Sebastian M. Schmon, PhD

Senior Statt Machine Learning Engineer, Altos Labs.

seb.jpeg

Welcome to my webpage! I am a machine learning researcher, statistician, and professional curious person. Currently, I’m excited to be part of the team at Altos Labs, where I’m working on developing machine learning methods that contribute to Altos’ mission of transforming medicine through cellular rejuvenation programming. Previously, I had the opportunity to work as a Research Scientist at Improbable, where I gained valuable experience applying my skills to real-world problems. During my time at Improbable, I also served as an Assistant Professor in Statistics at Durham University, where I enjoyed contributing to the academic community and mentoring the next generation of statisticians and machine learning practitioners. My research interests lie at the intersection of statistics, machine learning, and probability theory, with a particular focus on applications in the sciences. I’m also intrigued by the philosophical aspects of science and enjoy digging into the foundations when the opportunity arises. Recently, I’ve been working on projects involving generative AI, including large language models, embeddings, and diffusion models. I obtained my DPhil (the Oxford equivalent of a PhD) from the Department of Statistics at the University of Oxford. Below, you’ll find a list of my publications, highlighting my contributions to the field.

news

Oct 12, 2024 Our team at Altos Labs will be presenting our paper PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis as a spotlight presentation at the Neurips workshop on AI for New Drug Modalities. If you’re planning to attend, feel free to reach out — we’d love to connect!
Oct 11, 2024 Together with Bastian Grossenbacker Rieck and Juius von Rohrscheidt we investigate what happens when Bayesian Computation Meets Topology. Now accepted at TMLR!
Sep 26, 2024 I am serving as an Area Chair at AISTATS 2025.
Jul 17, 2024 Our paper on Approximate Bayesian Computation with Path Signatures won the OUTSTANDING PAPER award at UAI2024!
Apr 26, 2024 Our paper on Approximate Bayesian Computation with Path Signatures got accepted as a Spotlight paper at UAI 2024!

selected publications

  1. CVPR
    Anoddpm: Anomaly detection with denoising diffusion probabilistic models using simplex noise
    Julian Wyatt , Adam Leach , Sebastian Schmon, and Chris G Willcocks
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022
  2. ICLR
    Capturing Label Characteristics in {VAE}s
    Tom Joy , Sebastian Schmon, Philip Torr , Siddharth N , and Tom Rainforth
    In International Conference on Learning Representations , 2021
  3. ICLR
    Denoising diffusion probabilistic models on so (3) for rotational alignment
    Adam Leach , Sebastian Schmon, Matteo T Degiacomi , and Chris G Willcocks
    In ICLR 2022 Workshop on Geometrical and Topological Representation Learning , 2022
  4. Biometrika
    Large-sample asymptotics of the pseudo-marginal method
    Sebastian Schmon, George Deligiannidis , Arnaud Doucet , and Michael K Pitt
    Biometrika, 2021
  5. ICLR
    Learning Multimodal VAEs through Mutual Supervision
    Tom Joy , Yuge Shi , Philip Torr , Tom Rainforth , Sebastian Schmon, and Siddharth N
    In International Conference on Learning Representations , 2022