I am a fourth-year joint Ph.D. candidate between Xi’an Jiaotong University (XJTU) and Microsoft Research Asia (MSRA). My research focuses on applying and advancing Large Language Models (LLMs) in structured data analysis/understanding and code generation.

Publications

• TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models. (Under Review)
  Xinyi He, Yihao Liu, Mengyu Zhou, Yeye He, Haoyu Dong, Shi Han, Zejian Yuan, Dongmei Zhang.
• TabEval: How Far Large Language Models Have Gone on Tabular Data? (Under Review)
  Xinyi He*, Yun Lin*, Mengyu Zhou, Yirui Luo, Junyu Xiong, Yeye He, Haoyu Dong, Shi Han, Dongmei Zhang.
• CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing. (EMNLP 2024) paper
  Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou, Shi Han, Zejian Yuan, Dongmei Zhang.
• Tap4llm: Table provider on sampling, augmenting, and packing semi-structured data for large language model reasoning. (EMNLP 2024) paper
  Yuan Sui, Jiaru Zou, Mengyu Zhou, Xinyi He, Lun Du, Shi Han, Dongmei Zhang.
• Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries. (AAAI 2024) paper
  Xinyi He, Mengyu Zhou, Xinrun Xu, Xiaojun Ma, Rui Ding, Lun Du, Yan Gao, Ran Jia, Xu Chen, Shi Han, Zejian Yuan, Dongmei Zhang.
• AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks. (ACL 2023) paper
  Xinyi He, Mengyu Zhou, Mingjie Zhou, Jialiang Xu, Xiao Lv, Tianle Li, Yijia Shao, Shi Han, Zejian Yuan, and Dongmei Zhang.
• Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks. (IJCAI 2022, Survey Track) paper
  Haoyu Dong, Zhoujun Cheng, Xinyi He, Mengyu Zhou, Anda Zhou, Fan Zhou, Ao Liu, Shi Han, Dongmei Zhang.
• Table2Charts: Recommending Charts by Learning Shared Table Representations. (KDD 2021) paper
  Mengyu Zhou, Qingtao Li, Xinyi He, Yuejiang Li, Yibo Liu, Wei Ji, Shi Han, Yining Chen, Daxin Jiang, and Dongmei Zhang.
• Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems. (EMNLP 2022) paper
  Jialiang Xu, Mengyu Zhou, Xinyi He, Shi Han, and Dongmei Zhang.
• MultiVision: Designing Analytical Dashboards with Deep Learning Based Recommendation. (IEEE TVCG 2022) paper
  Aoyu Wu, Yun Wang, Mengyu Zhou, Xinyi He, Haidong Zhang, Huamin Qu, Dongmei Zhang.

Educations

2020.7 ~ Present: Microsoft Research Asia, Joint Ph.D Program.

• Advisor: Dongmei Zhang, mentors: Shi Han & Mengyu Zhou.
• Data, Knowledge, and Intelligence Group.

2021.9 ~ Present: Xi’an Jiaotong University, Joint Ph.D Candidate.

• Advisor: Prof. Zejian Yuan.
• The College of Artificial Intelligence.

2017.8 ~ 2021.7: Xi’an Jiaotong University, Bachelor’s Degree.

• Automatic Science and Technology.

Honors and Awards

Honor Awards

• 2018, National Scholarship
• 2021, The Honor of “Star of Tomorrow” by MSRA
• 2019 / 2020, First-class / Second-class scholarship of Xi’an Jiaotong University
• 2023, Excellent Graduate Student
• 2018 & 2019 & 2020, Excellent Student

Competition Awards

• 2019, Second prize in the 11th National Mathematics Competition for College Students
• 2020 / 2019, H / S Prize, Mathematical Modeling Competition
• 2022, “Xinhuo Cup” AI Competition First Prize & Innovation Award
• 2018, Second prize in Shaanxi Division, Undergraduate Group, National Mathematical Modeling Contest for College Students