Yixia Li

large language model (6) instruction tuning (2) model compression (2) reinforcement learning (2) language model (2) singular value decomposition (2) computer vision (1) text generation (1) policy optimization (1) chain-of-thought reasoning (1) in-context learning (1) vision-language alignment (1) instruction following (1) model merging (1) few-shot learning (1) low-rank approximation (1) data augmentation (1) synthetic data generation (1) sparse optimization (1) sparse representation (1)