NVIDIA GEAR researcher to present GR00T 2 Turbo world action models for humanoids at Penn GRASP
zhengyiluo · x · 2026-11-18
Zhengyi (Zen) Luo of NVIDIA GEAR Lab will speak at Penn's GRASP seminar on Wednesday, Nov 18, 3–4 pm ET, on "From Motion Tracking to World Action Models for Humanoids".
The talk traces the team's evolution from SONIC human motion tracking to world action models with GR00T 2 Turbo. The poster shows GR00T 2 Turbo driving a G1 humanoid cleaning up a spill and putting a can in a bin in a kitchen scene. In-person at Levine 307 with a Zoom livestream available.
More from Embodied
- Apple open-sources FastFrames: two-step diffusion for interactive-latency 480p video — _akhaliq · 2026-11-18
- Starkey's AI Hearing Aids Top $1B in Sales: 'The Ear Is the New Wrist' — BrandonSawalich · 2026-11-18
- binarybits: Tesla Robotaxi faces the same city-by-city slog as Waymo — binarybits · 2026-11-18
- California bans Waymo autonomous vehicles from state freeways — armcat · 2026-11-18
- Teleoperated humanoid robot TAU cooks a burger in a real kitchen — Distinct-Question-16 · 2026-11-18
- Ropedia Xperience 2: 1,500+ real scenes for scaling physical AI training data — _akhaliq · 2026-11-18