Elmo Aphiwetsa

Introducing EgoVerse: an ecosystem for robot learning from egocentric human data. Built and tested by 4 research labs + 3 industry partners, EgoVerse enables both science and scaling 1300+ hrs, 240 scenes, 2000+ tasks, and growing Dataset design, findings, and ecosystem 🧵

EgoBridge will be featured at NeurIPS on Wednesday Dec 3 at Exhibit Hall C,D,E #2211 at 4:30 p.m. PST — 7:30 p.m. PST! Come check it out!

Robots struggle to learn new skills from human videos. Why? We found that naive co-training produces disjoint distributions. Our EgoBridge (NeurIPS’25) extends Optimal Transport to align human-robot latents, improving success by 44% and generalization to human-only tasks!🧵

Can we scale up mobile manipulation with egocentric human data? Meet EMMA: Egocentric Mobile MAnipulation EMMA learns from human mobile manipulation + static robot data — no mobile teleop needed! EMMA generalizes to new scenes and scales strongly with added human data. 1/9