Edmond Cunningham

PhD Candidate, UMass Amherst

prof_pic.jpg

I am completing my PhD at UMass Amherst this year and am actively seeking industry and post-doc positions. My research sits at the intersection of generative modeling and representation learning, where I am interested in characterizing the geometric structure of data in order to understand how to build better representations of data and interpretable generative models. Additionally, I have expertise in flow based and diffusion based generative models and have used them for image generation, time series modeling, variational inference, and Boltzmann sampling.

selected publications

  1. ICLR GRaM
    conformal-coordinate-frames.png
    Conformal Coordinate Frames for Disentanglement
    Edmond Cunningham
    2026
    Accepted, ICLR 2026 Workshop on Geometry-grounded Representation Learning and Generative Modeling (GRaM)
  2. Preprint
    ar-fbgm.png
    On Autoregressive Time Series Generation using Flow-based Generative Models
    Edmond Cunningham, Madalina Fiterau, and Daniel Sheldon
    2025
  3. ICML
    principal-component-flows.png
    Principal Component Flows
    Edmond Cunningham, Adam D. Cobb, and Susmit Jha
    In Proceedings of the 39th International Conference on Machine Learning, 2022
    HTML
  4. AISTATS
    change-of-variables-rectangular.png
    A Change of Variables Method For Rectangular Matrix-Vector Products
    Edmond Cunningham and Madalina Fiterau
    In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021
    HTML