Shujian Zhang

offline reinforcement learning (2) preference optimization (2) diffusion model (2) stochastic attention (2) variational inference (2) text generation (2) instruction following (2) model-based reinforcement learning (2) uncertainty estimation (2) ordinary differential equation (2) adversarial robustness (2) reinforcement learning from human feedback (2) preference learning (1) prototype learning (1) policy optimization (1) multi-label learning (1) bayesian inference (1) probabilistic modeling (1) domain adaptation (1) data augmentation (1)