Yingtong Dou

Bio

I am a research scientist at Visa Research. As a member of the Foundational AI team, I am currently working on payment foundation models, deep learning for fraud detection, and various LLM applications in payment. My research interests include transaction data modeling, ML trust and safety, and graph mining.

Prior to joining Visa, I obtained my Ph.D. in Computer Science at University of Illinois Chicago in 2022, advised by Prof. Philip S. Yu. My Ph.D. dissertation is “Robust Graph Learning for Misbehavior Detection” [PDF]. Before attending UIC, I received my B.E. from Beijing University of Posts and Telecommunications in 2017.

News

Show more

Talks and Blogs

Show more

Recent Work

  • TransactionGPT Tech Report
    Yingtong Dou, Yuzhong Chen et al.
    Technical Report 11/2025.
    [Paper][Website]
  • Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts ICLR 2026
    Kartik Sharma, Yiqiao Jin, Vineeth Mohan, Yingtong Dou et al.
    [Paper]
  • TREASURE: A Transformer-Based Foundation Model for High-Volume Transaction Understanding KDD 2026
    Chin-Chia Michael Yeh, Uday Singh Saini et al.
    [Paper]
  • Enhancing Foundation Models in Transaction Understanding with LLM-based Sentence Embeddings EMNLP 2025
    Xiran Fan, Zhimeng Jiang et al.
    [Paper]
  • SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression Preprint
    Yiqiao Jin, Kartik Sharma, Vineeth Mohan, Yingtong Dou et al.
    Preprint 07/2025.
    [Paper]
  • Personalized Layer Selection for Graph Neural Networks TMLR 2025
    Kartik Sharma, Vineeth Mohan, Yingtong Dou et al.
    [Paper]

Selected Publications