Xiaojian Ma

imitation learning (4) instruction following (2) embodied ai (2) large language model (2) scene understanding (2) visual grounding (2) vision-language model (2) energy-based model (2) latent diffusion (2) reinforcement learning (2) foundation model (2) bayesian learning (1) image segmentation (1) transfer learning (1) variational inference (1) policy optimization (1) continual learning (1) generative modeling (1) visual question answering (1) autoregressive transformer (1)