Jiaming Ji

large language model (11) reinforcement learning from human feedback (6) safe reinforcement learning (5) constraint satisfaction (4) policy optimization (4) human preference (3) safety alignment (3) multimodal large language model (3) human preference alignment (2) preference learning (2) value alignment (2) benchmark evaluation (2) nash equilibrium (2) reward model (2) responsible ai (2) reward modeling (2) preference optimization (2) ai safety (2) language model alignment (2) helpful assistant (2)