🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Now out in Digital Discovery! 14 case studies on how LLMs can be used in chemistry, materials science, and beyond!

Thanks, Martin Vetterli, and even more thanks to all current and former group members and collaborators; without them, I would be scienceless!

This is a massively collaborative work. Would not have been possible without all the hackathon participants and organizers - especially Ben Blaiszik who spearheaded the organization.

Congratulations Kevin M Jablonka !

Happy to announce our new publication applying geometrical\topological methods to material sciences (batteries): *Predicting Ion Diffusion from the Shape of Potential Energy Landscapes* pubs.acs.org/doi/10.1021/ac……… +Hannes Gustafsson, Melania Kozdra, Berend Smit, and Amber Mace

Better chemistry with #AI nature.com/articles/s4225… Prediction, that is, with GPT 3 Nature Machine Intelligence Berend Smit Kevin M Jablonka Jablonka Lab (Lab for AI for Materials) Universität Jena Philippe Schwaller (he/him) EPFL

Large-language models will change #CHEMISTRY. See 15+ examples of answers to chemical questions. What is common to those: Kevin M Jablonka et al have near zero knowledge but we could fine-tune #GPT3 to get models that do better than the state of the art. rdcu.be/dxZ3x

Please share/apply 🔊 #PhD and #Master opportunities in our team to work on #AI/ #ML for molecule/materials discovery! Application by writing me an email (contact information: chem-eng.utoronto.ca/faculty-staff/…)

We still have a few places left in our CECAM workshop on LLMs for materials, molecules and beyond in beautiful Lausanne (July 9 - July 12). cecam.org/workshop-detai…

This news feature in Nature highlights the work Mohamad Moosavi on capturing chemical intuition by (machine) learning from failed and partially successful experiments. ‘the ugly side of science’: fresh incentives for reporting negative results nature.com/articles/d4158…

I am honored to announce my election as a foreign member of the Royal Netherlands Academy of Arts and Sciences (KNAW). This honor was made possible because of exceptional PhD students, postdocs, and colleagues. I am deeply grateful to all of them! knaw.nl/nieuws/knaw-ki…

Excited about our just-out Nature article! 🌟 A standout: a machine learning study where we used net-carbon avoidance cost to identify top-performing materials. Started with 20, #MachineLearning added 135 more, boosting commercialization chances! doi.org/10.1038/s41586…

📢Starting with a DFT calculation on a MOF, and years of work with an incredible team, we can now predict how much #CO2 this MOF can capture over a plant’s lifetime and at what net cost. Excited to share our findings in nature nature.com/articles/s4158… Heriot-Watt RCCS Heriot-Watt University

Out now in nature: a collaborative Article from Susana Garcia, Berend Smit, and many other co-workers presents a platform that integrates materials, process design, TEA and LCA to identify leading sorbent-based materials for carbon capture. Link here (OA): nature.com/articles/s4158…

From atomistic modeling to power plants and environmental assessment of carbon capture with MOFs. Check it out here: doi.org/10.1038/s41586… Congratulations to this incredible team!

We're thrilled to share that Prof. Berend Smit and Prof. Susana Garcia, two world-renowned experts in carbon capture, have joined the CuspAI team. Building on their seminal research featured in Nature last week, we're excited to be combining their deep domain knowledge with our