Qi He

I’m a first-year PhD student at Hong Kong University of Science and Technology under the guidance of Prof. Yi R. Fung. Prior to my doctoral studies, I earned bachelor’s degree in Data Science from Fudan University. I have worked with Prof. Heng Ji from University of Illinois Urbana-Champaign, Prof. Zhongyu Wei and Prof. Baojian Zhou from Fudan University.

My research focuses on reasoning techniques. My research interests lie in RL for Reasoning, Diffusion Language Models, and Efficient AI Architectures. Lately, I’ve been especially excited about on-device AI, aiming to build personal and reliable AI systems.

Feel free to reach out to me to explore potential research opportunities together.

Latest update: Aug, 2026

news

Sep 01, 2026	Join Hong Kong University of Science and Technology as a CSE PhD Student.

papers

arXiv

Reinforcement Learning from Denoising Feedback

Qi He, Huan Chen, Ya Guo, and 3 more authors

2026

arXiv Bib Code

@article{he2026reinforcement,
  title = {Reinforcement Learning from Denoising Feedback},
  author = {He, Qi and Chen, Huan and Guo, Ya and Zhu, Huijia and Fung, Yi R and Zhou, Baojian},
  booktitle = {arXiv preprint},
  year = {2026},
}

ACL Findings

Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning

Qi He, Cheng Qian, Xiusi Chen, and 3 more authors

2025

arXiv Bib Code

@article{he2025verir1precisefaithfulclaim,
  title = {Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning},
  author = {He, Qi and Qian, Cheng and Chen, Xiusi and He, Bingxiang and Fung, Yi R. and Ji, Heng},
  booktitle = {ACL Findings},
  year = {2025},
}

NeurIPS

Toolrl: Reward is all tool learning needs

Cheng Qian, Emre Can Acikgoz, Qi He, and 5 more authors

2025

arXiv Bib Code

@article{qian2025toolrl,
  title = {Toolrl: Reward is all tool learning needs},
  author = {Qian, Cheng and Acikgoz, Emre Can and He, Qi and Wang, Hongru and Chen, Xiusi and Hakkani-T{\"u}r, Dilek and Tur, Gokhan and Ji, Heng},
  booktitle = {Annual Conference on Neural Information Processing Systems},
  year = {2025},
}

ACM Surveys

From individual to society: A survey on social simulation driven by large language model-based agents

Xinyi Mou, Xuanwen Ding, Qi He, and 8 more authors

2024

arXiv Bib Code

@article{mou2024individual,
  title = {From individual to society: A survey on social simulation driven by large language model-based agents},
  author = {Mou, Xinyi and Ding, Xuanwen and He, Qi and Wang, Liang and Liang, Jingcong and Zhang, Xinnong and Sun, Libo and Lin, Jiayu and Zhou, Jie and Huang, Xuanjing and others},
  booktitle = {ACM Computing Surveys},
  year = {2024},
}