视觉大模型 / VLM - arXivDaily 专题

2403.11631 2025-04-15 cs.CV 79%

Compositional Kronecker Context Optimization for Vision-Language Models

Kun Ding, Xiaohui Li, Qiang Yu, Ying Wang, Haojian Zhang, Shiming Xiang

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

2504.08966 2025-04-15 cs.CV 79%

PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models

Mohamed Dhouib, Davide Buscaldi, Sonia Vanier, Aymen Shabou

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

Comments Accepted to CVPR 2025

2504.03154 2025-04-07 cs.CV 79%

TokenFLEX: Unified VLM Training for Flexible Visual Tokens Inference

Junshan Hu, Jialiang Mao, Zhikang Liu, Zhongpu Xia, Peng Jia, Xianpeng Lang

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

2502.19777 2025-04-01 cs.CV 79%

InPK: Infusing Prior Knowledge into Prompt for Vision-Language Models

Shuchang Zhou, Jiwei Wei, Shiyuan He, Yuyang Zhou, Chaoning Zhang, Jie Zou, Ning Xie, Yang Yang

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

2503.18943 2025-03-28 cs.CV 79%

SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding

Mingze Xu, Mingfei Gao, Shiyu Li, Jiasen Lu, Zhe Gan, Zhengfeng Lai, Meng Cao, Kai Kang, Yinfei Yang, Afshin Dehghan

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

Comments Technical report

2110.04544 2025-03-26 cs.CV cs.CL 79%

CLIP-Adapter: Better Vision-Language Models with Feature Adapters

Peng Gao, Shijie Geng, Renrui Zhang, Teli Ma, Rongyao Fang, Yongfeng Zhang, Hongsheng Li, Yu Qiao

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

Comments Accepted by IJCV

2503.18160 2025-03-25 cs.CV cs.MM 79%

MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language Models

Haoyang Li, Siyu Zhou, Liang Wang, Guodong Long

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

Comments Accepted by the IEEE International Conference on Multimedia & Expo 2025 (ICME 2025); 12 pages, 6 figures, 8 tables

2503.16945 2025-03-24 cs.CV 79%

PE-CLIP: A Parameter-Efficient Fine-Tuning of Vision Language Models for Dynamic Facial Expression Recognition

Ibtissam Saadi, Abdenour Hadid, Douglas W. Cunningham, Abdelmalik Taleb-Ahmed, Yassin El Hillali

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

2503.16843 2025-03-24 cs.CV 79%

LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models

Jian Liang, Wenke Huang, Guancheng Wan, Qu Yang, Mang Ye

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

Comments Accepted by CVPR 2025

2406.19905 2025-03-18 cs.CV 79%

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model

Longrong Yang, Dong Shen, Chaoxiang Cai, Fan Yang, Tingting Gao, Di Zhang, Xi Li

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

2503.11205 2025-03-17 cs.CV 79%

LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs

Leqi Shen, Tao He, Guoqiang Gong, Fan Yang, Yifeng Zhang, Pengzhang Liu, Sicheng Zhao, Guiguang Ding

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

2412.11509 2025-03-17 cs.CV 79%

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

Shihan Wu, Ji Zhang, Pengpeng Zeng, Lianli Gao, Jingkuan Song, Heng Tao Shen

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

2411.15232 2025-03-13 cs.CV cs.CL 79%

BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models

Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz, Yiming Xiao

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

Comments Accepted to CVPR 2025

2503.08019 2025-03-12 cs.CV 79%

Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models

Bozhi Luan, Wengang Zhou, Hao Feng, Zhe Wang, Xiaosong Li, Houqiang Li

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

2503.06141 2025-03-11 cs.CV 79%

Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model

Mingxing Li, Rui Wang, Lei Sun, Yancheng Bai, Xiangxiang Chu

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

2502.18101 2025-03-11 cs.CV cs.CL 79%

Detecting Offensive Memes with Social Biases in Singapore Context Using Multimodal Large Language Models

Cao Yuxuan, Wu Jiayang, Alistair Cheong Liang Chuen, Bryan Shan Guanrong, Theodore Lee Chong Jen, Sherman Chann Zhi Shen

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

Comments Accepted at 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP), co-located with NAACL 2025. This is an extended version with some appendix moved to the main body

2502.14125 2025-02-21 cs.CV 79%

Modular Prompt Learning Improves Vision-Language Models

Zhenhan Huang, Tejaswini Pedapati, Pin-Yu Chen, Jianxi Gao

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

Comments 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing

2502.12095 2025-02-18 cs.CV 79%

Descriminative-Generative Custom Tokens for Vision-Language Models

Pramuditha Perera, Matthew Trager, Luca Zancato, Alessandro Achille, Stefano Soatto

