Awesome Robotics Manipulation · full_paper

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

作者：Chi-Pin Huang, Yunze Man, Zhiding Yu, Min-Hung Chen, Jan Kautz, Yu-Chiang Frank Wang, Fu-En Yang · 单位：NVIDIA · 会议/期刊：CVPR 2026 · 日期：2026-01-14 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / CoT Acceleration

任务规划视觉语言动作潜变量学习机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning figure
AlphaXiv 中文论文页面（可滚动查看）