Xingtai Lv

large language model (3) language model (2) supervised fine-tuning (2) reinforcement learning from human feedback (2) preference optimization (2) parameter efficient fine-tuning (2) model compression (2) instruction tuning (1) knowledge transfer (1) transfer learning (1) efficient computing (1) model fusion (1) model adaptation (1) language model alignment (1) attention mechanism (1) proximal gradient (1) policy learning (1) scalable training (1) reward model (1) markov decision process (1)