In the end, we didn't find a bad place to run the #LLMHackthon for materials and chemistry kn Berlin. 🖖
Pepe Márquez
@pepe-marquez.bsky.social
Materials Scientist at Humboldt University of Berlin | @fairmat.bsky.social | #NOMAD (https://nomad-lab.eu/nomad-lab/).
It is very much fun to be back the #EMRS2025! Lots of interesting research and discussions. Sadly, we are also seeing a lot of no-shows in many sessions 😔. It is the first time I have seen this at this scale in a major conference.
We are organizing a cool workshop on research data management for PV research with NOMAD Oasis in Berlin! Registration link and tentative program: events.fairmat-nfdi.eu/event/42/ It's free, with cool people driving the digitalization of research, and there will be 🍕!
There seems to be a massive electrical blackout in the WHOLE Spain 😱 (!!)
📣 Meet #FAIRmat at #EMRS2025 in Strasbourg (May 26-30)! Visit us at booth 35 & don’t miss the talks by @pepe-marquez.bsky.social and Hampus Näsström. 👉 Check our website for more details: www.fairmat-nfdi.eu/fairmat/even... #EMRS #RDM #NFDI
Taking some days off in Spain after a super interesting #AI4AM in San Sebastián. What a conference and what a city!
Just finished the exciting #AI4AM2025 conference in San Sebastián — learned a lot! I loved seeing recognition for people developing open-source tools for the community. Even if these tools don’t always lead to immediate breakthroughs, they’re incredibly important for enabling everyday science.
I just had the pleasure of listening to @txie.bsky.social talk about the wonders of MatterSim and MatterGen in Berlin. I think I heard correctly that for their calculations they get something of the order of 5000-10000 GPUs/CPUs in Azure for a couple of weeks! 😳🤯 Exciting times!
In 2020, we predicted that hydrogen doping could be key to overcoming the efficiency bottleneck of kesterite solar cells pubs.rsc.org/en/content/a.... It's neat to see the strategy working for Cu₂ZnSnS₄ in 2025! www.nature.com/articles/s41... #ChemSky
Hydrogen-enhanced carrier collection enabling wide-bandgap Cd-free Cu2ZnSnS4 solar cells with 11.4% certified efficiency - Nature Energy
The power conversion efficiency of wide-bandgap pure-sulfide kesterite is low. Wang et al. propose annealing in a hydrogen-containing atmosphere and report the underlying mechanism that enables a cert...
nature.com
@digital-discovery.bsky.social new submission category commit -m "is a great idea". Congrats to the editors and collaborators behind the initiative! @aspuru.bsky.social @joshuaschrier.bsky.social and @jasonhein.bsky.social 🙌🙌 pubs.rsc.org/en/content/a...
Commit: Mini article for dynamic reporting of incremental improvements to previous scholarly work
Introducing Commit, a new article type at Digital Discovery intended for reporting incremental improvements on work previously published in the journal.
pubs.rsc.org
📢 Paper + code release 📃💻 After 2 years of work, I'm excited to announce our newest paper, MatterGen, has been published in Nature! www.nature.com/articles/s41... We are also releasing all the training data, model weights, model code, and evaluation code on GitHub! github.com/microsoft/ma...
GitHub - microsoft/mattergen: Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards...
Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property c...
github.com
Microsoft Research@msftresearch.bsky.social · 2y agoMicrosoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. www.microsoft.com/en-us/resear...
