Han Zhang

👨‍🎓 个人简介

我是张晗，鹏城实验室助理研究员。我于2025年6月博士毕业，目前我的主要研究兴趣是大模型推理、去中心化分布式训练。 在过往的研究中，我的研究领域包括大模型价值观对齐、偏好学习、表示学习、持续学习等方向。 以第一作者在 ICLR / AAAI / ACL / EMNLP 等人工智能/自然语言处理等国际顶级会议发表文章。欢迎大家与我学术交流。

🥇 获奖情况

• 2025.05 鹏城实验室优秀博士提名
• 2024.12 鹏城实验室主任奖学金 (5万奖金)
• 2023.10 第二届暹星杯竞赛一等奖
• 2022.11 鹏城实验室主任奖学金 (5万奖金)
• 2014.04 全国大学生数学竞赛一等奖（专业组）

📖 教育经历

• 2021.09 - 2025.06，哈尔滨工业大学（深圳）& 鹏城实验室（联培），博士学位，计算机技术
• 2015.09 - 2017.12，国防科技大学，硕士学位，应用数学
• 2011.09 - 2015.06，河北工业大学，学士学位，数学与应用数学

💼 工作经历

• 2025.06 - 至今，鹏城实验室
• 2020.12 - 2021.08，鹏城实验室
• 2020.08 - 2020.12，腾讯科技(深圳)有限公司
• 2020.04 - 2020.07，中国航天科工集团先进院

📞 联系方式

张晗 (Hanlard)

邮箱: zhangh04@pcl.ac.cn

谷歌学术: 链接

📝 发表论文

I. 会议论文

• Correcting Large Language Model Behavior via Influence Function. Han Zhang (张晗), Zhuo Zhang, Yi Zhang, et al. AAAI Conference on Artificial Intelligence (AAAI), 2025. (Oral)

• CPPO: Continual Learning for Reinforcement Learning with Human Feedback. Han Zhang (张晗), Yu Lei, Lin Gui, et al. International Conference on Learning Representations (ICLR), 2024.

• COPR: Continual Human Preference Learning via Optimal Policy Regularization. Han Zhang (张晗), Lin Gui, Yu Lei, et al. Association for Computational Linguistics (ACL), 2025.

• CLLE: A benchmark for continual language learning evaluation in multilingual machine translation. Han Zhang (张晗), Sheng Zhang, Yang Xiang, et al. Empirical Methods in Natural Language Processing (EMNLP), 2022.

• Incremental pre-training from smaller language models. Han Zhang (张晗), Wang Hui, Xu Ruifeng. Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10), 2025.

• BeyondGender: A Multifaceted Bilingual Dataset for Practical Sexism Detection. Xuan Luo, Li Yang, Han Zhang (张晗), et al. AAAI Conference on Artificial Intelligence (AAAI), 2025.

II. Preprint论文

• Group Expectation Policy Optimization for Heterogeneous Reinforcement Learning. Han Zhang (张晗), Ruibin Zheng, Zexuan Yi, Zhuo Zhang, Hanyang Peng, Hui Wang, Zike Yuan, Cai Ke, Shiwei Chen, Jiacheng Yang, Yangning Li, Xiang Li, Jiangyue Yan, Yaoqi Liu, Liwen Jing, Jiayin Qi, Ruifeng Xu, Binxing Fang, Yue Yu. ArXiv, 2025.

• PanGu-alpha: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation. Wei Zeng, Xiaozhe Ren, Teng Su, Hui Wang, Yi Liao, Zhiwei Wang, Xin Jiang, ZhenZhang Yang, Kaisheng Wang, Xiaoda Zhang, Chen Li, Ziyan Gong, Yifan Yao, Xinjing Huang, Jun Wang, Jianfeng Yu, Qi Guo, Yue Yu, Yan Zhang, Jin Wang, Hengtao Tao, Dasen Yan, Zexuan Yi, Fang Peng, Fangqing Jiang, Han Zhang (张晗), Lingfeng Deng, Yehong Zhang, Zhe Lin, Chao Zhang, Shaojie Zhang, Mingyue Guo, Shanzhi Gu, Gaojun Fan, Yaowei Wang, Xuefeng Jin, Qun Liu, Yonghong Tian. ArXiv, 2021

III. 期刊论文

• An Orthogonality-based Dual-memory Framework for Continual Text Classification. Han Zhang (张晗), Yu Lei, Bin Liang, et al. IEEE Transactions on Audio, Speech and Language Processing (TASLP), 2025.

• Prompt-based prototypical framework for continual relation extraction. Han Zhang (张晗), Bin Liang, Min Yang, et al. IEEE Transactions on Audio, Speech and Language Processing (TASLP), 2022.

• 支持鹏程系列开源大模型应用生态演化的可持续学习能力探索. 余跃, 刘欣, 蒋芳清, Han Zhang (张晗), et al. 智能科学与技术学报, 2022.