视觉大模型 / VLM

Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models

Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Taiga Yamane, Naoki Makishima, Naotaka Kawata, Mana Ihori, Tomohiro Tanaka, Shota Orihashi, Ryo Masumura

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

Comments Accepted by AAAI 2026

MTAttack: Multi-Target Backdoor Attacks against Large Vision-Language Models

Zihan Wang, Guansong Pang, Wenjun Miao, Jin Zheng, Xiao Bai

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

Comments AAAI2026, with supplementary material

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

GridPrune: From "Where to Look" to "What to Select" in Visual Token Pruning for MLLMs

Yuxiang Duan, Ao Li, Yingqin Li, Luyu Li, Pengwei Wang

机构 * Shandong University（山东大学） 纠错

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

Rethinking Visual Information Processing in Multimodal LLMs

Dongwan Kim, Viresh Ranjan, Takashi Nagata, Arnab Dhua, Amit Kumar K C

机构 * Seoul National University（首尔国立大学） ； Amazon（亚马逊） 纠错

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

Xiaoice: Training-Free Video Understanding via Self-Supervised Spatio-Temporal Clustering of Semantic Features

Shihao Ji, Zihui Song

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

Comments This paper is being withdrawn because we have identified a significant error in the implementation of our self-supervised clustering approach. Specifically, our feature aggregation step inadvertently leaked temporal information across frames, which violates the core assumption of our training-free method. We sincerely apologize to the research community

Fine-grained Token Allocation Via Operation Pruning for Efficient MLLMs

Aoming Liu, Reuben Tan, Boqing Gong, Bryan A. Plummer

机构 * Boston University（波士顿大学） ； Microsoft Research（微软研究院） 纠错

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

Remodeling Semantic Relationships in Vision-Language Fine-Tuning

Xiangyang Wu, Liu Liu, Baosheng Yu, Jiayan Qiu, Zhenwei Shi

机构 * Hangzhou International Innovation Institute, Beihang University（北京航空航天大学杭州国际创新研究院） ； School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院） ； Nanyang Technological University（南洋理工大学） ； University of Leicester（莱斯特大学） ； School of Astronautics, Beihang University（北京航空航天大学航天学院） 纠错

专题命中 VLM训练与架构 ：visual question answering(abstract)；分类 cs.CV、cs.AI

Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for Pulmonary Embolism Diagnosis and Report Generation from CTPA

Zhusi Zhong, Yuli Wang, Lulu Bi, Zhuoqi Ma, Sun Ho Ahn, Christopher J. Mullin, Colin F. Greineder, Michael K. Atalay, Scott Collins, Grayson L. Baird, Cheng Ting Lin, Webster Stayman, Todd M. Kolb, Ihab Kamel, Harrison X. Bai, Zhicheng Jiao

机构 * Department of Diagnostic Imaging, Brown University Health（布朗大学健康中心诊断影像科） ； Warren Alpert Medical School of Brown University（布朗大学沃伦·阿尔珀特医学院） ； Department of Biomedical Engineering, Johns Hopkins University School of Medicine（约翰霍普金斯大学医学院生物医学工程系） ； Department of Radiology and Radiological Sciences, Johns Hopkins University School of Medicine（约翰霍普金斯大学医学院放射科） ； Johns Hopkins University Division of Pulmonary and Critical Care Medicine（约翰霍普金斯大学肺科与重症医学科） ； Department of Radiology, University of Colorado School of Medicine（科罗拉多大学医学院放射科） 纠错

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