SIWEI CHEN

feature alignment (1) causal inference (1) deep reinforcement learning (1) contrastive learning (1) imitation learning (1) variational inference (1) multimodal learning (1) policy learning (1) inverse reinforcement learning (1) mutual information (1) continuous control (1) model-based reinforcement learning (1) robot manipulation (1) vision-language model (1) temporal knowledge graph (1) large vision-language model (1) vision encoder (1) model-based reasoning (1) differentiable physics (1) cognitive alignment (1)