Xuanlin Li

zero-shot classification (2) vision-language model (2) reinforcement learning (1) multi-task learning (1) action recognition (1) policy optimization (1) domain generalization (1) embodied ai (1) variational inference (1) policy gradient (1) knowledge distillation (1) chain-of-thought reasoning (1) point cloud (1) multi-modal learning (1) policy learning (1) robotic manipulation (1) out-of-distribution generalization (1) trajectory optimization (1) model-based reinforcement learning (1) zero-shot learning (1)