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

2406.15279 2025-02-18 cs.AI cs.CL 79%

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model

Siyin Wang, Xingsong Ye, Qinyuan Cheng, Junwen Duan, Shimin Li, Jinlan Fu, Xipeng Qiu, Xuanjing Huang

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

Journal ref NAACL 2025

2408.08093 2025-02-17 cs.CV cs.MM 79%

When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding

Pingping Zhang, Jinlong Li, Kecheng Chen, Meng Wang, Long Xu, Haoliang Li, Nicu Sebe, Sam Kwong, Shiqi Wang

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

2409.01162 2025-02-13 cs.CV 79%

Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models

Gaotong Yu, Yi Chen, Jian Xu

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

2502.02069 2025-02-05 cs.CV 79%

LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models

Yuto Kojima, Jiarui Xu, Xueyan Zou, Xiaolong Wang

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

2502.01616 2025-02-04 cs.LG 79%

Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning

Udita Ghosh, Dripta S. Raychaudhuri, Jiachen Li, Konstantinos Karydis, Amit Roy-Chowdhury

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

2502.00717 2025-02-04 cs.CV 79%

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction

Chao Wang, Jianming Yang, Yang Zhou

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

Comments 8 pages, 5 figures, 4 tables

2501.09532 2025-02-04 cs.CV 79%

AdaFV: Rethinking of Visual-Language alignment for VLM acceleration

Jiayi Han, Liang Du, Yiwen Wu, Xiangguo Zhou, Hongwei Du, Weibo Zheng

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

Comments 14 pages, 9 figures

2501.16786 2025-01-29 cs.CV cs.CL 79%

Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding

Yun Li, Zhe Liu, Yajing Kong, Guangrui Li, Jiyuan Zhang, Chao Bian, Feng Liu, Lina Yao, Zhenbang Sun

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

2412.17304 2025-01-22 cs.AI 79%

On the Feasibility of Vision-Language Models for Time-Series Classification

Vinay Prithyani, Mohsin Mohammed, Richa Gadgil, Ricardo Buitrago, Vinija Jain, Aman Chadha

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

2501.10318 2025-01-20 cs.CV 79%

HiMix: Reducing Computational Complexity in Large Vision-Language Models

Xuange Zhang, Dengjie Li, Bo Liu, Zenghao Bao, Yao Zhou, Baisong Yang, Zhongying Liu, Yujie Zhong, Zheng Zhao, Tongtong Yuan

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

2501.06282 2025-01-14 cs.CL cs.AI cs.HC cs.SD eess.AS 79%

MinMo: A Multimodal Large Language Model for Seamless Voice Interaction

Qian Chen, Yafeng Chen, Yanni Chen, Mengzhe Chen, Yingda Chen, Chong Deng, Zhihao Du, Ruize Gao, Changfeng Gao, Zhifu Gao, Yabin Li, Xiang Lv, Jiaqing Liu, Haoneng Luo, Bin Ma, Chongjia Ni, Xian Shi, Jialong Tang, Hui Wang, Hao Wang, Wen Wang, Yuxuan Wang, Yunlan Xu, Fan Yu, Zhijie Yan, Yexin Yang, Baosong Yang, Xian Yang, Guanrou Yang, Tianyu Zhao, Qinglin Zhang, Shiliang Zhang, Nan Zhao, Pei Zhang, Chong Zhang, Jinren Zhou

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

Comments Work in progress. Authors are listed in alphabetical order by family name

2409.00698 2025-01-08 cs.CV 79%

Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification

Karim El Khoury, Maxime Zanella, Benoît Gérin, Tiffanie Godelaine, Benoît Macq, Saïd Mahmoudi, Christophe De Vleeschouwer, Ismail Ben Ayed

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

Comments Accepted at ICASSP 2025

1. VLM训练与架构 5039 篇

Compositional Kronecker Context Optimization for Vision-Language Models

PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models

TokenFLEX: Unified VLM Training for Flexible Visual Tokens Inference

InPK: Infusing Prior Knowledge into Prompt for Vision-Language Models

SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding

CLIP-Adapter: Better Vision-Language Models with Feature Adapters

MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language Models

PE-CLIP: A Parameter-Efficient Fine-Tuning of Vision Language Models for Dynamic Facial Expression Recognition

LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model

LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models

Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models

Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model

Detecting Offensive Memes with Social Biases in Singapore Context Using Multimodal Large Language Models

Modular Prompt Learning Improves Vision-Language Models

Descriminative-Generative Custom Tokens for Vision-Language Models

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model

When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding

Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models

LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models

Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction

AdaFV: Rethinking of Visual-Language alignment for VLM acceleration

Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding

On the Feasibility of Vision-Language Models for Time-Series Classification

HiMix: Reducing Computational Complexity in Large Vision-Language Models

MinMo: A Multimodal Large Language Model for Seamless Voice Interaction

Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification