Marwin Segler
banner
marwinsegler.bsky.social
Marwin Segler
@marwinsegler.bsky.social
Machine Learning, {Org, Med, Comp} Chem, RL/Planning, AI-assisted Scientific Discovery & Creativity, Music. ELLIS Scholar. Team Lead at Microsoft Research AI for Science. 2xDad
Pinned
new preprint on chemical synthesis ML models

- showing how to combine multiple models in a principled way
- modern Transformers + GNN to featurize chemical reaction:
- new insights in where the models shine
+ bonus: find the quirky named reaction!

Feedback welcome!

arxiv.org/abs/2412.05269
Chimera: Accurate retrosynthesis prediction by ensembling models with diverse inductive biases
Planning and conducting chemical syntheses remains a major bottleneck in the discovery of functional small molecules, and prevents fully leveraging generative AI for molecular inverse design. While ea...
arxiv.org
Reposted by Marwin Segler
Save the date! Next year's European #RDKit UGM will take place from 16-18 September in Darmstadt, Germany.
Pre-registration will open in early 2026.
October 21, 2025 at 3:25 PM
Reposted by Marwin Segler
Do you want to invent the future of Chemistry with us? We‘re looking for a "Digital Native” Organic Chemist to join our team at Microsoft Research AI for Science. We offer an amazing environment where you can do deep research with passionate and talented colleagues to solve problems that matter! 1/2
October 16, 2025 at 10:06 PM
Reposted by Marwin Segler
Are you a PhD student interested in ML and biology or health? Come do an internship with me, @avapamini.bsky.social, Alex Lu, @lcrawford.bsky.social, or Kristen Severson at MSRNE!

Applications are due Dec 1: make sure you include a research statement!

jobs.careers.microsoft.com/global/en/jo...
Search Jobs | Microsoft Careers
jobs.careers.microsoft.com
October 21, 2025 at 7:32 PM
Do you want to invent the future of Chemistry with us? We‘re looking for a "Digital Native” Organic Chemist to join our team at Microsoft Research AI for Science. We offer an amazing environment where you can do deep research with passionate and talented colleagues to solve problems that matter! 1/2
October 16, 2025 at 10:06 PM
Reposted by Marwin Segler
Want to join our efforts @msftresearch.bsky.social AI for Science to push the frontier of AI for materials? We are the team behind MatterGen & MatterSim and we have 2 job openings! Each can be in Amsterdam, NL, Berlin, DE, or Cambridge, UK.
Search Jobs | Microsoft Careers
jobs.careers.microsoft.com
July 31, 2025 at 2:36 PM
Reposted by Marwin Segler
We may have the chance to hire an outstanding researcher 3+ years post PhD to join Tarleton Gillespie, Mary Gray and me in Cambridge MA bringing critical sociotechnical perspectives to bear on new technologies.

jobs.careers.microsoft.com/global/en/jo...
Search Jobs | Microsoft Careers
https://jobs.careers.microsoft.com/global/en/job/1849026/Principal-Researcher-–-Sociotechnical-Systems-–-Microsoft-Research
July 28, 2025 at 5:26 PM
Reposted by Marwin Segler
I put this up at the old place in 2019 when we did our Periodic Table anniversary special issue, with my own added lyrics for all the post-Nobelium elements

chemsky
July 27, 2025 at 8:55 PM
Reposted by Marwin Segler
New work from my team! arxiv.org/abs/2507.12950
Intersecting mechanistic interpretability and health AI 😎

