IROS

PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding

PD-VLA：通过并行解码加速集成动作分块的视觉-语言-动作模型

Wenxuan Song, Jiayi Chen, Pengxiang Ding, Han Zhao, Wei Zhao, Zhide Zhong, Zongyuan Ge, Zhijun Li, Donglin Wang, Jun Ma, Lujia Wang, Haoang Li

AI总结 PD-VLA通过并行解码框架提升视觉-语言-动作模型在动作分块中的效率与性能

Comments Accepted by IROS 2025, updated results on LIBERO