Wenqiao Zhu

representation learning (1) contrastive learning (1) reinforcement learning (1) variational inference (1) embedding learning (1) direct preference optimization (1) chain-of-thought reasoning (1) language model alignment (1) perplexity evaluation (1) diffusion model (1) gradient flow (1) language model (1) recommendation system (1) context window (1) position encoding (1) rotary position embedding (1) cold-start problem (1) language model efficiency (1) click-through rate prediction (1) context window extension (1)