Awesome Robotics Manipulation · full_paper

VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation

arXiv · 2025-11-21 · Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models

3D 表征VLA机器人学习操作
新标签打开 AlphaXiv新标签打开 Paper
VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）