For all those providing reviews of scientific papers–firstly, thank you. We would not have a useful scientific literature without you. Secondly, please keep in mind that your reviews are read not only by the PIs but also students. There is no place for anger or impolite language in a review.... 1/
ML can be powerful for understanding defects, but currently sufficient only in select cases MLFFs (& geometric/electrostatic tools in doped) allow screening challenging 'non-local' defect reconstructions (split vacancies) in all ICSD/MP solids, w/caveats arxiv.org/abs/2412.19330 #CompChem #chemsky
It is super exciting to see how our #NOMAD Discord community is growing, full of people wanting to share data, raise issues, develop plugins and customize their NOMAD Oasis. It has also been great for us to provide better and faster support to the community. NOMAD Discord: discord.gg/Gyzx3ukUw8
Our data extraction tutorial is now online in Chem. Soc. Rev. The notebooks can be run using the #jupyter4nfdi service from #base4nfdi. 📝 Paper: pubs.rsc.org/en/content/a... 💻 JupyterHub: t1p.de/matextract-cpu 📚 Online book: matextract.pub 📽️ intro from @kjablonka.com! 👇
From text to insight: large language models for chemical data extraction
The vast majority of chemical knowledge exists in unstructured natural language, yet structured data is crucial for innovative and systematic materials design. Traditionally, the field has relied on m...
pubs.rsc.org
Kevin Jablonka@kjablonka.com · 2y ago🎅🏼 A small early Christmas present from our team. To celebrate the publication of our data extraction tutorial in Chem Soc Rev, we made it easy to run it — without any installation — on a JupyterHub of the Base4NFDI. 🎥 Video intro to the JupyterHub deployment: youtu.be/l-5QNUo1fcU
We’re very happy to launch our social media page of our combined research groups, led by Professors Silvana Botti and Miguel Marques, at Ruhr University Bochum! 🌟 We combine ab-initio methods and machine learning to design innovative materials for energy applications. ⚡ Follow us and repost 📢
Some statistis on the number of 'perovskite solar cells' published in jounrals up to 2022. Journal of Materials Chemistry A clearly on the lead!
A holiday treat for direct air capture of CO₂ with metal-organic frameworks 🎄 A #preprint led by @hspark1212.bsky.social & @yunsunglim.bsky.social with: - Fine-tuned machine learning force field MACE-DAC - Integrated simulation package DAC-SIM chemrxiv.org/engage/chemr... #CompChemSky #ChemSky
amazing to have @ryanhunn.bsky.social and my @stadio.bsky.social friends in this platform 🥹
Interested in Halide Perovskites, Solar Cells and Optoelectronic devices? We are hiring!!!! Research support specialists staff: euraxess.ec.europa.eu/jobs/294758 PhD Student: euraxess.ec.europa.eu/jobs/294749 Postdoc: euraxess.ec.europa.eu/jobs/294751 Deadline Dec 12 @sofiamasi.bsky.social
We wanted to make sure it is for everyone to use and also raises interest in the community to add new ways to evaluate MLIPs to gain new insights. The decision to make it open source and MIT licensed was made before we even started developing it.
The Introduction to NOMAD Webinar with Hampus Näsström of @fairmat.bsky.social starts tomorrow! 🚨 Last day to register ▶️ www.psdi.ac.uk/event/webina... 🚨 #psdi #FAIRmat #webinar #nomad #event #freeevent #registernow
We're thrilled to announce the release of MatterSimV1-1M and MatterSimV1-5M on GitHub. These cutting-edge models are now available for researchers, developers, and innovators to explore, customize and build upon. github.com/microsoft/ma...
Our multimodal follow-up to ChemBench. Our team went to the lab to create images to challenge leading vision language models. Check the paper arxiv.org/abs/2411.16955 to learn more.
Probing the limitations of multimodal language models for chemistry and materials research
Recent advancements in artificial intelligence have sparked interest in scientific assistants that could support researchers across the full spectrum of scientific workflows, from literature review to...
arxiv.org
Jablonka Lab (Lab for AI for Materials)@jablonkagroup.bsky.social · 2y agoAre Vision Language Models ready for scientific research? 🧑🔬🧪 We compared leading VLLMs on the three pillars of chemical and material science discovery: data extraction, lab experimentation and data interpretation. arxiv.org/abs/2411.16955
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
Are Vision Language Models ready for scientific research? 🧑🔬🧪 We compared leading VLLMs on the three pillars of chemical and material science discovery: data extraction, lab experimentation and data interpretation. arxiv.org/abs/2411.16955