Deng Qiyuan — accepted AI-conference papers

2026

HiPO: Self-Hint Policy Optimization for RLVR

Deng Qiyuan, Kehai Chen, Min Zhang, Zhongwen Xu

ICLR 2026poster

Reinforcement Learning from Verifiable Rewards (RLVR) is a promising method for enhancing the complex problem-solving abilities of large language models (LLMs). This is particularly evident in domains requiring long-horizon reasoning and precise execution, such as solving complex mathematical prob…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling

Deng Qiyuan, Xuefeng Bai, Kehai Chen, Yaowei Wang, Liqiang Nie, Min Zhang

ACL 2025long

Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution shift. Current approaches typically address this issue through online sampling from the target policy, which requires sig…

Cited by 0 Source ↗PDF ↗Scholar ↗