Furong Huang Lab brings six human-video-to-robot works to CoRL 2026
furongh · x · 2026-11-09
Furong Huang Lab (University of Maryland) shared its CoRL 2026 lineup, unified by the vision of robots watching humans perform tasks, remembering what matters, and adapting.
- EgoScale: scaling dexterous manipulation with large-scale egocentric human data (Oral + Poster).
- μ₀: a scalable world model built on 3D interaction traces (Poster).
- HumanEgo: zero-shot robot learning from minutes of egocentric video (Workshop).
- Dex-One2Many: dexterous manipulation from a single human demo (Late Breaking Results + Workshop Oral).
- What to Attend, What to Keep: skill-conditioned visuospatial-tactile representations with progress-guided event memory (Workshop).
- Fly-by-Code / Guava: embodied coding agents for aerial manipulation, and distilling frontier VLMs into a compact robotic agent (Workshops).
Plus an invited talk by Ruijie Zheng at the Scaling Human2Robot Workshop.
More from Embodied
- iPad mini 8 hands-on: 1g heavier and a third the price of iPhone Air, 60Hz capped — oran_ge · 2026-11-09
- Dooder puts an AI with on-device hearing and voice entirely on the Apple Watch — breagz · 2026-11-09
- Stanford team teaches an AI agent a pool table's physics by letting it take real shots (CoRL) — drmapavone · 2026-11-09
- 3D animated teardown explains how the open-source local-AI microduck robot works — Individual-Dot5488 · 2026-11-09
- Three CMU robot papers spotlighted at CoRL 2026: memory, vision-touch steering, world models — pabbeel · 2026-11-09
- CoRL 2026 balloons to 5,000+ attendees; Princeton PRISM brings 6 robotics papers including oral MolmoB0T — shahdhruv_ · 2026-11-09