Research

Research & Papers

Machine learning for graphs, uncertainty, generative modeling and scientific data: my papers, and posts that explain them.

Publications

  1. NeurIPS 2026

    Improving Function Space Flow Matching with Kernel Optimal Transport

    Fred Xu, Thomas Markovich, Barbora Barancikova, Yizhou Sun

    arXiv

  2. NeurIPS 2026

    Graph Anomaly Detection as Finite-Horizon Control: Training-Free Scoring via Empirical Bayes

    Fred Xu, Thomas Markovich, Florence Regol, Yizhou Sun

    arXiv

  3. NeurIPS 2026

    A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion

    Fred Xu, Thomas Markovich, Florence Regol, Yizhou Sun

    arXiv

  4. KDD 2026

    FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation

    Haixin Wang, Ruoyan Li, Fred Xu, Fang Sun, Kaiqiao Han, Zijie Huang, Ching Chang, Xiao Luo, Wei Wang, Yizhou Sun · Co-first author

    arXiv

  5. KDD 2026

    TIDAL: A Temporal Causal Diffusion Framework for Visualizing Knee Osteoarthritis Treatment Outcomes

    Second author

  6. ACL 2026

    Training Recipes for Agentic Reinforcement Learning in LLMs: A Survey

    Co-author

  7. NeurIPS 2025

    Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations

    Fred Xu, Thomas Markovich

    arXiv

  8. ACL 2024

    FUSE: Measure-Theoretic Compact Fuzzy Set Representation for Taxonomy Expansion

    Fred Xu, Song Jiang, Zijie Huang, Xiao Luo, Shichang Zhang, Adrian Chen, Yizhou Sun

    OpenReviewarXiv

  9. Manuscript

    Neural Hybrid Residual XRO Models for ENSO Forecasting

    First author

  10. Under review

    FlowPhon: Graph Generation via Flow Matching on Graphon Operators

    Second author