Lol. I wonder why? Maybe because I used to have my feed filled with scientific papers of people I follow, but since Musk, it's filled with stupid videos, politics from people I don't care, and Academic drama rather than papers. LinkedIn has become a much better resource for

We curated 40+ quantum mechanics datasets covering 250+ quantum methods & 1.5B geometries. All of this is easily accessible through the OpenQDC library. 🧵 Harness the power of QM data with a single line of code: openqdc.io Blog: valencelabs.com/blog-posts/ope…

📢Calling all researchers! The #LMRL workshop is now accepting paper submissions! 🧬✨ 🎯Showcase complete works / early-stage ideas💡 via your chance to inspire & connect with a non-traditional AIxBio #ICLR2025 audience 🌍 👉Help us spread the word of lmrl.org 🙌

📢 Big news ahead of #JPM2025: two of our potential best-in-class oncology drugs designed using the RecursionOS have received regulatory approval to advance to clinical trials: 🔹REC-4539 – a potential best-in-class LSD1 inhibitor for small-cell lung cancer (SCLC) & other

We are excited to share today that two of our Recursion oncology programs have received regulatory approval to advance into clinical trials! Both of these programs are a testament to the precision design capabilities of the RecursionOS which allows us to create novel,

A new story from BiopharmaTrend looks at our two investigational oncology drugs progressing to clinical trials – REC-3565 and REC-4539 – which target critical unmet needs in hematologic malignancies and small-cell lung cancer (SCLC). They write: “Both programs exemplify the

2025 is the year of the open-source o3 reproduction.

As training spend shifts to generating synthetic data/ reasoning traces, the fraction of compute spent on massive clusters may shrink.

Advancing our vision for building a virtual cell to deliver transformational medicines. In a presentation at the J.P. Morgan Healthcare Conference, cofounder & CEO Chris Gibson shared his vision for the future of the TechBio industry, in which our biological and chemical

🏁 The antiviral challenge is now live! 🏁 Ready to test your skills on new data? Hosted in partnership with ASAP Discovery and Open Molecular Software Foundation, the antiviral challenge is now live! To help you get started, we've prepared detailed notebooks showcasing how to format your data and

People scaled LLMs by ~10,000x from 2019 to 2024, and their scores on ARC stayed near 0 (e.g. GPT-4o at ~5%). Meanwhile a very crude program search approach could score >20% with hardly any compute. Then OpenAI started adding test-time CoT search. ARC scores immediately shot up.

It only takes a few lines of code to get started with the ASAP Discovery x Open Molecular Software Foundation antiviral challenge on Polaris! In this short tutorial, we’ll show you how easy it is to: 💻 Login to Polaris 💽 Load the challenge data 📈 Train a simple scikit-learn baseline model 🏆 Submit

If you have been waiting for the right time to start working on the ASAP Discovery challenge, this is it! 🏆 For all results submitted up until January 31st, we will publish an intermediate leaderboard. Get your first set of results in and see how you stack up against your peers

Only a few days left to submit your predictions for the first leaderboard. We’ve got an incredibly passionate team on standby to help solve any issues you may run into and we’d love to hear your feedback. 🧑‍💻 Github: github.com/polaris-hub/po… 💬 Discord: discord.gg/vBFd8p6H7u

Big moments of focus often follow big bets. Over the last few years, we’ve been running one of the most ambitious experiments in the history of biotechnology: to decode biology with unprecedented scale and precision through the integration of automation, AI, and wet lab science.

Are you working on a NeurIPS Conference paper related to molecules? There's still chance to submit a short 1-page abstract for the MoML 2025 conference on June 18th in #Montreal portal.ml4dd.com/moml-2025-post…

1/ At Valence Labs, Recursion's AI research engine, we’re focused on advancing drug discovery outcomes through cutting-edge computational methods Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵

1/ Introducing TxPert: a new model that predicts transcriptional responses across diverse biological contexts It’s designed to generalize across unseen single-gene perturbations, novel combinations of gene perturbations, and even new cell types 🧵

We are deeply honoured to share that Intrepid Labs has been nominated by The Galien Foundation The Galien Foundation for the #PrixGalienUSA Award in the “Best Startup” category! 📖 Read the full announcement here: prnewswire.com/news-releases/… prnewswire.com/news-releases/…

Welcome, Christof Boehler! 🌟 With 25+ years in technology transfer, business development, and management, Christof brings a proven record of building partnerships and commercializing life sciences innovations. We’re excited for his leadership and the future ahead! #NewHire