Awesome Robotics Manipulation · full_paper

ReViP: Reducing False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance

arXiv · 2026-01-23 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - Text Goal Extraction

辅助任务VLA机器人学习
新标签打开 AlphaXiv新标签打开 Paper
ReViP: Reducing False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance figure
AlphaXiv 中文论文页面（可滚动查看）