Awesome Robotics Manipulation · full_paper

Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations

作者：Chancharik Mitra, Yusen Luo, Raj Saravanan, Dantong Niu, Anirudh Pai, Jesse Thomason, Trevor Darrell, Abrar Anwar, Deva Ramanan, Roei Herzig · 单位：Carnegie Mellon University, University of Southern California, University of California, Berkeley, MIT-IBM Watson AI Lab · 会议/期刊：arXiv · 日期：2025-11-27 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models for Generalization / Few-shot Learning

数据需求量大模仿学习视觉语言动作泛化机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations figure
AlphaXiv 中文论文页面（可滚动查看）