Xiyao Wang

vision-language model (3) modality alignment (2) model-based reinforcement learning (2) sample efficiency (2) domain generalization (2) policy learning (2) preference learning (1) visual reinforcement learning (1) domain adaptation (1) large multimodal model (1) instruction following (1) preference optimization (1) reinforcement learning from human feedback (1) model alignment (1) state representation (1) continuous control (1) knowledge distillation (1) distribution shift (1) benchmark evaluation (1) contrastive learning (1)