Chenglong Wang

knowledge distillation (5) fake audio detection (5) catastrophic forgetting (4) model compression (4) audio deepfake detection (4) continual learning (4) reward model (3) code generation (3) machine translation (3) neural machine translation (3) proximal policy optimization (2) model ensemble (2) large language model (2) transfer learning (2) efficient computing (2) preference optimization (2) reinforcement learning (2) language model alignment (2) reinforcement learning from human feedback (2) transformer model (2)