Zhiqin (Brian) Yang

zqy.png

I’m a PhD student at HKUST supervised by Prof. Yike Guo and Prof. Wei Xue I’m also working closely with Prof. Bo Han and Prof. Yonggang Zhang at the TMLR group, HKBU . Prior to this, I earned my M.S. degree from Beihang University (BUAA), advised by Prof. Hao Peng. I also completed my B.S. degree at Nanjing University of Science and Technology (NJUST), where I spent four enriching years. My research focuses on Federated Learning and its applications, particularly in privacy-preserving healthcare solutions.

Beyond academia, I am an avid basketball enthusiast and a devoted fan of Kobe Bryant. I enjoy immersing myself in live music, especially hip-hop and R&B, with Nous Underground from XAC being a favorite. Additionally, I have a deep interest in Chinese history, particularly the Ming Dynasty.

If you’re interested in discussing potential collaborations or shared passions, please feel free to reach out! I welcome diverse perspectives and ideas to broaden me. :face_holding_back_tears:

news

May 01, 2026 One first author paper on rethinking the equivalence between DPO and RLHF got accepted by ICML’26 as a spotlight paper, congrats to all collaborators!
Apr 07, 2026 LearnAlign to select high-quality data for LLM post-training get accepeted by ACL’26 as findings paper, . Welcome to check our paper:kissing_smiling_eyes:
Apr 04, 2026 ClawNet Check out ClawNet, our human-agent symbiosis framework from HKGAI@HKUST for AI agent governance! Check out our technical report!!
Feb 21, 2026 One co-first author paper on rethinking federated noisy problem got accepted by CVPR’26, congrats to all collaborators!
Feb 10, 2026 We release MemFly (got accepted by ICLR’26 workshop about MemAgent) for the agent memory workflow. Welcome to check our paper :smile:

Selected publications

  1. NeurIPS 2023
    FedFed: Feature distillation against data heterogeneity in federated learning
    Zhiqin Yang, Yonggang Zhang, Yu Zheng, Xinmei Tian, Hao Peng, Tongliang Liu, and Bo Han
    Advances in Neural Information Processing Systems, 2023
  2. NeurIPS 2025
    FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
    Zhiqin Yang, Yonggang Zhang, Chenxin Li, Yiu-ming Cheung, Bo Han, and Yixuan Yuan
    Advances in Neural Information Processing Systems, 2025
  3. ICLR 2024
    Robust Training of Federated Models with Extremely Label Deficiency
    Yonggang Zhang*, Zhiqin Yang*, Xinmei Tian, Nannan Wang, Tongliang Liu, and Bo Han
    In The Twelfth International Conference on Learning Representations, 2024
  4. ACL 2026 Findings
    LearnAlign: Reasoning Data Selection for Reinforcement Learning in Large Language Models Based on Improved Gradient Alignment
    Shipeng Li*, Zhiqin Yang*, Shikun Li*, Xiaobo Xia, Hengyu Liu, Xinghua Zhang, Gaode Chen, and 3 more authors
    arXiv preprint arXiv:2506.11480, 2026
  5. arXiv 2602.07885
    MemFly: On-the-Fly Memory Optimization via Information Bottleneck
    Zhenyuan Zhang, Xianzhang Jia, Zhiqin Yang, Zhenbo Song, Wei Xue, Sirui Han, and Yike Guo
    arXiv preprint arXiv:2602.07885, 2026
  6. arXiv 2604.19211
    ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation
    Zhiqin Yang, Zhenyuan Zhang, Xianzhang Jia, Jun Song, Wei Xue, Yonggang Zhang, and Yike Guo
    arXiv preprint arXiv:2604.19211, 2026
  7. CVPR 2026
    FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients
    Tian Wen*, Zhiqin Yang*, Yonggang Zhang, Xuefeng Jiang, Hao Peng, Yuwei Wang, and Bo Han
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2026
  8. ICML 2026 Spotlight
    Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment
    Zhiqin Yang, Yonggang Zhang, Wei Xue, Dong Fang, Bo Han, and Yike Guo
    In Forty-Third International Conference on Machine Learning, 2026

Awards

Academic Services

Journal Reviewer: Conference Reviewer: