Jonathan Crabbé
Member Of Technical Staff at Latent Labs
London, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolJonathan Crabbé is a Member of Technical Staff at Latent Labs with a PhD in Applied Mathematics from Cambridge and ten years of experience building generative models for scientific discovery. He specializes in GenAI for biology and protein design, where he leads development of frontier diffusion-based models to accelerate drug discovery. Previously he held research internships and a contractor role at Apple and Microsoft, contributing to publications on multimodal robustness and a Nature paper on generative material design. His background blends rigorous theory with applied ML—discrete diffusion for atom/sequence assignment and robustness analysis of CLIP-style models. Based in London, he also creates widely used educational content through a popular YouTube channel that grew to over 100k subscribers, reflecting a talent for communicating complex STEM topics. Colleagues describe him as a research-minded engineer who moves ideas from papers into production-ready models.
10 years of coding experience
1 year of employment as a software developer
M1 ICFP Physics, M1 ICFP Physics at Ecole normale supérieureDoctor of Philosophy - PhD Applied Mathematics, Doctor of Philosophy - PhD Applied Mathematics at University of CambridgeBachelor of Engineering - BE Physics Engineering, Bachelor of Engineering - BE Physics Engineering at Université libre de Bruxelles
English, French
Github Skills (21)
representation-learning10
variational-autoencoder10
interpretable-machine-learning10
representations10
simplex9
xai9
artificial-intelligence9
fourier-transform9
frequency-domain9
unsupervised-learning9
information-theory9
corpus8
robustness8
machine-learning8
diffusion-models8
Programming languages (2)
Github contributions (5)
JonathanCrabbe/Label-Free-XAI
Nov 2021 - Sep 2022
This repository contains the implementation of Label-Free XAI, a new framework to adapt explanation methods to unsupervised models. For more details, please read our ICML 2022 paper: 'Label-Free Explainability for Unsupervised Models'.
Contributions:73 commits, 1 PR, 2 pushes in 10 months
xaiartificial-intelligenceautoencodersexplainable-aiinterpretability
JonathanCrabbe/Symbolic-Pursuit
Oct 2020 - Feb 2021
Github for the NIPS 2020 paper "Learning outside the black-box: at the pursuit of interpretable models"
Contributions:38 commits, 29 pushes, 1 comment in 4 months
pytorchpursuitboxinterpretable-modelsdeep-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.