NSF Robotics Meeting Workshop: Four Researchers on Learning, Generalization and Physical Intelligence
YuXiang_IRVL · x · 2026-09-26
At the NSF FRR Robotics Annual Meeting, YuXiang co-organized a mini-workshop on robot learning featuring four invited talks:
- Nadia Figueroa (UPenn): composable dynamical-system skills for interactive manipulation beyond more data
- Guanya Shi (CMU): humanoid learning from human data with physics grounding
- Erdem Biyik (USC): robot learning from everyday human feedback
- Wanxin Jin (ASU): physics as the backbone of dexterity — scalable contact simulation and physics-grounded learning
A panel discussion followed on the limits of current robot learning, the role of representations and world models, and what it takes to build more adaptable, generalizable robots.
More from Embodied
- iPhone won't dominate forever: DJI Pocket vs iPhone shows form factors win — alexmacgregor__ · 2026-09-26
- Meta Connect 2026: Zuckerberg unveils new AI glasses and VR glasses — FinanceYF5 · 2026-09-26
- Trossen dual robot arms strike a match fully autonomously, unveils 2026 Physical AI lineup — YuXiang_IRVL · 2026-09-26
- Scoble: robot revolution is here, humanoids 2-7 years out and a funding wave is coming — Scobleizer · 2026-09-26
- Prediction: DeepSeek V4 Flash-scale real-time robot vision models coming within weeks — zhaoran_wang · 2026-09-26
- Déjà View, a NeurIPS Oral: one looped transformer block matches 3D reconstruction models 8-10x its size — ZGojcic · 2026-09-26