Hanze Dong

large language model (2) generative modeling (1) knowledge distillation (1) representation learning (1) reinforcement learning (1) feature learning (1) offline reinforcement learning (1) policy optimization (1) domain adaptation (1) bayesian inference (1) model calibration (1) object detection (1) preference learning (1) weakly supervised learning (1) langevin dynamics (1) data augmentation (1) multimodal learning (1) convergence analysis (1) distributed learning (1) stochastic optimization (1)