Super excited to present our poster (rayanirban.github.io/files/EMBL_p...) on HazeMatching and ResMatching at the EMBL AI and Biology Symposium 2026 in Heidelberg, Germany, this week. 🎉
If you’re around, please drop by our poster (#148 on Thursday, 12/3)! 😊
@embl.org #EESAIBio #AI4Science
SciDER: Scientific Data-centric End-to-end Researcher. Flowchart of expert-based and LLM-based research lifecycle.
This project (paper, demo, and open-source repo) seems like a promising step toward having an AI scientist on your team.
The framework, SciDER, actually does science. Data → experiments → results. End-to-end.
Read on 👇
#ai4science
Greetings from Paris! 🇫🇷 🥖 We have just kicked off the second session of the day with a lecture from Prof. Laurence Grimaud on applications of ML approaches for optimisation of synthetic chemistry. 🧪
Join us on Zoom - visit aichemist.eu/lectures for the full programme + meeting IDs.
#AI4Science
The Paris School kicks off tomorrow (04.03) at 9:00 AM CET☀️ The full programme and hybrid lecture list + Zoom meeting IDs for the first three days of lectures is available on aichemist.eu/lectures
See you all tomorrow! #AI4Science #drugdiscovery #machinelearning #CADD
Struggling with underwater adhesion? AI has deciphered the secrets of natural glues, and designed smart hydrogels with tenfold stronger bond! Discover how machine learning co-designs, materials and unlock a new materials design paradigm.
doi.org/10.1016/j.xi...
#machinelearning #ai4science
Our work on MōLE, our AI approach to learn the coupled cluster wave function to accelerate quantum chemsitry is out now! #ai4science #compchemsky #chemsky #ai @thematterlab.bsky.social
⭕El BSC cuenta con más de 150 personas becadas a través de este programa que desarrollan sus proyectos en los diferentes campos de investigación del BSC.
💻 La visita ha servido para presentarle el #BSCAIInstitute
#AI4Science #GeneraciónD #PlanDeRecuperación #NextGenerationEU
Saw this metaphor by Terence Tao floating around about one of the drawbacks of using AI to solve hard math problems, and kind of have the same feeling for “vibe science” or “fully automated science” line of research in #AI4Science.
www.theatlantic.com/technology/2...
#ScAISci
Gene essentiality prediction with ProteomeLM-Ess.
New one for the #AI4Science crowd:
ProteomeLM suggests we can infer interactomes from proteome-scale context, not just residue-level features.
Keywords: protein foundation models, PPI prediction, representation learning.
Read all about it 👇
It's a wrap! The winners of the 2nd Joint EUOS/SLAS Challenge have been announced - congrats to teams "Yumiz" and "Microsomes" as well as AiChemist DC Vasilii Fastovskii!
It was a pleasure to be your co-host!
👉 More details at www.eu-openscreen.eu/newsroom/eu-...
#MachineLearning #AI4Science
Interested in #AI4Science but don't know where to start? No worries -- at #EACL2026, we will give a #tutorial providing an overview of recent advances in AI-assisted tools and models that support and enhance the entire scientific research process, building upon findings from our recent survey paper.
Excited to share a career update! This week, I started my 4-month stay in the LIAC lab with @pschwllr.bsky.social at EPFL, as part of my FWO-funded postdoc. Very much looking forward to collaborating with the team, and happy to connect with the Swiss AI for science community. #ChemSky #AI4Science
🌟 A strong start to 2026 for the AiChemist Consortium! 🌟
Three exciting pre-prints in the first five weeks of the year.
Proud of our talented young researchers pushing the boundaries of #AI4Science and #DrugDiscovery! 🚀
6/
📄 Paper: arxiv.org/pdf/2601.18005
💻 Code: github.com/berczig/Flow...
Built at
@au.dk
and
@maxplanck.de.
Happy to discuss methodology, results, or potential applications!
#AI4Mathematics #AI4Science #FlowMatching
A book I contributed to is now out (open access):
"Artificial Intelligence and Intelligent Matter"
link.springer.com/book/10.1007...
