🔥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

Thanks to everyone who came out, and the teams Valence Labs and Mila - Institut québécois d'IA for organizing!

Check out Auroris, the Python library that empowers researchers to manage, clean, and prep data! 🧬

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.

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

I am happy to announce that our paper called Metric Flow Match (MFM) has been accepted to NeurIPS Conference #neurips2024 🔥🔥🔥 I am grateful to all my collaborators and see u in Vancouver! ⛰️ Teo Reu Alex Tong Michael Bronstein Joey Bose Francesco Di Giovanni

Another exciting day Recursion! Announcing FDA IND clearance for a Phase 1/2 study of REC-1245, a potentially first-in-class RBM39 degrader for biomarker enriched solid tumors and lymphoma! This is our first program derived from our AI-enabled Maps of Biology to advance

We’ve released an improved version of SynFlowNet! SynFlowNet can now handle large action spaces (up to 220k building blocks) and we experiment with training different GFlowNet backward policies. (1/3) arXiv: arxiv.org/abs/2405.01155 code: github.com/mirunacrt/synf…

Relaxed Equivariance via Multitask Learning Instead of baking equivariance into the architecture, one could also get it via data augm. or - as done here - via multi-task learning. The (relaxed) equivariance is part of the loss. Good results on MD17 P: arxiv.org/abs/2410.17878

1/ Can _equivariance_ be learned by unconstrained models? How does that affect generalization and computational costs? We introduce REMUL: Relaxed Equivariance via Multitask Learning! Together with Konstantin Rusch ,Francesco Di Giovanni , & Michael Bronstein ! paper: arxiv.org/pdf/2410.17878

I am recruiting PhD students for 2025!😃 You want to reveal the geometric signatures of natural and artificial intelligence, and unlock the mysteries of the brain?🤖🧠 Apply to the UCSB Geometric Intelligence Lab✨ This is the view you'd have from... well, your desk🌴

Michael Churchill Peter Potaptchik Teo Reu Leo Zhang Alex Tong Michael Bronstein Joey Bose Francesco Di Giovanni github.com/kksniak/metric…

Camera-ready version and code available for MFM! 📷 📜arxiv.org/abs/2405.14780 💻github.com/kksniak/metric…

A postdoc position is available in my group at Harvard Harvard SEAS to perform research at the intersection of Geometry & Machine Learning. Research interests include Representation Learning, Learning on Graphs & Manifolds, and applications in the Sciences. Details here:

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…

🧵We hope OpenQDC will help advance the field of MLIP development towards a future of universal potentials with greater generalizability and robustness. Explore the library: openqdc.io Find us on GitHub: github.com/valence-labs/o…

Metric Flow Matching for Smooth Interpolations on the Data Manifold Kacper Kapuśniak Peter Potaptchik Teo Reu Leo Zhang Alex Tong Joey Bose Francesco Di Giovanni nips.cc/virtual/2024/p… x.com/KKapusniak1/st…

At #NeurIPS and interested in Flow Matching? Come and find us on Thursday presenting MFM - a generalization of FM with probability paths supported on the data manifold 🗺️ Poster: #2411 East Exhibit Hall A-C ⏲️Thu 12 Dec 11 am-2pm neurips.cc/virtual/2024/p… Reach out to chat!

Missed the event yesterday? Our team is still at NeurIPS today and throughout the workshops. Come talk to us and learn more about open roles. We’re hiring for both full-time and internship positions: valencelabs.com/careers

📢 ML Internship Valence Labs - Interested in GenAI? - Excited to join a team with deep expertise in Physics? - You like BoJack Horseman/Thermodynamics/ML potentials? Then join our unit! 🦒 Please spread the word and reach out to me for questions🫶 job-boards.greenhouse.io/valencelabs

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 🧵