Jiaming Ji

large language model (9) reinforcement learning from human feedback (6) safe reinforcement learning (5) constraint satisfaction (4) policy optimization (4) human preference (3) safety alignment (3) preference learning (2) helpful assistant (2) value alignment (2) language model alignment (2) benchmark evaluation (2) multimodal large language model (2) responsible ai (2) reward modeling (2) ai safety (2) question answering (1) knowledge distillation (1) constraint optimization (1) risk management (1)