Junming Yang

model compression (1) representation learning (1) offline reinforcement learning (1) transfer learning (1) knowledge distillation (1) multimodal learning (1) visual reinforcement learning (1) model-based reinforcement learning (1) value estimation (1) vision language model (1) world model (1) contrastive language-image pretraining (1) multimodal benchmark (1) model refinement (1) capability assessment (1) perception stage (1) reasoning stage (1)