My recent work at DeepMind and Udio hasn't been published publicly, so this page is a bit outdated.
Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
International Conference on Machine Learning 2023
Continuous Diffusion for Categorical Data
Sander Dieleman, Laurent Sartran, Arman Roshannai, Nikolay Savinov, Yaroslav Ganin, Pierre H. Richemond, Arnaud Doucet, Robin Strudel, Chris Dyer, Conor Durkan, Curtis Hawthorne, Rémi Leblond, Will Grathwohl, Jonas Adler Pre-print 2022
Maximum Likelihood Training of Score-Based Diffusion Models
Advances in Neural Information Processing Systems Spotlight 2021
On Contrastive Learning for Likelihood-free Inference
International Conference on Machine Learning 2020
Neural Spline Flows
Advances in Neural Information Processing Systems 2019
Cubic-Spline Flows
1st workshop on Invertible Neural Networks and Normalizing Flows (ICML) 2019
Autoregressive Energy Machines
International Conference on Machine Learning Oral 2019
Sequential Neural Methods for Likelihood-free Inference
3rd workshop on Bayesian Deep Learning (NeurIPS) 2018