Abstract: Robot manipulation succeeds only when perception preserves the aspects of a scene that matter for action. Yet most robot learning pipelines still rely on visual encoders pre-trained for static recognition or vision-language alignment, leaving motion understanding to downstream policies....
Abstract: Egocentric human videos provide a scalable source of manipulation demonstrations; however, deploying them on robots requires active viewpoint control to maintain task-critical visibility, which human viewpoint imitation often fails to provide due to human-specific priors. We propose Ego...
Abstract: Maximum entropy reinforcement learning (MaxEnt-RL) enables robust exploration, yet practical implementations often restrict policies to simple Gaussians. While recent MaxEnt-RL approaches incorporate expressive generative policies via weighted supervised learning, they use importance sa...