←
Michael Cho ✈️ CoRL3,142 posts
Michael Cho ✈️ CoRL avatar✓

Michael Cho ✈️ CoRL ✓

@micoolcho

I ❤️ robots, cheap hardware, steam engines, XGBoost, Liverpool FC & SG 🇸🇬 | Plane crash survivor | Building @BitRobotNetwork @frodobots

◷ Joined May 2010▧ 340 Photos and videos
RoboPapers avatar
⟳ Michael Cho ✈️ CoRL retweeted
RoboPapers@RoboPapers·20h

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!

58:12
Michael Cho ✈️ CoRL avatar
Michael Cho ✈️ CoRL@micoolcho·22h

Solana Breakpoint is the one time in a yr where I go update my priors on crypto. The industry is maturing quickly, with all the pros/cons of growing up. Hear @toly debate SOL as money vs @mert Refreshing break from my typical feed filled wjth world model vs VLA vs agentic robotics vs....

Post attachment
RoboColosseum avatar
⟳ Michael Cho ✈️ CoRL retweeted
RoboColosseum@RoboColosseum·Nov 17

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 ↓

4:27
RoboColosseum avatar
⟳ Michael Cho ✈️ CoRL retweeted
RoboColosseum@RoboColosseum·Nov 12

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!

Post attachment
Roei Herzig avatar
⟳ Michael Cho ✈️ CoRL retweeted
Roei Herzig@roeiherzig·Nov 12

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

Post attachmentPost attachment
Grounded Superintelligence avatar
⟳ Michael Cho ✈️ CoRL retweeted
Grounded Superintelligence@GroundedSI·Nov 11

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 ↓

1:18
LeRobot avatar
⟳ Michael Cho ✈️ CoRL retweeted
LeRobot@LeRobotHF·Nov 11

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 ↓

1:18
Michael Cho ✈️ CoRL avatar
Michael Cho ✈️ CoRL@micoolcho·Nov 11

Taku is sooo cool! It just works! Congrats to @DynaRobotics on another great showcase!

1:57
0:41