HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model

作者：Jiaming Liu, Hao Chen, Pengju An, Zhuoyang Liu, Renrui Zhang, Chenyang Gu, Xiaoqi Li, Ziyu Guo, Sixiang Chen, Mengzhen Liu, Chengkai Hou, Mengdi Zhao, KC alex Zhou, Pheng-Ann Heng, Shanghang Zhang · 单位：State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University; Beijing Academy of Artificial Intelligence (BAAI); CUHK · 会议/期刊：arXiv preprint 2025 · 方向：高效动作解码 / 令牌优化 · 发布日期：2025-03-13