Sign in

Iain Murray

@imurray.bsky.social
2.4K followers 482 following 10 posts

Professor of Machine Learning and Inference, Edinburgh Informatics, Formerly Amazon Scholar. Opinions are my own. Also homepages.inf.ed.ac.uk/imurray2 and mastodon.social/@imurray and x.com/driainmurray

PostsRepliesMedia
Iain Murray @imurray.bsky.social · 08/08/2026
Sharing this postdoc opportunity at Imperial to develop and apply machine-learning and structural-bioinformatics methods for protein design, with focus on modern generative approaches such as protein diffusion models and flow-based models.
imperial.ac.uk
Description
Please note that job descriptions are not exhaustive, and you may be asked to take on additional duties that align with the key responsibilities ment...
044
Iain Murray @imurray.bsky.social · 12/01/2026
My department in Edinburgh is hiring a lecturer (assistant prof) in Software Engineering: elxw.fa.em3.oraclecloud.com/hcmUI/Candid...
elxw.fa.em3.oraclecloud.com
Lecturer in Software Engineering
The School of Informatics, University of Edinburgh invites applications for a Lecturer in Software Engineering. To develop an innovative independent, research programme in Software Engineering; develo...
089
Iain Murray @imurray.bsky.social · 03/05/2025
The 13x13 grid became 14x14. It's really hard to get image models to make a board with the correct number of evenly spaced lines and star points. I'd thought it might copy a reference board into a scene, but it can't even do a simple copy, showing limits to guidance that's possible with this model.
010
Iain Murray @imurray.bsky.social · 02/05/2025
Image models struggle to create Go boards correctly. I thought ChatGPT may be able to copy a correct one into a scene, but conditioning the model is through too small a bottleneck. "Please copy this image exactly to create a new image. Every line and stone should appear in exactly the same places."
A screenshot of a virtual 13x13 go board with some go stones on it.ChatGPT's reconstruction of a 13x13 go board is actually 14x14 and it has changed the configuration of the stones.
1151
Iain Murray @imurray.bsky.social · 29/11/2024
Standard normalizing flows are "approximate" too: e.g., standard implementations are often not exactly invertible in practice. But ODE solvers can use adaptive computations to control the errors. So they're not intractable in the same way that (say) a Boltzmann machine is.
190
Iain Murray @imurray.bsky.social · 20/11/2024
@ramandutt4.bsky.social 👋
230
Iain Murray @imurray.bsky.social · 18/11/2024
I do ML + Bayesian inference.
0100
Iain Murray @imurray.bsky.social · 18/11/2024
Yes please.
100
Iain Murray @imurray.bsky.social · 18/11/2024
Yes please.
110
Iain Murray @imurray.bsky.social · 18/11/2024
👋
110