Kjell Jorner

Assistant Professor of Digital Chemistry at @ETH_DCHAB. Leader of the @DCL_ETHZ. Making chemistry more sustainable within @NCCR_Catalysis. Views my own.

[Kjell Jorner @kjelljorner]

I’m incredibly excited, honored and humbled to have been appointed as Assistant Professor of Digital Chemistry at @ETH_en, in @ETH_DCHAB and the Institute for Chemical and Bioengineering. Starting January 2023.

[D-CHAB @ETH_DCHAB]

Welcome at @ETH_DCHAB: Kjell Jorner appointed as Assistant Professor of Digital Chemistry, Yohei Yamauchi as Full Professor of Molecular Medicine. Beat Meier, Full Professor of Physical Chemistry, will retire at the end of Jan. 2023.
https://t.co/aDTeWppuGh

[Poranne Research Group @PoranneG]

We’re hiring! @Aromaticist’s group at @TechnionLive @SchulichT is looking for a Research Associate in #MachineLearning for #Chemistry. Ph.D. required

Send your CV, cover letter and 2 references 📩 [email protected]

#MLforChemistry #AI4Chem #CompChem #Hiring #Science #AI

[Kjell Jorner @kjelljorner]

@RolandDunbrack We’re big fans of the rotamer libraries 🙂

[Malte Franke @maltefranke_]

Check out our work on Grand Canonical Generators👇🏻

[Andreas Burger @atAndreasBurger]

Grand Canonical Generators (GCG)!
Generative sampling of the μVT ensemble <3

[Gabriele Corso @GabriCorso]

Looking forward to this hackathon on Friday in Zurich co-organized with AI4Science Zurich and @merckgroup! I'll be around helping and brainstorming with teams, I'm excited to hear a lot of cool ideas!

Sign up! https://t.co/6ogWObZSTu

[Kjell Jorner @kjelljorner]

@Andrew_S_Rosen @RowanReads Why stop when your own method gets to be the best 😄

[Kjell Jorner @kjelljorner]

@szczepanikgroup Congratulations, that looks great.

[Mario Krenn @MarioKrenn6240]

Want to earn an easy 10,000EUR? Just develop an advanced new optimization algorithm for physical systems. 😊

Join our NeurIPS competition Learn2Design:
https://t.co/hCN9ih0SnN
https://t.co/KElcG6r6mt

The first round of submissions have already beaten (very hard) our own baselines. Now -- the second public evaluation deadline is Sunday, in 4 days.

The top-3 submissions and the two most surprising/creative solutions will get extra cash prices -- as decided by our Scientific Advisory Board:
- Max Dax (ELLIS Institute Tübingen)
- Anna Green (Maastricht University, Nikhef)
- Haixing Miao (Tsinghua University)
- Stephen Wright (University of Wisconsin-Madison)
- @yuqirose (UC San Diego)

[Kjell Jorner @kjelljorner]

@andrewwhite01 @srikosuri Let’s pray that enlightenment comes quickly so that I don’t have to review AI slop for scientific journals anymore 😅

[Riccardo De Santi @r_de_santi]

I’m at #ICML2026 presenting several works on flow and diffusion models for discovery: from theory and algorithms to molecules, peptides, and proteins.

These works have been done with amazing students and collaborators at @ETH_AI_Center, Caltech, KTH, and UPenn, including @maltefranke_ , @KimonProto6689, @yapinghsieh, @cristianpjensen, Sven Gutjahr, Luca Schaufelberger, Zifan Wang, @_sophia_tang_, Bruce Lee, Chenghao Liu, @kjelljorner, Karl Henrik Johansson, @pranamanam, @yisongyue, and @arkrause.

Feel free to reach out if you’d like to chat these days at ICML!

[Kjell Jorner @kjelljorner]

@ruben_laplaza @ChemicalScience Fully agree

[Malte Franke @maltefranke_]

Molecular properties are inherently tied to size, so why fix atom counts? Introducing Morph: a flexible-size generative model for 3D molecule design that learns to insert, delete, substitute and move atoms.🔬

📜Read the pre-print here: https://t.co/8ugO9U3ZsW

A few highlights👇

[Kjell Jorner @kjelljorner]

Check out this very nice work by @maltefranke_. Masterclass in visualization as well!

[Malte Franke @maltefranke_]

Molecular properties are inherently tied to size, so why fix atom counts? Introducing Morph: a flexible-size generative model for 3D molecule design that learns to insert, delete, substitute and move atoms.🔬

📜Read the pre-print here: https://t.co/8ugO9U3ZsW

A few highlights👇

[TheorHetCat ICIQ @TheorHetCatICIQ]

They claim everybody has an interview... this one is mine
Thanks @LaVanguardia Laura Frances and Manel Espinosa
https://t.co/r2isycpB7U

[Riccardo De Santi @r_de_santi]

Very excited to share several works on Flows for Discovery we are presenting at ICLR 2026 🇧🇷. They span new theoretical frameworks for generative optimization, practical and scalable methods for flow-based exploration, as well as applications to molecular design👨‍🔬.

These works have been done with amazing students and collaborators: Kimon Protopapas, @yapinghsieh, Cristian Jensen, @luca_schaufelb, Andrey Kharitenko, @ZebangShen, @maltefranke_ , Zifan Wang and advisors: @kjelljorner, @florian_dorfler, Niao He, Karl Henrik Johansson, and @arkrause.

Feel free to reach out to me or my collaborators if you’d like to chat these days at ICLR!

[NCCR Catalysis @NCCR_Catalysis]

A big thank you to our community, speakers, and partners for making Sustainability Day 2026 a success! 🙌

110+ participants joined discussions on redesigning the chemical value chain—from circularity to data gaps and real-world impact. ♻️📊

Video and key takeaways coming soon!

[Riccardo De Santi @r_de_santi]

A central open problem for generative models in scientific discovery is how to go reliably beyond the observed data distribution—for instance, toward new-to-nature designs—without losing validity.

Very excited to share “Verifier-Constrained Flow Expansion for Discovery Beyond the Data” — a new paper on flow-based exploration for discovery that I will present at ICLR 2026 🇧🇷

We study how entropy exploration and verifier-feedback can be combined to adapt a pre-trained generative model toward new valid regions of a high-dimensional design space. The resulting formulation is principled, scalable, and supported by theory.

Empirically, on a drug-like molecular design task, we expand a pre-trained model increasing both diversity and validity.

Work done with amazing collaborators Kimon Protopapas, @yapinghsieh, and @arkrause. Paper and code in comments!

[JCIM & JCTC Journals @JCIM_JCTC]

Rapid Generation of Transition-State Conformer Ensembles via Constrained Distance Geometry
https://t.co/lARIRRvdzH
@kjelljorner @ETH_DCHAB @DCL_ETHZ @NCCR_Catalysis
#JCIM Vol66 Issue5 #compchem

[NCCR Catalysis @NCCR_Catalysis]

We recently celebrated a few of our PIs for their recent achievements, but what about our 𝗷𝘂𝗻𝗶𝗼𝗿 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵𝗲𝗿𝘀?

At the beginning of their careers, many of them are already making waves!

Congratulations, everyone. 🏆 🏅 🎓 ⚜️
@NCCR_Catalysis

[NCCR Catalysis @NCCR_Catalysis]

Are you passionate about sustainable chemistry & catalysis and planning your Master’s thesis? Apply for our Young Talents Fellowship to conduct your research in our member labs in Switzerland🇨🇭! 🌱🧪🌍
📑 Full info https://t.co/A67hpboBlp
⏰ 30 April 2026
🔁 Much appreciated 🫶🏻