Malte Franke

Generate property-optimized small molecules with 𝘴𝘵𝘦𝘦𝘳𝘢𝘣𝘭𝘦 𝘢𝘯𝘥 𝘨𝘳𝘢𝘯𝘶𝘭𝘢𝘳 synthesizability control - allowing complete user-flexibility to impose various reaction constraints!

Pre-print: arxiv.org/abs/2505.08774
Code: github.com/schwallergro...

(1/4)

PhD position in machine learning for photocatalysis

We are recruiting a PhD student in machine learning for photocatalysis! In this project, we will collaborate with the group of Frank Glorius @gloriusgroup.bsky.social to develop predictive tools for energy-transfer-catalyzed photocycloadditions.

Reposts appreciated!
jobs.ethz.ch/job/view/JOP...

Symmetry-constrained generation of diverse low-bandgap molecules with Monte Carlo tree search Organic optoelectronic materials are a promising avenue for next-generation electronic devices due to their solution processability, mechanical flexibility, and tunable electronic properties. In parti...

Out in @chemicalscience.rsc.org!
We constrain the molecular generation space to follow the "symmetry" of molecules from patents. Achieved with "symmetry-aware" fragment decomposition, and a constrained Monte Carlo Tree Search generator.
@rgblabmit.bsky.social
pubs.rsc.org/en/Content/A...

Wishing you a great start!🚀

Generative modelling in latent space Latent representations for generative models.

New blog post: let's talk about latents!
sander.ai/2025/04/15/l...

Check out our paper published in @chemicalscience.rsc.org - pubs.rsc.org/en/content/a...

(1) *General-purpose* generative model + retrosynthesis model = design molecules with optimized properties with an *explicit* predicted synthesis pathway

(1/2)

People are rushing to apply AI to discover materials for applications in health, energy, aerospace and more. Are we the cool kids now?

- Lila => $200M
- OpenAI VP => AI+materials company
- Cusp => $30M
- RadicalAI automating materials discovery
- FutureHouse scientific agents

New blog post on overcoming academic impostor syndrome. This arose from great discussions during our group retreat, and I decided to make it publicly available in the hope of providing some utility to #academia.

#AcademicSky #AcademicChatter

bastian.rieck.me/blog/2025/im...

One Set to Rule Them All: How to Obtain General Chemical Conditions via Bayesian Optimization over Curried Functions General parameters are highly desirable in the natural sciences - e.g., chemical reaction conditions that enable high yields across a range of related transformations. This has a significant practical...

🚀 Looking for reaction conditions that work well for multiple substrates? CurryBO can help🍛

Now out on arXiv: arxiv.org/abs/2502.18966

A short explanation thread 👇

Good news for AI research in Europe🇪🇺

Homepage - DCL

Digital Chemistry Laboratory is excited to be on BlueSky 👋

We are a research group at ETH Zurich led by @valencekjell.com that develops digital solutions to chemical problems in catalysis and molecular design 🖥️ 🧪

More about us: dcl.ethz.ch

See you here for the news and research updates!

Last week to apply for this position in my group!

What Is Entropy? A Measure of Just How Little We Really Know. | Quanta Magazine Exactly 200 years ago, a French engineer introduced an idea that would quantify the universe’s inexorable slide into decay. But entropy, as it’s currently understood, is less a fact about the world th...

www.quantamagazine.org/what-is-entr...

I am not familiar with cover spaces. However, I can see a parallel to optimal packing which is quite relevant to chemistry/ materials, e.g. to determine how many molecules can fit into a porous material. Not sure if that's what you're looking for though

Great figure indeed - makes it very intuitive how tori can model periodicity! In my field, we can leverage tori e.g. to design periodic materials (arxiv.org/abs/2406.04713) or to represent torsion angles in molecular conformer generation (arxiv.org/abs/2206.01729)

LeMaterial: an open source initiative to accelerate materials discovery and research We’re on a journey to advance and democratize artificial intelligence through open source and open science.

⚛️🤗 Announcing LeMaterial ⚛️🤗

@hf.co & @entalpic.bsky.social are teaming up to release LeMaterial -- an open source initiative aiming to facilitate (AI for) materials discovery !

Datasets, hash function, tools to explore the chemical space & more !

huggingface.co/blog/lemater...

PhD position in digital ligand engineering for nanocatalysis

Another chance to join our group! We are recruiting a PhD student in digital ligand engineering for nanocatalysis. Reposts and spreading the word to interested people in your network appreciated!
jobs.ethz.ch/job/view/JOP...

I will be at #NeurIPS next week, presenting work on Bayesian Optimization over curried functions at the AI4Mat workshop. We use it to identify general reaction conditions (see below)

If you are around and interested in talking #BayesOpt or #AI4Science, let’s meet

A common question nowadays: Which is better, diffusion or flow matching? 🤔

Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.

We are hiring (resharing appreciated)!

Given recent successful grant applications (I got my SNSF Starting Grant 🚀), we are extending the LIAC team with multiple openings (PhD/postdoc) for 2025.

Apply now (deadline: December 20th) by filling in this form: forms.fillout.com/t/eq5ADAw3kkus.
#ChemSky

One week left to apply to this position in my group.

Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!

We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423