Thanks Sergei! I gained much inspiration from your work!

Amazing example Kevin M Jablonka! Very impressive few-shot prediction results! Would be keen to hear the thoughts of a photoswitch expert such as Jake Greenfield on the ChatGPT output

📢 Looking to hire a (home-based) Ph.D. student to work on foundational algorithmic data-driven decision-making (RL, Bayesian optimization, Experiment design) at UCL E&EE Supported by MediaTek Research Retweets appreciated! Details: ucl.ac.uk/electronic-ele…

Please RT. These are positions similar to those that you would have at a company building something over several years, or a national lab-style position. We have several openings in several areas that interface AI, automation, chemistry, biochemistry and materials science!

A fantastic group of people! Well done!

Really amazing to be able to reproduce and try simple calculations for catalyst discovery! Most importantly, we'd love to get some community contributions so please reach out if you're interested in writing a similar case study for us to host!

What are the mathematical capabilities of #LLMs and how are they evolving with time? GHOSTS is a new advanced mathematics benchmark for large language models accepted to #NeurIPS2023 CITATIONS: If you spot something you feel we should cite, leave a comment before the

Many thanks to BOjana Ranković and Philippe Schwaller (he/him) for leading this work!

Come join myself, BOjana Ranković , Samuel Stanton , Gary Tom , and Arian Jamasb at *Poster 108* from 17:00-19:00 at #NeurIPS2023 where we will be presenting GAUCHE: A library for Gaussian Processes in Chemistry! Paper: neurips.cc/virtual/2023/p… Code: github.com/leojklarner/ga…

[Updated] I believe that machine learning is one of the greatest areas if you like mathematics. I'm always amazed at how advanced mathematical and statistical notions are transformed into powerful tools that open new perspectives on machine learning. (1/5)

The Bayesian Optimization Hackathon for Chemistry and Materials Science is official! See the hackathon website for the registration link 👉 ac-bo-hackathon.github.io. Who is planning to participate? #ACBOHackathon (Acceleration Consortium (AC) & EMD)

Proceedings now available for GAUCHE: A Library for Gaussian Processes in Chemistry at #NeurIPS2023! Calling for contributors to support the next wave of applications for GP regression and Bayesian optimisation in #AI4Science Poster: neurips.cc/virtual/2023/p… Code:

Delighted to join Sam Rodriques and Andrew White 🐦‍⬛ FutureHouse last week. It was a very difficult decision to turn down a faculty position for this opportunity but these are unprecedented times in #AI4Science and I strongly believe in FutureHouse's mission.

ChemCrow was one of the first serious demonstrations of using AI to automate science. There will be many more to come. Major congratulations to the team: Sam Cox Carlo Baldassari Oliver Schilter Carlo Baldassari Andrew White 🐦‍⬛ Philippe Schwaller (he/him)

An extensive new biology benchmark for LLMs!

A much delayed #BOHackathon presentation on input warping for Bayesian optimization in GAUCHE. Many thanks to Mathieu Alain Sang T. Truong and Anthony Onwuli for collaborating and Sterling G. Baird and Acceleration Consortium (AC) for organizing! Code: github.com/leojklarner/ga…

Introducing PaperQA2, the first AI agent that conducts entire scientific literature reviews on its own. PaperQA2 is also the first agent to beat PhD and Postdoc-level biology researchers on multiple literature research tasks, as measured both by accuracy on objective benchmarks