Awesome Robotics Manipulation · full_paper

MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation

arXiv · 2026-03-26 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D LLM-based Vision Language Action Models

VLADiffusion Policy语言条件机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation figure
AlphaXiv 中文论文页面（可滚动查看）