Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think
微调视觉-语言-动作模型所需的层数比你想象的少
Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha, Khoa Vo, Philip Lund Møller, Quang T. Nguyen, Long Dinh, Tung M. Luu, Tuan Dam, Vu Duong, Trung Le, Nghi D. Q. Bui, Minh Vu, Tran Nguyen Le, An Thai Le, Ngan Le, Daniel Sonntag, James Zou, Jan Peters, Duy M. H. Nguyen, Ngo Anh Vien
机构
*
Center for AI Research, VinUniversity(VinUniversity人工智能研究中心)
;
VinRobotics
;
University of Arkansas(阿肯色大学)
;
Technical University of Denmark(丹麦技术大学)
;
Hanoi University of Science and Technology(河内科技大学)
;
KAIST(韩国科学技术院)
;
Monash University(莫纳什大学)
;
Oldenburg University(奥尔登堡大学)
;
DFKI(德国人工智能研究中心)
;
University of Stuttgart(斯图加特大学)
;
IMPRS-IS(国际马克斯·普朗克智能系统研究学院)
;
Stanford University(斯坦福大学)
;
Technische Universität Darmstadt(达姆施塔特工业大学)
机构
*
Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology(韩国科学技术院赵春植移动研究生院)
;
Department of Mechanical Engineering, Hanyang University(汉阳大学机械工程系)
;
Narnia Labs(纳尼亚实验室)
CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning
CapRL++:基于可验证奖励的统一强化学习用于密集图像和视频描述生成
Penghui Yang, Long Xing, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Yibin Wang, Yujie Zhou, Jiazi Bu, Jianze Liang, Qidong Huang, Jiaqi Wang, Feng Wu, Dahua Lin
机构
*
Tsinghua University(清华大学)
;
University of Science and Technology of China(中国科学技术大学)
;
Microsoft(微软)
;
Shanghai AI Laboratory(上海人工智能实验室)
;
Shanghai Innovation Institute(上海创新研究院)
;
Alibaba Cloud(阿里云)
;
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(abstract);visual language model(abstract);分类 cs.CV
MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities
MODUS:仅解码器的多模态任意到任意建模
Mingqiao Ye, Zhaochong An, Zhitong Gao, Xian Liu, François Fleuret, Chuan Li, Amir Zadeh, Serge Belongie, Afshin Dehghan, Jesse Allardice, David Mizrahi, Oğuzhan Fatih Kar, Roman Bachmann, Amir Zamir
CommentsThis is a preprint version. A shorter version of this paper has been accepted for presentation and publication in the post-workshop proceedings of the 8th International Workshop on eXplainable Knowledge Discovery in Data Mining (XKDD 2026), co-located with ECML PKDD 2026. The appendix is included only in this preprint and is not part of the peer-reviewed proceedings paper
PhysV2A: Reachability-Gated and Semantic-Mask-Constrained Feasibility Completion for Video-to-Robot Manipulation
PhysV2A:用于视频到机器人操作的可达性门控和语义掩码约束的可行性完成
Haohui Huang, Junda Duan, Tao Teng, Chenguang Yang
机构
*
School of Automation, Guangdong University of Technology(广东工业大学自动化学院)
;
University of Liverpool(利物浦大学)
;
Department of Computing, The Hong Kong Polytechnic University(香港理工大学计算学系)
机构
*
School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen(人工智能学院,香港中文大学(深圳))
;
School of Computing, University of Portsmouth(计算学院,朴茨茅斯大学)
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
TEVI: 基于稀疏自编码器的文本条件视觉表示编辑以改进视觉-语言对齐
Sweta Mahajan, Sukrut Rao, Jiahao Xie, Alexander Koller, Bernt Schiele
机构
*
Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany(马克斯·普朗克研究所信息学院,萨尔兰信息学院,德国萨尔布吕肯)
;
Department of Language Science and Technology, Saarland University, Saarbrücken, Germany(语言科学与技术系,萨尔兰大学,德国萨尔布吕肯)