Peng Wang

Reward Is Enough: LLMs Are In-Context Reinforcement Learners

Training-Free Speedup for Retrieval-Augmented Generation with Staged Parallel Speculation

CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Review and Rebuttal: Zero-shot In-context Adversarial Learning for Improving Research Ideation