
10,000 hrs of RoboCap data. Another big collab between @BitRobotNetwork & @GroundedSI
✓I ❤️ robots, cheap hardware, steam engines, XGBoost, Liverpool FC & SG 🇸🇬 | Plane crash survivor | Building @BitRobotNetwork @frodobots

10,000 hrs of RoboCap data. Another big collab between @BitRobotNetwork & @GroundedSI

Imitation learning has enabled amazing robot capabilities, empowered in part by diffusion or flow-matching policies. These generative models outperform direct action prediction, but come at a cost: they are often slower and harder to train. The performance gap is usually explained by better support of multimodality, but @yuchen010807 and @maojiayuan say this is wrong: that instead, the advantage generative policies have over pure regression is better explained by state-depended variation and by heavier-than-usual Gaussian “tails.” They propose HT-Policy, which learns an input-dependent residual scale and uses it to reduce the effect of these long-tail data example resulting in reduced influence of these long-tail examples on training, allowing you to train regression models that are competitive with flow matching. To learn more, watch Episode #117 of RoboPapers, with @chris_j_paxton and @ruijie_sg!


Last week we took the keynote stage at @corl_conf. Our mission: more robots in the real world, evaluations at scale to show what policies can do today, and all of it open-sourced. Catch RoboColosseum's founding member @DJiafei’s talk ↓

Never would have thought that we would have this community formed around @RoboPapers when @chris_j_paxton & I first started the pod. Awesome to have @DJiafei @ruijie_sg joined this journey too!

Thanks @sippeyxp ! This is super useful

You can benchmark an LLM from a laptop, but robot policies need real hardware / environments for testing. Yesteday, @pepijn2233 shared how @huggingface is releasing every RoboColosseum eval rollout, including failures. What a great to wrap up @corl_conf!

Full episode dropping soon! Geeking out with @yuchen010807 and @maojiayuan on Residual Modeling Closes the Regression and Generative Policy Gap in Robot Learning projects.thelabone.org/regre… Co-hosted by @chris_j_paxton @ruijie_sg



Tomorrow at @corl_conf: our SPIN workshop! #CoRL2026 🧒🤖 For the first time: a LIVE Child–Robot Challenge with @JitendraMalikCV @DJiafei @micoolcho @ZoharRimon @YiruHelenWang James Ni, Frank Hu, @k7agar @hq_fang, and @SharpaRobotics at 9:40 AM! Plus all-star talks by Georgia Chalvatzaki @GeorgiaChal, Jeannette Bohg @leto__jean, Yunzhu Li @YunzhuLiYZ & Mike Rabbat @michaelrabbat. 📍 8:30 AM, JW Marriott 208 spin-workshop.github.io

Introducing RoboCap-10k. 10,000 hours of open egocentric data with metric hand / head pose on every frame. Captured on RoboCap across 11 countries and 21 industries. GroundedAPI produces 3D enrichment giving robot policies high-fidelity action grounding. with @BitRobotNetwork @huggingface @rerundotio ↓

@pepijn2233 from @LeRobotHF explains why scaling in the wild at @RoboColosseum is very important for robotics and pushing physical AI progress.

10,000 hours of open egocentric data with SOTA 3D head and hand tracking from @GroundedSI are now available 🤗 RoboCap-10k spans 21 industries in 5 continents with 619 real, paid work tasks all using 6-camera/dual IMU RoboCap hardware. Explore the dataset and research ↓

Full episode dropping soon! Geeking out with @yuchen010807 and @maojiayuan on Residual Modeling Closes the Regression and Generative Policy Gap in Robot Learning projects.thelabone.org/regre… Co-hosted by @chris_j_paxton @ruijie_sg