We trained and interpreted sparse autoencoders on MAIRA-2, our radiology MLLM. We found a range of human-interpretable radiology reporting concepts, but also many uninterpretable SAE features.
Insights into a radiology-specialised multimodal large language model with sparse autoencoders
Interpretability can improve the safety, transparency and trust of AI models, which is especially important in healthcare applications where decisions often carry significant consequences. Mechanistic...
arxiv.org
July 18, 2025 at 9:30 AM
Reposted by Marwin Segler
Özçelik et al (2025) Generative Deep Learning for de Novo Drug Design─A Chemical Space Odyssey. JCIM ASAP #cheminformatics #CompChem #ML #AI #OpenAccess #chemsky 🧪
doi.org/10.1021/acs....
Generative Deep Learning for de Novo Drug Design─A Chemical Space Odyssey
In recent years, generative deep learning has emerged as a transformative approach in drug design, promising to explore the vast chemical space and generate novel molecules with desired biological pro...
doi.org
July 18, 2025 at 6:48 AM
Reposted by Marwin Segler
I am very happy to share Orbformer, a foundation model for wavefunctions using deep QMC that offers a route to tackle strongly correlated quantum states!
arxiv.org/abs/2506.19960 (1/n)
An ab initio foundation model of wavefunctions that accurately describes chemical bond breaking
Reliable description of bond breaking remains a major challenge for quantum chemistry due to the multireferential character of the electronic structure in dissociating species. Multireferential method...
arxiv.org
June 26, 2025 at 8:58 AM
One for #compchemsky
🚀 After two+ years of intense research, we’re thrilled to introduce Skala — a scalable deep learning density functional that hits chemical accuracy on atomization energies and matches hybrid-level accuracy on main group chemistry — all at the cost of semi-local DFT ⚛️🔥🧪🧬
June 18, 2025 at 11:51 AM
Reposted by Marwin Segler
🚀 After two+ years of intense research, we’re thrilled to introduce Skala — a scalable deep learning density functional that hits chemical accuracy on atomization energies and matches hybrid-level accuracy on main group chemistry — all at the cost of semi-local DFT ⚛️🔥🧪🧬
June 18, 2025 at 11:24 AM
Reposted by Marwin Segler
Alright, people, let's be honest: GenAI systems are everywhere, and figuring out whether they're any good is a total mess. Should we use them? Where? How? Do they need a total overhaul?

(1/6)
June 15, 2025 at 12:20 AM
Reposted by Marwin Segler
This week's cover of @rsc.org @chemicalscience.rsc.org AIMNet2: a neural network potential to meet your neutral, charged, organic, and elemental-organic needs. pubs.rsc.org/en/content/a... #compchem #chemsky
June 11, 2025 at 6:18 PM
Reposted by Marwin Segler
Very excited to be recruiting for an Associate Principal Scientist: Molecular Modeling, Analytical Research & Develop. Our Digital Sciences team is seeing many requests related to influencing formulation design, especially for biologics. #chemjobs #compchem #chemsky jobs.merck.com/us/en/job/R3...
Associate Principal Scientist: Molecular Modeling, Analytical Research & Development job in Rahway, New Jersey, United States of America | jobs at Merck migration
Apply for Associate Principal Scientist: Molecular Modeling, Analytical Research & Development job with Merck migration in Rahway, New Jersey, United States of America. Browse and apply for the jobs a...
jobs.merck.com
June 7, 2025 at 10:46 AM
Reposted by Marwin Segler
We have several open, fully-funded PhD and Postdoc positions at my group, now at the University of Tübingen. Please #RT and share with potential candidates!

Generally: AI for scientific discoveries in physics 🔥.
mariokrenn.wordpress.com/wp-content/u...
mariokrenn.wordpress.com
May 27, 2025 at 11:25 PM
Reposted by Marwin Segler
🚨 Brand new postdoctoral researcher position in my group at Princeton! Please apply or share with anyone interested in computational materials science and being an electron whisperer! puwebp.princeton.edu/AcadHire/app....
puwebp.princeton.edu
May 22, 2025 at 8:42 PM
Reposted by Marwin Segler
As chemical data grows, turning names into machine-readable structures is key for discovery, automation, and data integration.

OPSIN – now hosted at EMBL-EBI – helps solve this by converting IUPAC names into chemical structures and other machine-readable formats.

www.ebi.ac.uk/about/news/u...
OPSIN chemical name-to-structure tool moves to EMBL-EBI
The Open Parser for Systematic IUPAC Nomenclature (OPSIN) allows users to convert chemical names into structures and machine-readable formats.
www.ebi.ac.uk
May 21, 2025 at 2:40 PM
Back in Züri 😎
May 17, 2025 at 7:33 PM
Reposted by Marwin Segler
TENURE TRACK PROFESSORSHIP in Reinforcement Learning announced at Johannes Kepler University Linz.

Three other ML/AI tenure tracks also open.

www.jku.at/en/the-jku/w...
Reinforcement Learning
www.jku.at
May 9, 2025 at 8:06 AM
Not the greatest weather at Bürgenstock, but amazing discussions & science throughout!
May 8, 2025 at 8:18 AM
Reposted by Marwin Segler
🎉The Phi-4 reasoning models have landed on HF and Azure AI Foundry. The new models are competitive and often outperform much larger frontier models. It is exciting to see the reasoning capabilities extend to more domains beyond math, including algorithmic reasoning, calendar planning, and coding.
May 1, 2025 at 12:50 AM