christopher beckham
Academic blog: generative models, diffusion, VAEs, and model-based optimisation, amongst other topics. ML researcher
about me
I am a machine learning researcher with more than a decade of experience across classical methods, deep learning, and generative modeling. My work emphasises theoretical clarity paired with practical execution, especially in domains where standard assumptions about data or ground truth break down. I have a strong interest in evaluation, metric design, and reproducibility, and I prioritise understanding model behavior over headline performance alone. I have led and contributed to end-to-end ML systems in industrial settings. I am particularly drawn to problems that reward rigour, skepticism, and careful empirical validation.
positions
- Current: ML researcher @ vopemed
- Previously:
- ML researcher at AlpacaML
- Intern / visiting researcher at NVIDIA, ServiceNow, Imagia
education
- PhD @ Polytechnique Montreal & MILA (2019-2024)
- MASc @ Polytechnique Montreal & MILA (2016-2017)
- BCMS(Hons) @ University of Waikato (2012-2015)
blog
- 2025-07-01 reflecting on past work -- offline model-based optimisation
- 2024-10-07 paper thoughts -- questionable research practices (qrps) in machine learning
- 2024-05-31 edm diffusion models - a jupyter implementation, and how they are implemented in practice
- 2023-04-27 a deep dive into conditional variational autoencoders
- 2023-01-27 techniques for label conditioning in gaussian denoising diffusion models
- 2022-09-24 learning the conditional prior over classes for image diffusion
- 2022-08-02 the obsession with sota needs to stop
- 2022-07-24 towards a more sane mac os user experience, and i am late to the party
- 2022-07-11 my notes on discrete denoising diffusion models (d3pms)
- 2021-06-28 training gans the right way