Geyang Guo

large language model (3) reinforcement learning (1) preference learning (1) model evaluation (1) text generation (1) parameter efficient (1) structured sparsity (1) language model (1) parameter-efficient fine-tuning (1) parameter efficient fine-tuning (1) inference scalability (1) cultural awareness (1) human preference (1) sparse fine-tuning (1) training strategy (1) adapter fusion (1) model compression (1) unified library (1)