Accelerating vision-language-action model integrated with action chunking via parallel decoding

作者：Wenxuan Song, Jiayi Chen, Pengxiang Ding, Han Zhao, Wei Zhao, Zhide Zhong, Zongyuan Ge, Zhijun Li, Donglin Wang, Jun Ma, Lujia Wang, Haoang Li · 单位：Hong Kong University of Science and Technology, University of Hong Kong, Westlake University,AI Division, School of Engineering,Hangzhou,China, Westlake University, Monash University,Department of Data Science & AI,Melbourne,Australia, Monash University, Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China, Harbin Institute of Technology · 会议/期刊：IROS 2025 · 方向：高效动作解码 · 发布日期：2025-03-04