Meituan Releases MR0, a Desktop-Manipulation VLA Foundation Model
What happened
Meituan's robotics team has released Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied agent system for fixed-base desktop manipulation. Its training data consists of 147 million vision-language samples and 15,060 hours of robot trajectories covering 12 embodiments. The team reports that MR0 achieves a 93.6% success rate on RoboTwin 2.0 and ranks fifth on the RoboDojo VLA track; under the same HG-DAgger post-training conditions, MR0's average success rate and progress score on three real-robot tasks are both higher than those of π0.5. In addition, CFG-DAgger trained with Rollback data reaches a 70% success rate and a 0.90 progress score on the network-cable insertion task.
AI 根据报道生成 · 2 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.ROMeituan Robotics releases MR0 desktop manipulation vision-language-action foundation model
The Meituan Robotics team has released Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for fixed-base desktop manipulation. Its training data includes 147 million vision-language samples and 15,060 hours of robot trajectories covering 12 embodiments.
Activity for this event
- Current
- 3
- Peak
- 10Nov 9 14:00
- Past 24 hours
- -50%
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.