Conor Durkan (@conormdurkan) / X

I’m excited to join @DeepMind as a research scientist next week :)

Jan 3, 2025

I like the Bayesian framing of reward-based post-training (i.e. reward-maximization with a KL penalty). Up to an additive constant, reward functions are log-likelihoods, and the pre-trained model is a prior. Then the posterior target is the product of the likelihoods and prior

"On Maximum Likelihood Training of Score-Based Generative Models" -- a new technical note with @YSongStanford showing how score-based generative models can be fit using maximum likelihood. 1/7

arxiv.org

Maximum Likelihood Training of Score-Based Diffusion Models

Score-based diffusion models synthesize samples by reversing a stochastic process that diffuses data to noise, and are trained by minimizing a weighted combination of score matching losses. The...

Conor Durkan

@conormdurkan

Jun 26, 2020

In motivating their 'grad' API, the JAX docs point to the prologue of 'Functional Differential Geometry' (mitpress.mit.edu/books/function…), which shows how the Euler-Lagrange equations can be written in a purely functional form, and is worth a read.

mitpress.mit.edu

Book Details

MIT Press - Book Details Analysis of the epistemic dynamics created via the financialization of translational medicine and the effects of socializing private sector R&D risk. Translational Thinking...

Conor Durkan

@conormdurkan

Feb 18, 2025

I'm rejoining @GoogleDeepMind in NYC this week, looking forward to catching up with folks :)

"On Contrastive Learning for Likelihood-free Inference" - new work with @driainmurray and @gpapamak. arxiv.org/abs/2002.03712

Conor Durkan

@conormdurkan

Apr 11, 2024

I'm delighted to launch Udio this week with fantastic co-founders @DavidDingAI @charlietcnash @yaroslav_ganin @avincentsanchez I've wanted to work on music models for a long time, and it's pretty surreal to this in the wild. It's also been great to work on something that's just

udio

@udiomusic

Apr 10, 2024

Introducing Udio, an app for music creation and sharing that allows you to generate amazing music in your favorite styles with intuitive and powerful text-prompting. 1/11

00:00

This paper addresses a major drawback of likelihood-based generative models, which traditionally assume a distribution with full support in the ambient data space, whereas we believe this is likely not the case for highly-structured data like e.g. images. Very exciting work.

Kyle Cranmer

@KyleCranmer

Jun 4, 2020

Johann & I released v2 of our paper "Flows for simultaneous manifold learning and density estimation" with more experiments. We dubbed the class of model ℳ-Flows Here you see the flow learning the 2d manifold and the density for the Lorenz attractor! 1/n arxiv.org/abs/2003.13913

GIF

Conor Durkan

@conormdurkan

Nov 16, 2023

This model has a magical quality that’s hard to convey without trying it yourself. It’s musical and idiomatic in ways that I thought were years away. It was an extraordinary thing to work on.

Google DeepMind

@GoogleDeepMind

Nov 16, 2023

Today with @YouTube, we’re announcing Lyria: our most advanced music generation model to date. 🎶 We’re also releasing 2️⃣ AI experiments in close collaboration with participating artists and creators to bring their ideas to life responsibly. → deepmind.google/discover/blog/…

GIF

Chatting with Flamingo about images is definitely the most organic experience I’ve had with an ML model. The ability to readily describe output from e.g. DALL-E 2 might be the closest we’ve come to two independently-trained large-scale models having a conversation 👀

Google DeepMind

@GoogleDeepMind

Apr 28, 2022

Introducing Flamingo 🦩: a generalist visual language model that can rapidly adapt its behaviour given just a handful of examples. Out of the box, it's also capable of rich visual dialog. Read more: dpmd.ai/dm-flamingo 1/

Conor Durkan

@conormdurkan

Jun 3, 2020

Replying to @fhuszar

Hectic few weeks for Noah.

Conor Durkan

@conormdurkan

Jun 8, 2020

"On Contrastive Learning for Likelihood-free Inference" will appear at ICML 2020. #icml2020

Conor Durkan

@conormdurkan

Feb 11, 2020

"On Contrastive Learning for Likelihood-free Inference" - new work with @driainmurray and @gpapamak. arxiv.org/abs/2002.03712

Conor Durkan

@conormdurkan

Sep 4, 2019

Neural Spline Flows has been accepted to @NeurIPSConf! #NeurIPS2019

Conor Durkan

@conormdurkan

Jun 11, 2019

Neural spline flows replace affine transformations in coupling and autoregressive layers with flexible monotonic rational-quadratic splines, significantly boosting density estimation performance without sacrificing analytic invertibility.

Conor Durkan

@conormdurkan

Jan 3, 2025

Replying to @conormdurkan

2K