π₀.₅ hits 64% on LIBERO-Long with just 25 demos vs GR00T's 52% with 100
rahulshivchand · x · 2026-11-11
A repeated thread post: π₀.₅ is the most sample-efficient VLA across all four LIBERO tasks, needing 2-5× fewer demos than GR00T N1.7; on LIBERO-Long it reaches 64% with 25 demos vs N1.7's 52% with 100. Overlaps with other thread posts.
More from Embodied
- Beni robot, #1 personal robot on Kickstarter, officially launches with self-recovery and 4K60 — Scobleizer · 2026-11-11
- Berkeley's Social Humanoid teaches Unitree G1 socially responsive interaction — berkeley_ai · 2026-11-11
- Robotics is not solved: frontier models are ~6 orders of magnitude off real assembly lines — ZeeshanZiaML · 2026-11-11
- MacBooks do have a hinge angle sensor—verified with Codex, prompt included — lipeng0820 · 2026-11-11
- DynaRobotics robot demo at CoRL sparks 'I want one at home' reactions — JasonMa2020 · 2026-11-11
- Humanoid Factory Deploy Stalls: Teleop Intervention Every 6 Minutes After 15 Weeks — ZeeshanZiaML · 2026-11-11