#Nanoscience #MaterialsScience #SoftMatter #AIforScience #IntelligentMatter #AI4Science
We are pleased to announce the inaugural recipients of #AI4Science Center’s seed grants. Led by faculty from across the Institute, the selected projects push the boundaries of AI-enabled scientific discovery.
cos.gatech.edu/news/ai4scie...
#ScientificDiscovery #AI4Science #LLMs #Creativity Survey maps LLM scientific ideation into 5 method families: knowledge grounding (RAG, graphs), prompt steering, inference-time search, multi-agent collaboration, and fine-tuning.: balance novelty with empirical soundness. arxiv.org/abs/2511.07448
Excited to share our new PNAS paper: we propose a Deep Diffusion Model for Thunderstorm Nowcasting that extends the warning lead time to 4 hours using satellite data, offering a vital tool for disaster prevention. 🛰️👉
#AI4Science #Weather Nowcasting
Especially when we have #AI4Science. We'll just ask AI to solve climate change later. Full circle.
Sustainable vibes.
"Vibe Science" == Efficient Science!
MORE PRODUCTIVITY. MORE!! MOREEEEEEEE!
YESSS!!!!
Europe needs public funding and inclusive equitable access to infrastructure, data and skills to fully benefit from artificial intelligence in research.
🔗 EUA's response to the @ec.europa.eu’s call for evidence on a European strategy for #AIinScience at buff.ly/OjjeQCH
#AI4Science #AIinResearch
🚀 Call for Reading
Can AI save the planet? The authors propose an ML-guided Life Cycle Assessment (LCA) framework to take environmental remediation from the lab to the real world. 🌍
📖 sciltp.com/journals/emt...
#AI4Science #MachineLearning #GreenTech #Chemistry #Photocatalysis
Vu joined us in Oct 2025 as DC13 and is already making waves - he gave a spotlight talk “Synthelite: chemist-aligned, feasibility-aware synthesis planning with LLMs” at the 2025 ELLIS #ML4Molecules Workshop and won the Best Paper Award. Thrilled to have him onboard! #AI4Science #innovation
Lots of #MachineLearningScienceandTechnology published research by @labcosmo.bsky.social and @kulikgroup.bsky.social at the #AI4Science workshop #NeurIPS2025. Happy to see so much #compchem here! 🧪⚗️⚛️ #machinelearning @iopp-mlresearch.bsky.social (terrible pictures by yours truly 🥲)
Different seeds with same training loss doesn't always mean same solution. When do neural nets converge vs diverge? What are the implications for inverse problems, #AI4Science & #MechInterp?
#NeurIPS2025 poster 2001 (“a space odyssey”), 4:30–7:30pm today 12/5:
Loved seeing our OSU collaborator Sam Stevens featured at the #NeurIPS SAIL Media Booth w/ @natolambert.bsky.social! Great convo on how AI accelerates scientific discovery (not just bigger models 🙃).
Clips ⬇️
youtube.com/shorts/v0k5D...
youtube.com/shorts/4R-BF...
#AI4Science #NeurIPS2025
Struggling with multi-level quantum chemistry datasets?😫 OMNI-P1 solves it!🌟
This single neural network covers DFT to CCSD(T) accuracy.
Ready for geometry optimization & MD in MLatom. 🧪Try it on Aitomistic Hub! What should we improve next? 💬
#AI4Science #compchem #MachineLearning #OpenScience
The Europe PMC and @opentargets.org collab, Lit-OTAR, powers drug discovery by mining biomedical literature at scale.
Finding ~48.5M unique links, enriching key databases and updated daily to fuel therapeutic R&D.
Read more 👉 europepmc.org/article/MED/...
#AI4Science #BioNLP #DrugDiscovery
Still, normalisation was strong overall 💪
Lit-OTAR even helped identify new disease synonyms, like 'T2D’, enhanced data processing, and improve analyses with FAERS 🎯
But disease names remain tricky, more variation = more missed matches, highlighting areas for future work!
#AI4Science #BioNLP
