Publications

Research papers & selected writing.

A concise record of my work across mathematical machine learning, algebraic statistics, geometric data analysis, and reliable AI. For the most current citation record, see Google Scholar.

In circulation

Preprints

  1. 2026
    Singular learning theory

    A Basin-Selection Perspective on Grokking via Singular Learning Theory

    Ben Cullen, Sergio Estan-Ruiz, Riya Danait, and Jiayi Li

    arXiv:2603.01192

  2. 2026
    Algebraic statistics

    Identifiability in Graphical Discrete Lyapunov Models

    Cecilie Olesen Recke, Sarah Lumpp, Nataliia Kushnerchuk, Janike Oldekop, Jiayi Li, Jane Ivy Coons, and Elina Robeva

    arXiv:2601.21818

Selected

Peer-reviewed publications

  1. 2024
    Neuroalgebraic geometry

    Geometry of Polynomial Neural Networks

    Kaie Kubjas, Jiayi Li, and Maximilian Wiesmann

    Algebraic Statistics, 15, 295–328

  2. 2024
    Topological data analysis

    Pull-back Geometry of Persistent Homology Encodings

    Shuang Liang, Renata Turkeš, Jiayi Li, Nina Otter, and Guido Montúfar

    Transactions on Machine Learning Research

  3. 2024
    Algebraic statistics

    New Directions in Algebraic Statistics: Three Challenges from 2023

    Yulia Alexandr, Miles Bakenhus, Maize Curiel, Sameer K. Deshpande, Elizabeth Gross, Yuqi Gu, Max Hill, Joseph Johnson, Bryson Kagy, Vishesh Karwa, Jiayi Li, Hanbaek Lyu, Sonja Petrović, and Jose Israel Rodriguez

    Algebraic Statistics, 15, 357–382

  4. 2023
    Statistical inference

    Discussion of “Estimating Means of Bounded Random Variables by Betting”

    Jiayi Li, Yuantong Li, and Xiaowu Dai

    Journal of the Royal Statistical Society: Series B, 86(1), 41–43

  5. 2022
    Control

    Image-Based Regulation of Mobile Robots without Pose Measurements

    Dejun Guo, Xu Jin, Dan Shao, Jiayi Li, Yang Shen, and Huan Tan

    IEEE Control Systems Letters, 6, 2156–2161

  6. 2021
    Digital twins

    A Survey on AI-Driven Digital Twins in Industry 4.0: Smart Manufacturing and Advanced Robotics

    Ziqi Huang, Yang Shen, Jiayi Li, Marcel Fey, and Christian Brecher

    Sensors, 21(19), 6340

Earlier work

Earlier research

This early geometric study examines how artificial neural networks fail and recover under component damage. It connects directly to my continuing interest in reliable learning systems.

  1. 2020
    Resilient systems

    Geometric Algorithms for Predicting Resilience and Recovering Damage in Neural Networks

    Guruprasad Raghavan, Jiayi Li, and Matt Thomson

    arXiv:2005.11603

Editorial

Selected writing from ACM XRDS

Editor in Chief, ACM XRDS
2022–2025

I served on the editorial team from 2020 to 2025, first as Feature Editor, then Lead Editor, and finally Editor in Chief. These three pieces are selected for how they connect technical work to education, living systems, and creativity. The full CV carries the complete list.

  1. 2024
    AI & education

    Exploring the Frontiers of Machine Learning in Education

    Jiayi Li

    XRDS: Crossroads 31(1), 5

  2. 2023
    Computing & biology

    Code of Life: Unraveling Biological Mysteries through Computational Innovation

    Jiayi Li

    XRDS: Crossroads 30(2), 5–6

  3. 2023
    AI & creativity

    Computational Creativity: Bridging Art and Computer Science

    Jiayi Li

    XRDS: Crossroads 29(4), 5