Ross Irwin

Thrilled to announce that the first paper from Flemming's PhD was accepted as Poster for NeurIPS2025! In this paper we adapt the HollowNet idea from Chen and Duvenaud to equivariant MP networks, to get cheap sample likelihoods for flow-based Boltzmann Generators. Preprint/code coming soon.

Looks great! Do you have a rough timeline for releasing the full dataset?

AIME Machine Learning ∩ Chemistry ∩ Life Sciences

P.S. We're opening 2 PhD positions very soon! If you're into AI for molecules and thinking about a PhD in drug and/or materials design, stay tuned @ ailab.bio 👀

Most of our extended team (including co-supervised students) posing in front of the propeller at Chalmers after the rain stopped.

Richard drawing on the board while the team listens and gives feedback.

Yossra giving her project pitch while the team listens.

The extended team + our guest Dr. Filip Miljković on the stairs in the physics building at Chalmers.

Had a great team workshop yesterday at Chalmers. A full day of getting to know each other better, discussing research, and brainstorming. I'm really proud of the team, the passion and supportive energy they bring, and the environment we've built together over the last couple years!

SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matching Methods for jointly generating molecular graphs along with their 3D conformations have gained prominence recently due to their potential impact on structure-based drug design. Current approaches, howe...

Paper -> arxiv.org/abs/2406.07266
Code -> github.com/rssrwn/semla...

I’ll be at AISTATS presenting our work on designing efficient and scalable equivariant models for 3D molecular generation. You can find me at poster session 2, no 132. Also very happy to meet up during the conference!

Join us in Gothenburg for the 3rd CHAIR Structured Learning Workshop! Very exciting line-up of speakers and we expect lots of engaging discussions, too. Attendance is free but you need to apply as we have limited slots.

2025 CHAIR Structured Learning Workshop Welcome to the 2025 Chalmers AI Research Center Workshop for Structured Learning. In this workshop we broadly cover topics related to Structured Learning targeting specifically the following questions...

Registration for this years CHAIR Structured Learning Workshop is open. Speakers include: Klaus Robert Müller, Jens Sjölund, @alextong.bsky.social ,
@janstuehmer.bsky.social, @arnauddoucet.bsky.social, @marcocuturi.bsky.social , Marta Betcke,
Elena Agliari, Beatriz Seoane, Alessandro Ingrosso

Looks great! Will def check it out

Excited to present our poster on Boltzmann priors for Implicit Transfer Operators tomorrow at @iclr-conf.bsky.social!
See you tomorrow at poster 13, 10-12:30.

Check out cool new work from our group in collaboration with Pfizer and AstraZeneca, lead by Julian Cremer and Ross Irwin on FLOWR, a flow-based ligand generation approach, and highly sanitized benchmark dataset, SPINDR, for the SBDD community!

Overview of the RetroSynFormer architecture.

Check out RetroSynFormer, a Decision Transformer model for multi-step retrosynthesis planning. Developed with an industrial PhD student in my team, Emma Granqvist, and her AstraZeneca co-supervisor Samuel Genheden, RetroSynFormer reframes retrosynthesis as a sequence modeling task. (1/2)

Industrial PhD student in Data-Driven Life Sciences Industrial PhD student in Data-Driven Life Sciences Are you passionate about applying computational approaches to solve problems within chemistry and biology? We are now looking for an Industrial PhD ...

Industry PhD opportunity: together with AstraZeneca, we’re recruiting an industial PhD student in data-driven life sciences to join us here in Gothenburg, SE! Deadline to apply April 24. More info in ad: www.scilifelab.se/career/indus...

The Chalmers AI4Science speakers for the spring term have just been announced please check the homepage for all the details: psolsson.github.io/AI4ScienceSe...

1/1 Papers accepted at ICLR2025 Congrats @viguera10.bsky.social and 1/1 papers accepted at AISTATS2025 congrats @rossirwin.bsky.social

Come join us on an exciting joint PhD project on ML for protein function with @kailalab.bsky.social -- We are looking for a strong quantitative candidate with prior experience in ML. The position is based in Gothenburg and is fully funded for 5 years.

www.chalmers.se/en/about-cha...

Really nice paper! The expert comparisons seem like a very useful addition to the usual accuracy metrics

Impressive work by @franknoe.bsky.social and team! A pragmatic tour-de-force combining experimental and predicted protein structures, MD simulations and experimental stability data to sample conformational ensembles of proteins. Think AlphaFold, but capturing multiple free energy minima.