From Sudan to Silicon Valley: Beyond the Resume link.medium.com/A2UhOn726Nb

We are happy to announce the Oxford LoG meet-up, LoG-Ox! The event is free to attend and will happen on November 25th. We plan to have keynote talks, lightning talks, posters and socials. More information and signup form is available here: log-ox.github.io. Learning on Graphs Conference 2024

⁦Learning on Graphs Conference 2025⁩ Oxford meet up ⁦@jacobbamberger⁩

*Relaxed Equivariance via Multitask Learning* by Ahmed Elhag Konstantin Rusch Francesco Di Giovanni Michael Bronstein They propose a regularization approach for exploiting symmetries over data (penalizing variable predictions over augmented data). arxiv.org/abs/2410.17878

The best place I’ve been in the new year

⁦Naamii Nepal⁩ AI winter school was a blast—thanks for the invitation and for listening to Oxford lecturers on a high horse (literally). I am grateful to my PhD students for being great companions in teaching and traveling and making it a most memorable experience.

It’s a great pleasure to be part of a wonderful team in an amazing program! Thanks for the chance! And at this point, it seems that someone convinced me to get back to horses :)

Thuerey Group at TUM Nice work and cool results! FWIW you can train a diffusion model directly in data space (and with general geometries) without requiring to compress data into a latent space arxiv.org/abs/2305.15586. Perhaps Fig. 17 is the closest to your experimental setting (cc Ahmed Elhag)

Are you at ICLR in Singapore this week 🇸🇬? Pls feel free to connect & get in touch! We will also present our recent work on learning symmetries as a spotlight in ML for genomics workshop (MLGenX), Sun 27/4! Looking forward to it!

Brownian path

Hi, Singapore!

Photos speak a lot more than words. What is happening in El Fasher is one example of the war in Sudan, that is entering its third year now. RSF and whoever backed them, what do you call it, when you’re the criminal and the documenter? Probably terrorism is too small word for this