Awesome Robotics Manipulation · full_paper

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

ICLR 2026 · 2025-10-14 · Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models

3D 表征VLA机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model figure
AlphaXiv 中文论文页面（可滚动查看）