Edvin Fako

Computational Chemistry and Machine Learning | previously: @SchwallerGroup @EPFL | @BASF | @TheorHetCatICIQ | scientific Illustrations when time allows

[Edvin Fako @efssh]

AutoAdsorbate is out in @ACSCatalysis!

Simple Heuristics for Advanced Sampling of Reactive Species on Surfaces

We demonstrate how to get a holistic and unbiased picture of surface reactive species energetics.

Code: https://t.co/p0nfGeDNzc
Paper: https://t.co/RcZnxhmttl

[Kostas Vogiatzis @VogLab]

We are very excited to share our new perspective article on AI for chemical reactivity and catalysis, available now in JACS! This is the outcome of a wonderful discussion with experts in this field #Compchem #MachineLearning #RealTimeChem #Cheminformatics

[J. Am. Chem. Soc. @J_A_C_S]

Boosting Computational Catalysis and Chemical Reactivity with Artificial Intelligence | Journal of the American Chemical Society @EPFL @ETH @ETH_DCHAB @UTKnoxvilleNews @UTKnoxville https://t.co/WhaBrPKx7j

[Junwu Chen @JunwuChen25]

Thrilled to share our new work MatInvent, a general and efficient reinforcement learning workflow that optimizes diffusion models for goal-directed crystal generation. Thanks to @JeffGuo__ , @efssh , @pschwllr , @SchwallerGroup , @NCCR_Catalysis .

https://t.co/S7ibrRNdxp

[Philippe Schwaller (he/him) @pschwllr]

Exciting postdoc opportunity in the @SchwallerGroup at EPFL!

We're hiring a postdoc to advance ML-driven synthesis planning after Zlatko Joncev’s successful exit to co-found B-12 (YC '25) 🚀

Work on:
- LLMs for strategic synthesis planning
- Chemical reasoning at scale
- Building the next-gen framework for retrosynthesis

Our recent preprint shows that LLMs can guide synthesis planning with natural-language strategies — combining AI reasoning with traditional chemical tools (https://t.co/RYVkt5NRYA).

Join us at the intersection of chemistry & AI. Up to 2 years. Based in Lausanne 🇨🇭

Apply: https://t.co/c3Uh1wcRjt

#ChemTwitter #MachineLearning #SynthesisPlanning #PostdocPosition

[Fabian Zills @PythonFZ]

Which foundation MLIP is best suited for your application? The MLIPX framework can help you answering this question. Checkout the Paper https://t.co/YYOfLpchqP and https://t.co/ZFh037oars

#MLIPX

[Philippe Schwaller (he/him) @pschwllr]

Check out the fantastic entries, adsKRK and DynoAgent, from the @SchwallerGroup's LLMs for Materials and Chemistry Applications Hackathon team!

From heterogeneous catalysis to proteins - MD simulations made simple and explainable 🚀

@efssh @XuanVuNguyen18 @6ojaHa Ryo, Salomé, Cassandra, and Jeremy. Proud of you!

Thanks for the global organisation, @BenBlaiszik!
#LLMHackathon #AIMat #AIChem

[Edvin Fako @efssh]

For making the FLOPs count and going (far) beyond physics and chemistry, kudos, @spozdn @pschwllr 🔥

[Sergey Pozdnyakov @spozdn]

High-dimensional linear mappings, or linear layers, dominate both the parameter count and inference cost in most deep learning models. We propose a general-purpose drop-in replacement with a substantially better capacity - inference cost ratio. Check it out!🧵

[Stefan Vučković @stefan_theochem]

🚨 PhD & Postdoc positions in Computational Chemistry 🚨
Funded by SNSF + ERC Starting Grant in my group @unifrChemistry (Fribourg 🇨🇭).
Focus: ML × DFT (method development & applications).
Please RT 🙏
📄 Info & apply: https://t.co/xdrc5LflYf

[Edvin Fako @efssh]

Efficient parametrization of complex surface structures with autoadsorbate:
https://t.co/5IX4BpcCVu

[Edvin Fako @efssh]

Psi-k @Psik_Network was intense & inspiring! Great to meet new & old faces (finally in 3D, not just 2D 😅)! Loved sharing our work on reactive interfaces on the big stage.

Hope our ideas help make sampling complex interfaces a bit easier. Soon more to come from @SchwallerGroup!

[Edvin Fako @efssh]

There is a lot of passion, knowledge, and experience that @ZJoncev @drecmb bring, and it is well reflected in the video! Congrats on the launch!

[Y Combinator @ycombinator]

b-12 (https://t.co/sUMDUAK8TT) is building AI agents that help chemists design experiments and automatically run them on lab robots. They turn months of manual chemistry work into minutes of automated execution.

Congrats on the launch @drecmb & @ZJoncev!

https://t.co/waQzlnrS7z

[Edvin Fako @efssh]

@lars__schaaf After a long and meandering way :) Thank you, Lars, for sharing!

[Edvin Fako @efssh]

@CatAstro_Piyush Yes, I made one, but there are for sure more :)
https://t.co/YJVbgAZeL3

The trick I used was to prepare a xyz trajectory, with aads and ase.mep interpolate. You can find the notebook on git ;)

For more inspiration check out @bradyajohnston

[Edvin Fako @efssh]

Started with some slides for AutoAdsorbate-ended up with an animated deep dive into surface site detection.

It works on any surface, no bulk symmetry needed.
Here’s what this one-liner really does:
s=Surface(slab211)

code: https://t.co/p0nfGeDNzc
paper: https://t.co/3ZdXPgqo3Q

[Edvin Fako @efssh]

@CatAstro_Piyush Exactly :)

[Edvin Fako @efssh]

Here is the notebook I used to prepare the frames:
https://t.co/l9U0PQacZa

After that is just a matter of making things look pretty, with #blenderforscience for example...

Here's a tutorial on that:
https://t.co/pSTFfd6nrj

Enjoy 🫠

[Edvin Fako @efssh]

The idea of what was suposed to be a slide...

Surface atoms: easy to see, hard to define:
- Z-cutoff? Too blunt.
- Coordination? Needs finesse.
- CatKit/Pymatgen? Powerful but opaque.

Surface roughness & reconstructions don't care.
Neither does 🔥AutoAdsorbate🔥!

[Edvin Fako @efssh]

@bradyajohnston @SchwallerGroup Hey Brady, I had my eye on your work for a long time (heard of you through Joe's community showcase). Still haven't had time to dig in, but I'm looking forward to that!

[Edvin Fako @efssh]

Learn how to render multiple molecules from a single multi-frame .xyz file in Blender! 🧪
Hands-on session recording from the AIChemist School: bridging explainable AI and chemistry. @SchwallerGroup

Watch here:
https://t.co/RjoTcnIdrU

More info:
https://t.co/xDEjiKtznB

[Edvin Fako @efssh]

@nuno_bandeira @SchwallerGroup Not sure if there is an out of the box way to do it, but certainly there is a way. Maybe a nice weekend project 🤔