Conor Durkan
I am a co-founder at Udio, a generative music company based in New York. At Udio I’m responsible for core model development, exploring the state-of-the-art in generative music technology.
I was previously a senior research scientist at DeepMind in London, where I worked on large-scale media modeling, including Imagen 2 and Lyria.
Prior to that, I completed my PhD in machine learning at the University of Edinburgh. My thesis primarily focused on methods for generative modeling, with some applications to likelihood-free inference.
Research
Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
Yilun Du, Conor Durkan, Robin Strudel, Joshua B Tenenbaum, Sander Dieleman, Rob Fergus, Jascha Sohl-Dickstein, Arnaud Doucet, Will Grathwohl
International Conference on Machine Learning, 2023
[arXiv]
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 Reblond,
Will Grathwohl,
Jonas Adler
Pre-print, 2022
[arXiv]
Maximum Likelihood Training of Score-Based Diffusion Models
Yang Song, Conor Durkan, Iain Murray, Stefano Ermon
Advances in Neural Information Processing Systems (Spotlight), 2021
[arXiv] [GitHub]
On Contrastive Learning for Likelihood-free Inference
Conor Durkan, Iain Murray, George Papamakarios
International Conference on Machine Learning, 2020
[arXiv] [GitHub]
Neural Spline Flows
Conor Durkan, Artur Bekasov, Iain Murray, George Papamakarios
Advances in Neural Information Processing Systems, 2019
[arXiv] [GitHub]
Cubic-Spline Flows
Conor Durkan, Artur Bekasov, Iain Murray, George Papamakarios
1st workshop on Invertible Neural Networks and Normalizing Flows (ICML), 2019
[arXiv]
[GitHub]
Autoregressive Energy Machines
Charlie Nash, Conor Durkan
International Conference on Machine Learning [Oral], 2019
[arXiv] [GitHub]
Sequential Neural Methods for Likelihood-free Inference
Conor Durkan, George Papamakarios, Iain Murray
3rd workshop on Bayesian Deep Learning (NeurIPS). 2018
[arXiv]