Multimodal Tabular Intelligence
Learning from tables together with text, images, and visual structure to enrich tabular signals.
Short Biography
I received my B.Sc. degree from Soochow University in June 2021. In the same year, I was admitted to pursue a Ph.D. degree at Nanjing University without an entrance examination. I am a member of the LAMDA Group, led by Professor Zhi-Hua Zhou, and am supervised by Professor De-Chuan Zhan and Professor Han-Jia Ye.
Research Interests
My research focuses on building intelligent systems that can transform complex, multimodal information into structured knowledge and actionable insights. In particular, I study how machines can jointly perceive, parse, understand, and reason over tables, documents, text, images, and visual structures, with the broader goal of developing data world models and agents capable of interacting with real-world information.
Data World Model
Building data world models/agents that parse, understand, reason over, and act on complex information.
Document Intelligence
End-to-end document parsing, OCR, document understanding, and structured information extraction.
Publications
Preprints, conference proceedings, and journal articles.
Preprints
Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation
Preprint
Conference Publications
Dissecting Post-Training: Uncovering the Complementary Roles of SFT and RL for Document Parsing
Proceedings of the 43rd International Conference on Machine Learning · ICML 2026 · Seoul, South Korea
Multimodal Tabular Reasoning with Privileged Structured Information
Advances in Neural Information Processing Systems 38 · NeurIPS 2025
Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
Advances in Neural Information Processing Systems 38 · NeurIPS 2025
Journal Publications
From Universal Prediction to Universal Workflows: A Survey of Foundation Models for Tabular and Time Series Data
Frontiers of Computer Science · FCS 2026
Tabular Data Generation for Complex Requirements Based on Large Language Models
Chinese Journal of Computers (计算机学报)· CJC 2026
Honors
- 2025南京大学栋梁奖学金优秀奖
- 2025第六届CSIG图像图形技术挑战赛 · 金山办公 2025 算法挑战赛多模态文档解析大赛二等奖
- 2024挑战杯“揭榜挂帅”专项赛 · 中国电信赛道特等奖
- 2024南京大学栋梁奖学金优秀奖
- 20242nd Place, IJCAI 2024 Competition — Visually Rich Form Document Intelligence and Understanding: Track B
- 2023百度商业 AI 技术创新大赛特等奖
- 2023华为—南京大学联合实验室优秀学生奖
- 2022挑战杯—小挑全国铜奖
Teaching Assistant
- Autumn 2025Introduction to Machine Learning · Undergraduate course · Prof. Han-Jia Ye
- Spring 2024Machine Learning Primer · MOCC, online · Prof. Zhi-Hua Zhou and Prof. Han-Jia Ye
- Autumn 2023Introduction to Machine Learning · Undergraduate course · Prof. Han-Jia Ye
- Spring 2022Introduction to Machine Learning · Undergraduate course · Prof. Han-Jia Ye
Academic Service
01 · Tutorial
Tabular Representation Learning
A tutorial with Prof. Han-Jia Ye at AAAI 2026.
View tutorial02 · Conference Service
- ICLR 2027
- ICML · NeurIPS · ICLR2023–2026
- CVPR · KDD · AAAI · IJCAI · AISTATS2024–2026
Area Chair
Reviewer
03 · Journal Reviewing
- IEEE TPAMI
- IEEE TKDE
- Pattern Recognition
- Neural Networks
- Knowledge-Based Systems
Contact
Mailing Address
Jun-Peng JiangNational 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