English

邓贺烜

Hexuan Deng 邓贺烜

photo

hxuandeng (at) gmail.com

[GitHub] [Google Scholar]
[ORCID] [Semantic Scholar]

哈尔滨工业大学（深圳）计算机科学与技术专业一年级博士生。 研究兴趣主要包括自然语言处理(NLP)、推理大模型(LRM)和数据中心人工智能(DCAI)。

教育经历

研究经历

研究工作

预印本

  1. REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Large Reasoning Models.
    Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Jun Rao, Min Zhang.
    arXiv preprint, 2025. [Github]
  2. Dynamic Sampling that Adapts: Iterative DPO for Self-Aware Mathematical Reasoning.
    Jun Rao, Xuebo Liu, Hexuan Deng, Zepeng Lin, Zixiong Yu, Jiansheng Wei, Xiaojun Meng, Min Zhang.
    arXiv preprint, 2025.

会议论文

  1. DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization.
    Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Jing Li, Min Zhang, Zhaopeng Tu.
    ACL Main Conference, 2025. [arXiv] [Github]
  2. NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates.
    Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Min Zhang, Zhaopeng Tu.
    NeurIPS D&B, 2024. [arXiv] [Github]
  3. Curriculum Consistency Learning for Conditional Sentence Generation.
    Liangxin Liu, Xuebo Liu, Lian Lian, Shengjun Cheng, Jun Rao, Tengfei Yu, Hexuan Deng, Min Zhang.
    EMNLP Main Conference, 2024. [Github]
  4. Improving Simultaneous Machine Translation with Monolingual Data.
    Hexuan Deng, Liang Ding, Xuebo Liu, Meishan Zhang, Dacheng Tao, Min Zhang.
    AAAI, 2023. [arXiv] [Github]

项目经历

  1. Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm.
    Hexuan Deng, Xin Zhang, Meishan Zhang, Xuebo Liu, Min Zhang.
    ACL Workshop, 2024. [arXiv] [Github]
    Focused on improving model performance and inference speed for UDS semantic parsing tasks.
  2. "LiZhi" Foundation Model and Intelligent Dialogue System
    Team Member, April 2023 -- June 2023
    Focused on enhancing the model's mathematical capabilities. Introduced a calculator tool to significantly reduce calculation errors.
  3. Recruitment Large Language Model
    AI-Assisted Interview Lead, August 2024 -- June 2025
    Led a team of five, focusing on customizing written and interview questions based on target positions and user resumes, with automated question updates via an agent system.

程序委员会 / 审稿人