Awesome Robotics Manipulation · full_paper

Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning

arXiv · 2026-02-08 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - Text Goal Extraction

辅助任务VLALatent Learning机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning figure
AlphaXiv 中文论文页面（可滚动查看）