Kaixiang Lin

large language model (3) imitation learning (2) zero-shot learning (1) few-shot learning (1) in-context learning (1) anomaly detection (1) sequential decision making (1) task-oriented dialogue (1) self-supervised learning (1) knowledge distillation (1) text classification (1) conversational ai (1) prompt engineering (1) code generation (1) sample efficiency (1) model merging (1) feature representation (1) instruction tuning (1) distribution matching (1) reinforcement learning (1)