Lichang Chen

large language model (7) instruction tuning (4) knowledge distillation (2) data selection (2) benchmark evaluation (2) chain of thought (2) visual question answering (1) human perception (1) few-shot learning (1) in-context learning (1) question answering (1) multimodal learning (1) code generation (1) visual reasoning (1) data augmentation (1) performance optimization (1) loss landscape (1) natural language understanding (1) reinforcement learning from human feedback (1) adversarial training (1)