung, Eun Tae Kim, Seoyeon Kim, Joo Ho Lee, Bumsoo Kim, Buru Chang

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

Comments CVPR2025 Camera-ready

2503.20662 2025-03-27 cs.CV cs.LG eess.IV 84%

AutoRad-Lung: A Radiomic-Guided Prompting Autoregressive Vision-Language Model for Lung Nodule Malignancy Prediction

Sadaf Khademi, Mehran Shabanpour, Reza Taleei, Anastasia Oikonomou, Arash Mohammadi

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

2503.08497 2025-03-27 cs.LG cs.CV 84%

MMRL: Multi-Modal Representation Learning for Vision-Language Models

Yuncheng Guo, Xiaodong Gu

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

Comments Accepted by CVPR 2025

2503.19508 2025-03-26 cs.CV cs.LG 84%

Improved Alignment of Modalities in Large Vision Language Models

Kartik Jangra, Aman Kumar Singh, Yashwani Mann, Geetanjali Rathee

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

2503.06993 2025-03-11 cs.LG cs.CV 84%

CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model

Shihao Hou, Xinyi Shang, Shreyank N Gowda, Yang Lu, Chao Wu, Yan Yan, Hanzi Wang

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

1. VLM训练与架构 5009 篇

Towards General Continuous Memory for Vision-Language Models

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

CF-VLM:CounterFactual Vision-Language Fine-tuning

Demystifying the Visual Quality Paradox in Multimodal Large Language Models

FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-Language Models

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation

What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models

VLM-KG: Multimodal Radiology Knowledge Graph Generation

CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation

Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization

MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models

Bridge the Modality and Capability Gaps in Vision-Language Model Selection

Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput

Position: Restructuring of Categories and Implementation of Guidelines Essential for VLM Adoption in Healthcare

Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects

Vision-Language Models Create Cross-Modal Task Representations

Vision-Language Model Selection and Reuse for Downstream Adaptation

Seeing the Abstract: Translating the Abstract Language for Vision Language Models

A Large Vision-Language Model based Environment Perception System for Visually Impaired People

FashionM3: Multimodal, Multitask, and Multiround Fashion Assistant based on Unified Vision-Language Model

Metropolis-Hastings Captioning Game: Knowledge Fusion of Vision Language Models via Decentralized Bayesian Inference

EffOWT: Transfer Visual Language Models to Open-World Tracking Efficiently and Effectively

Towards Understanding How Knowledge Evolves in Large Vision-Language Models

Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models

Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning

AutoRad-Lung: A Radiomic-Guided Prompting Autoregressive Vision-Language Model for Lung Nodule Malignancy Prediction

MMRL: Multi-Modal Representation Learning for Vision-Language Models

Improved Alignment of Modalities in Large Vision Language Models

CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model