DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation

作者：Xiongfeng Peng, Jiaqian Yu, Dingzhe Li, Yixiang Jin, Lu Xu, Yamin Mao, Chao Zhang, Weiming Li, Sujin Jang, Dongwook Lee, Daehyun Ji · 单位：Samsung AI Center, DS Division, South Korea Sujin Jang is also with Hanyang University ERICA, South Korea · 会议/期刊：ICRA 2026 · 日期：2026-03-01 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D LLM-based Vision Language Action Models