From Knowing to Doing Precisely: A General Self-Correction and Termination Framework for VLA models

作者：Wentao Zhang, Aolan Sun, Wentao Mo, Xiaoyang Qu, Yuxin Zheng, Jianzong Wang · 单位：Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · 会议/期刊：ICASSP 2026 · 日期：2026-02-02 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Robustness / Failure Analysis & Recovery