Jianquan Li

large language model (4) knowledge distillation (3) zero-shot learning (2) reinforcement learning from human feedback (2) supervised fine-tuning (2) pairwise comparison (2) probabilistic modeling (1) benchmark evaluation (1) contrastive learning (1) natural language generation (1) intent classification (1) graph attention network (1) bayesian updating (1) generative model (1) cross-lingual transfer (1) text-to-image model (1) reward model (1) decision boundary (1) bayesian inference (1) reinforcement learning (1)