Xingyu Lin

robotic manipulation (2) deformable object manipulation (2) cloth manipulation (2) policy learning (2) self-supervised learning (2) reinforcement learning (2) partial observability (2) occlusion reasoning (2) chain-of-thought reasoning (1) preference learning (1) sim-to-real transfer (1) multi-task learning (1) mathematical reasoning (1) point cloud (1) hierarchical learning (1) policy optimization (1) visual reinforcement learning (1) adversarial training (1) gradient descent (1) pose estimation (1)