CrossBFM distills shared behavior latent space across humanoid robots

CrossBFM introduces a cross-embodiment behavior foundation model that distills a shared behavior latent space, letting one instruction drive multiple humanoid robots while cutting training cost from hundreds of GPU hours to under one hour.

2026-09-30 ~ 2026-10-01 · 2 related posts

• CrossBFM Distills a Shared Behavior Space Across Humanoid Robots in Under One GPU-Hour — Tan-Dzung Do · 2026-09-30
• CrossBFM distills a shared latent behavior space across humanoid robots in under one GPU-hour — Jan_R_Peters · 2026-10-01