Yige Yuan

language model alignment (2) reinforcement learning (1) imitation learning (1) domain generalization (1) domain adaptation (1) model calibration (1) direct preference optimization (1) self-supervised learning (1) data augmentation (1) chain-of-thought reasoning (1) test-time adaptation (1) instruction following (1) covariate shift (1) density ratio estimation (1) diffusion model (1) partial differential equation (1) weak-to-strong learning (1) energy-based model (1) generative adversarial network (1) supervised fine-tuning (1)