Qiaozhi He

optimal transport (1) preference alignment (1) preference optimization (1) language model alignment (1) reinforcement learning from human feedback (1) diffusion model (1) reward model (1) hallucination mitigation (1) human preference alignment (1) multi-dimensional evaluation (1) probing method (1) human motion generation (1) text-to-motion generation (1) visual reward model (1) multi-condition generation (1) stickman sketch (1) preference representation (1)