Norman Di Palo

one-shot learning (1) sample efficiency (1) few-shot learning (1) imitation learning (1) embodied ai (1) trajectory optimization (1) model-based reinforcement learning (1) denoising autoencoder (1) motion control (1) diffusion policy (1) visual imitation learning (1) coarse-to-fine learning (1) multi-stage task (1) in-context imitation learning (1) keypoint action token (1)