NVIDIA releases MotionBricks: real-time humanoid motion generation at 15,000 FPS with 2ms latency
_akhaliq · x · 2026-10-26
NVIDIA has released MotionBricks on Hugging Face, a real-time generative motion model for humanoid robots and characters.
Key specs: trained on 350k+ motion clips, it reaches 15,000 FPS inference with only 2ms latency, generating full-body motion sequences in real time. The demo images show motion generation for game-style character scenes and humanoid robot behaviors including carrying, fall recovery, and balance.
More from Embodied
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27
- ROS names Alejandro Hernández Cordero new project lead, eyes 2027 release — ___Mufasaa · 2026-10-27
- ROS Meetup coming to Google's NYC office Oct 29 with speakers from Tangent, Cohesive Robotics, Intrinsic — kscottz · 2026-10-27