Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation
Overview
This paper presents Meituan-Robotics-0 (MR0), a vision-language-action foundation model designed for stationary-base desktop manipulation.
Generated from attributed reports · Updated 20 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · vision-language samples: 147000000 other · Basis not reported
“arXiv:2611.08577v1 Announce Type: new Abstract: We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete ac”
Exact source · revision 1Source owner not reported
Reported quantity · robot trajectories hours: 15060 hours · Basis not reported
“arXiv:2611.08577v1 Announce Type: new Abstract: We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete ac”
Exact source · revision 1Source owner not reported
Reported quantity · progress score Ethernet insertion: 0.9 other · Basis not reported
“MR0 achieves higher average success rate and progress score than $\pi_{0.5}$ across three real-robot tasks. On Ethernet insertion, CFG-DAgger trained with Rollback data reaches 70% success and a progress score of 0.90. Qualitative agent deployments demonstrate cross-task event retrieval and recovery from temporarily unsatisfied task conditions.”
Exact source · revision 1Source owner not reported
Dataset · modalities: vision-language-action
“arXiv:2611.08577v1 Announce Type: new Abstract: We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete ac”
Exact source · revision 1Source owner not reported
Dataset · embodiments: 12 embodiments
“arXiv:2611.08577v1 Announce Type: new Abstract: We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete ac”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalMeituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation
This paper presents Meituan-Robotics-0 (MR0), a vision-language-action foundation model designed for stationary-base desktop manipulation.
Event coverage history
Current attention 6·Peak within the comparable range 10（2026-11-09 06:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).