Rui Zheng

large language model (9) language model (5) reinforcement learning from human feedback (5) reinforcement learning (5) adversarial attack (4) reward model (4) text classification (4) preference alignment (3) reward modeling (3) contrastive learning (3) adversarial training (3) adversarial defense (3) code generation (3) model robustness (3) language model alignment (3) continual learning (2) transfer learning (2) distribution shift (2) out-of-distribution generalization (2) adversarial robustness (2)