Robotics & World Models Reading Club 13: HumanEgo: Train Robot Policy from 30 min Egocentric Videos — SF 0620

Robotics & World Models Reading Club 13: HumanEgo: Let Everyone Train Robot Policy from 30 min Human Egocentric Videos — SF 0620 A high-signal reading group for AI researchers & builders pushing the frontiers of robotic world models, WAMs, and embodied intelligence . In our previous sessions, we brought together researchers and engineers from Boston Dynamics, Google DeepMind, NVIDIA, Stanford, UC Berkeley, Dyna, Physical Intelligence, Tesla, Generalist, Rhoda AI, and leading Bay Area robotics startups. Hosted by Junfan Zhu & Aurora Feng . Supported by Neural Motion , a universal cross-embodiment data representation layer for embodied AI. ​​​Reading Club 13's Core Theme HumanEgo: Let everyone train their own robot policy from 30 minutes of human egocentric videos. Keynote by Zhi (Leo) Wang (Amazon FAR, UMD) tx-leo.github.io Vision-language models leverage the internet as a vast learning resource, yet robot policy learning remains bottlenecked by teleoperation — expensive, hardware-coupled, and confined to the lab. This talk argues that human egocentric video can serve as a new data…