NVIDIA open-sources MotionBricks: 350K motion skills at 15,000 FPS, 2ms latency
aftahi_ai · x · 2026-10-21
NVIDIA introduced MotionBricks, an open-source framework for scalable real-time character and humanoid motion generation. A single neural model produces over 350,000 motion skills running at 15,000 FPS with just 2 ms latency — no motion capture or traditional rigging required. Key features include intuitive smart primitives for scene authoring and integration with NVIDIA's GR00T robotics stack, targeting both animation and robotics use cases.
More from Embodied
- Robotics startup launches Deployments to serve fine-tuned HF checkpoints to robots in real time — arnie_hacker · 2026-10-21
- Amazon FAR's FIBER uses action-aligned latent planning to let Unitree G1 open doors and carry boxes — ChongZzZhang · 2026-10-21
- Sentdex trains robots to go from lying down to a half kneel, eyeing a full stand — Sentdex · 2026-10-21
- NVIDIA Cosmos3-H-Dreams: Generative Simulation Brings Clinical Surgery to Life — Hugging Face Blog · 2026-10-21
- FLoTS-SLAM uses optical-flow residuals to hit 0.73 DM-IoU in dynamic monocular SLAM — zhenjun_zhao · 2026-10-21
- Plato ring launches at $199 to turn near-silent speech into AI commands — TinfoilTricorn · 2026-10-21