Lifeng Liu

language model (2) knowledge editing (1) preference alignment (1) preference optimization (1) model editing (1) reinforcement learning from human feedback (1) hierarchical reinforcement learning (1) knowledge refinement (1) diffusion model (1) schrödinger bridge (1) human preference alignment (1) retrieval-augmented generation (1) robustness evaluation (1) power spectral density (1) signal denoising (1) knowledge recall (1) multi-source retrieval (1) deep search (1) implicit reward modeling (1) multi-dimensional preference (1)