Juntao Dai

safe reinforcement learning (3) large language model (3) constraint satisfaction (3) policy optimization (3) theorem proving (1) preference learning (1) transfer learning (1) visual reasoning (1) mathematical reasoning (1) ai safety (1) automated reasoning (1) safety alignment (1) reinforcement learning from human feedback (1) formal verification (1) first-order logic (1) policy learning (1) risk minimization (1) reward maximization (1) knowledge distillation (1) policy gradient (1)