🔥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

If you want to do research along some of those lines, research out kjablonka.com/openings!

Sleep is beautiful because it makes your training jobs advance

Do you want one of those cups? The only way to get one is to join the team! You can still apply kjablonka.com/openings! #chemjobs #chempostdocs

We have new open Ph.D. positions in our lab focussed on building materials design agents (using technologies such as foundation models). Please share in your network, and reach out via the details in the post below. #ChemTwitter #academicjobs #sciencejobs #PhDposition

Are large language models superhuman chemists? - Curated >7k QA pairs for various subfields of chemistry and evaluated leading LLMs - Found that the best models outperformed the best human chemists on average arxiv.org/abs/2404.01475

Are large language models superhuman chemists? We have been wondering about this, too and developed the first automated and comprehensive benchmark for evaluating large language models in chemistry and let LLMs compete with human chemists 👩🏼‍🔬 📝 arxiv.org/abs/2404.01475

This is the ChemBench core team (Adrian Mirza, Nawaf Alampara, sreekanth kunchapu, Kevin M Jablonka) trying to crash another leaderboard 🎳.

We are already on Day 3 of the CECAM workshop "L2M3: Large language models for materials, molecules and beyond" in CECAM-HQ (EPFL) ☀️ A fascinating panel discussion on "Agents for AI 4 science" with Santiago Miret, Tong Xie, Philippe Schwaller (he/him) and Timur Madzhidov is currently underway.

Chemists often combine many different techniques to elucidate structures. Adrian Mirza has been building a system that mimics this using machine-learning models and genetic algorithms.

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

Elucidating structures from spectra using multimodal embeddings and discrete optimization Representations of NMR spectra contrasted against molecular graph representations. Contrastive learning used for learned database look-up -- nice! P: chemrxiv.org/engage/chemrxi…