Si-Yang Liu @ LAMDA, NJU-AI

刘思阳
Si-Yang Liu
M.Sc Student, LAMDA Group
School of Artificial Intelligence
Nanjing University, Nanjing 210023, China
Email: liusy [at] lamda.nju.edu.cn
Resume / 简历

LAMDA Logo

NJU Logo

Short Biography

I received my B.Sc. degree from School of Artificial Intelligence, Nanjing University, in June 2024. In the same year, I was admitted to study for a M.Sc. degree in Nanjing University without entrance examination in the LAMDA Group led by professor Zhi-Hua Zhou, under the supervision of Associate Prof Han-Jia Ye.

Research Interests

My research interests include Machine Learning and Data Mining, with a primary focus on Tabular Foundation Models, LLMs for Assisting Tabular Data Prediction, evaluation and benchmarking of tabular learning models, and I am currently exploring LLM-based generative recommendation.

Publications

Tabular Foundation Model

WSFG

  • Si-Yang Liu, Han-Jia Ye. TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems. In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025, CCF-A, 第一作者). [Paper]

WSFG

  • Han-Jia Ye, Si-Yang Liu, Wei-Lun Chao. A Closer Look at TabPFN v2: Strength, Limitation, and Extension. In: Advances in Neural Information Processing Systems 38 (NeurIPS'25, CCF-A, 学生第一作者). [Paper]

Benchmarking Tabular Data Models

WSFG

  • Si-Yang Liu, Hao-Run Cai, Qile Zhou, Huai-Hong Yin, Tao Zhou, Jun-Peng Jiang, Han-Jia Ye. TALENT: A Tabular Analytics and Learning Toolbox. Journal of Machine Learning Research (JMLR, CCF-A, 第一作者). [Paper] [Code]

WSFG

  • Han-Jia Ye, Si-Yang Liu*, Hao-Run Cai*, Qile Zhou, De-Chuan Zhan. A Closer Look at Deep Learning Methods on Tabular Datasets. [Paper] [Code]

WSFG

  • Jun-Peng Jiang, Si-Yang Liu, Hao-Run Cai, Qile Zhou, Han-Jia Ye. Representation Learning for Tabular Data: A Comprehensive Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, CCF-A, 第二作者). [Paper] [Code]

LLMs for Assisting Tabular Data Prediction

WSFG

  • Si-Yang Liu*, Qile Zhou*, Han-Jia Ye. Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboard. In 1st ICML Workshop on Foundation Models for Structured Data, 2025. 共同第一作者 [Paper]

WSFG

  • Jun-Peng Jiang, Si-Yang Liu, De-Chuan Zhan, Han-Jia Ye. Mind the Modality Gap: Multimodal Representation Learning for Tabular Data with Text Signals. [Paper] [Code]

Teaching Assistant

Introduction to Machine Learning. (For undergraduate students, Autumn, 2025; Prof. Han-Jia Ye)

Introduction to Machine Learning. (For undergraduate students, Autumn, 2024; Prof. Han-Jia Ye)

Service

Conference Reviewer: AAAI'25, ICLR'25, ICLR'26, IJCAI'25, PAKDD'26, ICML'26

Correspondence

Email: liusy [at] lamda.nju.edu.cn

Office: Room A202, Shaoyifu Building, Xianlin Campus of Nanjing University

Address: National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China

(南京市栖霞区仙林大道163号, 南京大学仙林校区603信箱, 软件新技术国家重点实验室, 210023.)