@drecmb Profile picture

Andrés M Bran

@drecmb

PhD student @SchwallerGroup @EPFL | Previously intern @mpiMathSci. I like to travel sometimes! 🇨🇴

Similar User
LIAC at EPFL photo

@SchwallerGroup

Miruna Cretu photo

@MirunaCretu2

Puck van Gerwen photo

@puckvg

Teodoro Laino photo

@teodorolaino

Kevin M Jablonka photo

@kmjablonka

Philippe Schwaller (he/him) photo

@pschwllr

Oliver Schilter photo

@OSchilter

Rubén Laplaza photo

@ruben_laplaza

Kjell Jorner photo

@kjelljorner

BOjana Ranković photo

@6ojaHa

Rebecca Neeser photo

@RebeccaNeeser

Derek van Tilborg photo

@DerekvTilborg

Jeff Guo photo

@JeffGuo__

Andrew White 🐦‍⬛ photo

@andrewwhite01

Malte Franke photo

@maltefranke_

Pinned

New version of ChemCrow out 🔥🔥 arxiv.org/abs/2304.05376 The LLM-powered chemistry assistant got major updates 💪 What's new? Robots synthesizing stuff, human/crow collaboration, novel molecules, safety, new evaluations + open source release! 🤩 See more 👇 1/8 #compchem

Tweet Image 1

Andrés M Bran Reposted

We’ve released an improved version of SynFlowNet! SynFlowNet can now handle large action spaces (up to 220k building blocks) and we experiment with training different GFlowNet backward policies. (1/3) arXiv: arxiv.org/abs/2405.01155 code: github.com/mirunacrt/synf…


Andrés M Bran Reposted

FSscore has now been published in Chemistry-Methods (@ChemEurope)! 🚀 Check out the updated paper on personalized synthesizability scoring here: …mistry-europe.onlinelibrary.wiley.com/doi/10.1002/cm…

1/5 🌟 Thrilled to present our new work on predicting the synthesizability of small molecules this Saturday in the #AI4Science workshop at #NeurIPS2023 ! Thanks to my supervisors @pschwllr (@SchwallerGroup ) and @befcorreia 🧵 schwallergroup.github.io/fsscore/FSscor…



Andrés M Bran Reposted

Excited to share our preprint on a scalable ML optimisation framework applied to automated HTE reaction optimisation in highly parallel batches! preprint: chemrxiv.org/engage/chemrxi… Thanks to my PI @pschwllr (@SchwallerGroup) and @Roche for this exciting collaboration! (1/3)

Tweet Image 1

Andrés M Bran Reposted

🚨Are you looking for an exciting PhD position in drug discovery? 🚨 Come to beautiful Mainz, and do research with us! The project is about the discovery and design of neuroprotective drugs. Top molecules will be experimentally validated! 🔃 Please share/retweet #PhDposition

Tweet Image 1

Andrés M Bran Reposted

Thrilled to present our new preprint - AdsMT: A multi-modal transformer for predicting global minimum adsorption energy (GMAE). Thanks to my supervisors @pschwllr and LIAC group @SchwallerGroup ! preprint: go.shr.lc/4fBntT1 code: github.com/schwallergroup…

Tweet Image 1

Andrés M Bran Reposted

Molecular generative models can *directly* optimize for synthesizability using retrosynthesis models! Check out initial results which can be an alternative to synthesizability-constrained generation Pre-print: arxiv.org/abs/2407.12186… Code: github.com/schwallergroup… (1/2)

Tweet Image 1

Andrés M Bran Reposted

We are already on Day 3 of the CECAM workshop "L2M3: Large language models for materials, molecules and beyond" in CECAM-HQ (@EPFL_en) ☀️ A fascinating panel discussion on "Agents for AI 4 science" with Santiago Miret, Tong Xie, @pschwllr and @tmadzhidov is currently underway.

Tweet Image 1

Andrés M Bran Reposted

🧵1/5 New perspective on how LLMs are catalyzing chemistry education! chemrxiv.org/engage/chemrxi… Fun collaboration with @chenru_duan*, @drecmb*, Anna Sotnikova, Yi Qu, @KulikGroup, @ABosselut, Jinjia Xu, and @pschwller!

Tweet Image 1

Andrés M Bran Reposted

We are very happy to announce the first confirmed speakers for AI4Mat-Vienna. We are excited to have Jacqueline Cole,@JWestermayr, @felix_s_k and Gabor Csanyi. sites.google.com/view/ai4mat/sc…

We're 2 weeks away from #AI4Mat submission deadline! Submit your work and join us for a day of exciting research, ideas, and amazing talks Register here openreview.net/group?id=BOKU.… before **July 17th** More here sites.google.com/view/ai4mat/su… #Materials #AI #MatSci #BOKU #ICML



Andrés M Bran Reposted

(Near) mode collapse can be a feature, not a bug! Intentional overfitting can be strategic to improve sample efficiency for generative molecular design! We release Saturn 🪐, which features the first application of the Mamba architecture for molecular design. (1/5)

Tweet Image 1

Loading...

Something went wrong.


Something went wrong.