One MacAskill might have a discount factor of 1 but the other has a discount factor of 0! youtu.be/GL0rbxB9Lqg?t=…

(1/8) We propose a rigorous framework for investigating Molecular Out-of-Distribution (MOOD) performance in real-world applications of molecular modeling. It’s time to close the validation-deployment gap! 🎯 Paper: chemrxiv.org/engage/chemrxi… Experiments: github.com/valence-labs/m…

Valence Labs is actively hiring across multiple roles! We’re looking for Research Engineers, Research Scientists, a DevOps Engineer, and a Community Manager. Join us in pushing the frontier of AI research in drug discovery. valencelabs.com/careers

There are also many opportunities for Master's and PhD students! Apply for the Machine Learning Research Intern role or submit a research proposal to be considered for the Valence scholarship. You can find more details on the scholarship here: valencelabs.com/careers?gh_jid…

Found this card game in a bar in Montreal (around Mila)

From November 8 to 10, Mila will be holding its first workshop on generative flow networks (GFlowNets). Save this link and join us online tomorrow as of 9:30am : youtube.com/@mila-quebecar…

Thrilled to announce the first annual Reinforcement Learning Conference RL_Conference, which will be held at UMass Amherst August 9-12! RLC is the first strongly peer-reviewed RL venue with proceedings, and our call for papers is now available: rl-conference.cc.

Dhanya Sridhar, Chandler Squires and I are running a talk series on Causality, Abstraction, Reasoning and Extrapolation (CARE).First talk is at 11EST tomorrow by Johnny on "The Statistical Structure of Identifiable Generative Models".All are welcome! portal.valencelabs.com/events/post/th…

Valence Labs will be co-hosting a TechBio social with Recursion and NVIDIA at #NeurIPS. Join us on Wed, Dec 13th. RSVP here: lu.ma/5wx660v2 Our team will also be at #NeurIPS throughout the week. See below for a summary of our papers👇

Last November, we organized a workshop at Mila - Institut québécois d'IA on GFlowNets. All the videos are now available online. If you want to learn more about GFlowNets and their applications, check out this blog post: mila.quebec/en/gflownets_a…

Recently sat down with Parker Levesque for a fun chat, we talked about GFlowNets (of course), compilers, grad school, research, and more! Listen here: open.spotify.com/episode/7rXfkS…

M2D2 is back and Emmanuel Bengio will be joining Prudencio M Tossou as a co-host! 🤯 First talk of 2024 will feature Rıza Özçelik and his paper “Chemical Language Modeling with Structured State Spaces”. 📅 Tune in tomorrow, Jan 30th at 11am ET. Details here: portal.valencelabs.com/events/post/st…

Very excited to present SynFlowNet next week at GEMBio Workshop #ICLR2024! We tackle the synthesisability issue in molecular design by training a GFlowNet with an action space of chemical reactions. Thanks to my coauthors Charlie Harris Julien Roy Emmanuel Bengio and Pietro Lio (1/n)

Can we perform unbiased bayesian posterior inference with a diffusion model prior? We propose Relative Trajectory Balance (RTB) which allows us to directly optimize for this posterior model. We apply this to several tasks in image, language and control!🧵arxiv.org/abs/2405.20971

Prudencio M Tossou Semih Cantürk Dominique Beaini 3️⃣ “Learning to Scale Logits for Temperature-Conditional GFlowNets” Where: Poster Session 3 - Hall C 4-9 #1411 When: Wednesday, July 24th from 11:30am - 1:00pm Paper: arxiv.org/abs/2310.02823 Emmanuel Bengio

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…

Ecstatic to show off some work my brilliant colleagues and I did at ICLR 2026 this year! 🚀 We address the credit assignment challenge under long trajectories in RL or GFlowNets by constructing high order actions, or “chunks”, effectively compressing trajectory lengths!

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 🧵