RoboTok: Rice and NVIDIA's internet-scale engine retrieves human demo videos for robot learning
CSProfKGD · x · 2026-09-05
Researchers at Rice University with NVIDIA introduce RoboTok, an internet-scale data engine that represents videos as canonicalized 3D hand trajectories in actor-centered reference frames, enabling viewpoint-invariant retrieval of manipulation-relevant web videos as training demonstrations. It outperforms existing robot-data retrieval approaches on benchmarks and improves downstream dexterous policy success, with paper, code and models released.
Related event: Rice and NVIDIA Unveil RoboTok, a Web-Scale Data Engine for Robots(4 posts)→
More from Embodied
- A classic world model (s, a → s′) acting as a neural MuJoCo simulator — yshan2u · 2026-10-23
- Gen-HumanWholeBody: open 600-hour whole-body manipulation dataset for robots — AdinaYakup · 2026-10-23
- Stanford releases free 520-page robot autonomy course book and lectures — lukas_m_ziegler · 2026-10-23
- Pony.ai and inDrive target Kazakhstan robotaxis by 2027 as Nvidia GPU deployments expand — VectorWireAI · 2026-10-23
- MambaAct cuts VLA robot policy latency up to 59% while lifting success rates — MBZUAI · 2026-10-23
- Founders tour Greater Bay Area: a year of hardware prototyping done in 3 months — DominiqueCAPaul · 2026-10-23