Let humans be humans, and let robots be robots. Our paper at
#ICRA2026, X-Diffusion views human data as noisy counterparts of robot data.
Building on the Ambient Diffusion framework, we selectively integrate human data in the high-noise timesteps of diffusion policy training 👇
Teaching a robot shouldn't require humans to act like robots.
Human demonstrations contain valuable signal for robot manipulation, but they aren’t directly transferable to robots.
X-Diffusion learns from noisy human demonstrations while staying within the robot’s capabilities.