I am a 1st year Ph.D student in Computer Science of Harbin Institute of Technology (Shenzhen).
My research interests lie in the areas of Natural Language Processing (NLP), Large Language Models (LLM) and Data-Centric AI (DCAI).

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)、大语言模型(LLM)和数据中心人工智能(DCAI)。

教育经历

---

• 2024.09 - 至今, 计算机科学与技术, 博士在读, 哈尔滨工业大学（深圳）. 导师: 刘学博 和 张民.
• 2022.09 - 2024.07, 计算机技术, 硕士学位, 哈尔滨工业大学（深圳）. 导师: 刘学博 和 张民.
• 2018.09 - 2022.07, 智能科学与技术, 学士学位, 南开大学.

研究经历

---

• 2023.07 - 至今, 研究实习生, 交互翻译组, 腾讯AI Lab. 企业导师: 焦文祥 和 涂兆鹏.
• 2021.10 - 2022.04, 研究实习生, 探索研究院, 京东科技. 企业导师: 丁亮.

研究工作

---

会议论文

1. 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. [Github]
2. Curriculum Consistency Learning for Conditional Sentence Generation.
   Liangxin Liu, Xuebo Liu, Lian Lian, Shengjun Cheng, Jun Rao, Tengfei Yu, Hexuan Deng, Min Zhang.
   EMNLP, 2024. [Github]
3. Improving Simultaneous Machine Translation with Monolingual Data.
   Hexuan Deng, Liang Ding, Xuebo Liu, Meishan Zhang, Dacheng Tao, Min Zhang.
   AAAI, 2023. [arXiv] [Github] [Video]

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 -- December 2024
   Led a team of five, focusing on customizing written and interview questions based on target positions and user resumes.

程序委员会 / 审稿人

• NLPCC 2024 Conference NLP TxtMining Reviewers.
• Assisted in reviewing over ten papers for conferences such as ICLR, ICML, NeurIPS, EMNLP, and CVPR since 2023.