LLMs are strong at reasoning over unstructured text. But in biology, that reasoning is hard to verify. In our new preprint, we propose a framework for generating structured, falsifiable biological hypotheses from perturbation data. arxiv.org/abs/2604.11661 @yunhuijang_ @LuZhu66 @FawkesJake @AlisandraDenton @dom_beaini @ENoutahi

We're excited to announce that MarS-FM has been accepted at ICLR! We propose a new class of generative models that learn to sample state transitions of biomolecular systems, reproducing the statistics of Molecular Dynamics (MD) with drastic speedups. arxiv.org/abs/2509.24779

News! @airstreet has raised $232,323,232 for Fund III to back AI-first companies from the earliest stages in the US and Europe. Now the largest solo GP venture firm in Europe. Our third epoch begins today. Join us!

🎉 It’s a clean sweep! This past weekend at @NeurIPSConf, the world's most prestigious #ML conference, papers from @valence_ai & Recursion won first, second and third place awards at the Foundation Models for Science workshop. The winning papers offer breakthroughs in leveraging ML to better model the intersection of biology & chemistry in order to improve & scale AI drug discovery. The winning papers: 🧵

News! @modal_labs is supporting @RAAIS fellowships with $10,000 credits on their platform, alongside the $5,000 GPU credits from @LambdaAPI. Working on AI-first, open source research outside big institutions? Apply at airstreet(dot)com/fellowships

In biology, unpaired data is the norm as experiments are often destructive. This limits our ability to build powerful multimodal models for drug discovery. To fuel a multimodal future in TechBio, we propose a simple algorithm for matching. 🧵 youtu.be/7a29mGz9LXI

Announcing the 1st #neuroscience phenomap – “Neuromap” – optioned under our collaboration with @Roche and @Genentech for $30m. To build it, we produced over 1 trillion hiPSC-derived #neuronal cells – one of the largest such datasets – & scaled new genetic perturbation techniques. We’re combining this w/ Genentech’s #transcriptomics data to rapidly accelerate discovery of new treatments. @RecursionChris: “We look forward to initiating new programs and building more maps on the forefront of the field with our colleagues at Roche and Genentech.”

Huge day for Recursion and for neuroscience - so proud of our team for doing so many world firsts to achieve this and so excited to be working with the exceptional teams at Roche and Genentech to make great strides towards new neuro targets!

Thanks to everyone who came out, and the teams @valence_ai and @Mila_Quebec for organizing!

Today, at the ICML workshops, @TOSSOUPrudencio shared some details on our QM data generation efforts and @folinoid discussed the latest on GFlowNets. Come chat with us and learn more about our open roles in London. We're hiring! valencelabs.com/careers

As someone who has spent a lot of time writing, talking, and complaining about the sad state of benchmarks in our field, I'm incredibly excited by the Polaris platform. This effort will enable the community to easily share datasets and best practices for ML model validation.

🚀 Polaris is here! It's time to stop overfitting on the same 3 benchmarks in drug discovery.

Benchmarking is hard...but it doesn't have to be! Excited to see @Polaris_HQ launched at #ICML2024 today, w support from an awesome steering committee of industry leaders, to help up-level our collective research community. Excited to get everyone's feedback on this one :)

The @valence_ai team will be in Vienna for ICML next week. Join us and other TechBio friends at the @Polaris_HQ launch party on Thurs night to learn more :)

“I’m a shareholder, Recursion is the largest investment we’ve ever made .. outside of our own company” - Jensen Huang at (standing room only) @RecursionPharma 2024 Download Day

Last week our Deputy Mayor for Business and Chair of @londonpartners @howarddawber along with our North American team was honoured to attend the opening of @RecursionPharma new office in #London at Pancras Square, King’s Cross 👏. The site will provide Recursion and @valence_ai, the company’s AI research engine, access to world-class talent across Europe’s rapidly growing TechBio sector, and embed Recursion in a thriving innovation ecosystem of leading technology and life science companies 🧬. We look forward to seeing what’s next for Recursion and welcome them to the London ecosystem 👐!

Thanks to everyone who came out and hope to see you again next year!

Thanks to everyone who came out yesterday! Looking forward to sharing more about our work at @raais later today.

not long ago, @recursionpharma and @valence_ai announced the opening of their london office to accelerate ai for drug discovery and design i'm really happy that we'll have @_danielcohen at @raais this year dan is president of valence labs, which is a gem of an org :-)

Looking forward to this!