Awesome Robotics Manipulation · full_paper

Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models

作者：Riccardo Andrea Izzo, Gianluca Bardaro, Matteo Matteucci · 单位：Department · 会议/期刊：arXiv · 日期：2026-03-05 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies

视觉语言动作机器人学习
新标签打开 AlphaXiv新标签打开 Paper
Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）