Malte Franke
banner
maltefranke.bsky.social
Malte Franke
@maltefranke.bsky.social
Generative models for chemistry and materials science

Currently PhD student at ETH Zürich
Previously Dunia, MIT, EPFL, RWTH Aachen
Reposted by 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)
May 14, 2025 at 9:18 AM
Reposted by Malte Franke
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...
PhD position in machine learning for photocatalysis
jobs.ethz.ch
May 13, 2025 at 8:15 AM
Reposted by Malte Franke
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...
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...
pubs.rsc.org
May 12, 2025 at 9:27 PM
Reposted by Malte Franke
New blog post: let's talk about latents!
sander.ai/2025/04/15/l...
Generative modelling in latent space
Latent representations for generative models.
sander.ai
April 15, 2025 at 9:40 AM
Reposted by Malte Franke
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)
Directly optimizing for synthesizability in generative molecular design using retrosynthesis models - Chemical Science (RSC Publishing) DOI:10.1039/D5SC01476J
pubs.rsc.org
March 24, 2025 at 5:28 AM
Reposted by Malte Franke
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
March 18, 2025 at 8:07 PM
Reposted by Malte Franke
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...
Overcoming Academic Impostor Syndrome
bastian.rieck.me
March 13, 2025 at 2:40 PM
Reposted by Malte Franke
🚀 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 👇
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...
arxiv.org
March 3, 2025 at 9:06 AM
Good news for AI research in Europe🇪🇺
February 11, 2025 at 8:12 PM
Reposted by Malte Franke
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!
Homepage - DCL
dcl.ethz.ch
January 27, 2025 at 1:54 PM
Reposted by Malte Franke
Last week to apply for this position in my group!
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...
PhD position in digital ligand engineering for nanocatalysis
jobs.ethz.ch
December 31, 2024 at 9:57 AM
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)
Drifting to sleep pondering - "the torus is the cartesian product of two circles" as part of an intro to Morse Theory.

Saturday morning coffee "rabbit holing" - beautiful illustration from "Introduction to Topology" by Mendelson.

Wow. Why not teach this in middle school?

#MathSky #topology
December 15, 2024 at 5:34 PM
Reposted by Malte Franke
⚛️🤗 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...
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.
huggingface.co
December 11, 2024 at 4:49 PM
Reposted by Malte Franke
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...
PhD position in digital ligand engineering for nanocatalysis
jobs.ethz.ch
December 10, 2024 at 3:29 PM
Reposted by Malte Franke
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
December 6, 2024 at 12:50 PM
Reposted by Malte Franke
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.
December 2, 2024 at 6:45 PM
Reposted by Malte Franke
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
December 2, 2024 at 10:33 AM
Reposted by Malte Franke
One week left to apply to this position in my group.
What better first post than to advertise this position. Come join our group!

Our group is recruiting a postdoctoral researcher for a project on reactive machine learning potentials. Reposts and spreading the word to interested people in your network appreciated!

jobs.ethz.ch/job/view/JOP...
Postdoc position in reactive machine learning potentials
jobs.ethz.ch
November 29, 2024 at 1:18 PM
Reposted by Malte Franke
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
November 27, 2024 at 9:00 AM