Guhao Feng

large language model (3) reward modeling (1) offline reinforcement learning (1) autoregressive transformer (1) data transformation (1) mathematical reasoning (1) direct preference optimization (1) preference alignment (1) chain-of-thought reasoning (1) language model alignment (1) graph representation (1) computational complexity (1) dynamic programming (1) model-based reinforcement learning (1) weisfeiler-lehman test (1) expressive power (1) inference optimization (1) confidence estimation (1) subgraph neural network (1) circuit complexity (1)