Xi-Lai Liu

CAP: Continuously Adaptive Perception-Blind Humanoid Locomotion via Learned Denoising

CAP is proposed, a single-stage humanoid locomotion policy that recovers this signal with a perceptive world-model encoder trained as a learned denoiser to reconstruct clean depth from a corrupted input, together with a co-active proprioceptive variational encoder that supplies depth-free body-state information.