Zhewei Kang

2 accepted papers

2026

Learning to Reason without External Rewards

Xuandong Zhao, Zhewei Kang, Aosong Feng, Sergey Levine, Dawn Song

ICLR 2026poster

Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision. We explore Reinforcement Learning from Internal Feedback (RLIF), a framework that enables LLMs to learn f…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Scalable Best-of-N Selection for Large Language Models via Self-Certainty

Zhewei Kang, Xuandong Zhao, Dawn Song

NeurIPS 2025poster

Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models for response evaluation and selection. Reward-free alternative…

Cited by 0 Source ↗code ↗Scholar ↗