Rui Yang

large language model (6) offline reinforcement learning (4) style transfer (3) reinforcement learning from human feedback (3) sketch generation (3) benchmark evaluation (2) image generation (2) retrieval-augmented generation (2) semantic segmentation (2) knowledge graph (2) model alignment (2) reward model (2) self-supervised learning (2) human preference (2) weakly supervised learning (2) distribution shift (2) adversarial robustness (2) diffusion model (2) reward modeling (2) graph neural network (2)