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…

Read the latest blog post by Mila students, Edward Hu, Nikolay Malkin and Katie Everett, where they explore the links between GFlowNets and Variational Inference: pulse.ly/1iodrsgbhl

This year, Professor Dhanya Sridhar and Mizu Nishikawa-Toomey will represent Mila at the Women in Machine Learning Workshop on the margins of the NeurIPS 2023 conference. Read Dhanya Sridhar's interview on the importance of showcasing women in AI: pulse.ly/1pixpuafkh

I will be at #NeurIPS2023 next week 🎷. I will be presenting JSP-GFN (Bayesian structure learning with GFlowNets) at the main conference. Hope to see you there! 🕙 Tue 12 Dec, 10:45am CST (Poster Session 1) 🖥 neurips.cc/virtual/2023/p… 📄 arxiv.org/abs/2305.19366

Nikolay Malkin, finishing postdoc Mila - Institut québécois d'IA with #YoshuaBengio and now Prof The University of Edinburgh is looking for PhD students 24-25. Certainly one of the brightest minds these days in #ProbabilisticModeling and #MachineLearning. malkin1729.github.io

Framing regression as a classification has been “dark knowledge” for some time. We wanted to shed some light on this phenomenon in deep RL: Framing value-learning as a classification significantly improves performance and scalability in deep RL. But... not all classification

🤨Should you care about GFlowNets? What are they anyway?🧐 Learn about how GFlowNets speed up drug discovery and help large language models reason better in my new video!🔬📚 youtu.be/o0Ju9NQa5Ko

We're excited to have Sébastien Lachapelle presenting his work on additive decoding and extrapolation at the CARE reading group tomorrow! bit.ly/3x3kuRu

Excited to announce the 9th #causality workshop at UAI 2025 with Razieh Nabi Karthika Mohan Caleb Miles @d_malinsky 🎉 Do you have interesting work in #causality #causalInference #causalDiscovery #CRL etc? Consider submitting an abstract by May 31st: sites.google.com/view/causaluai…

At #ICLR2024 and thinking about generating proteins? Come checkout FoldFlow, our spotlight paper "SE(3) Stochastic Flow Matching for Protein Backbone Generation" - When? Thurs, May 9, 09:45 -- Poster Session 5 iclr.cc/virtual/2024/p… - We also are (finally) releasing model code +

Congratulations to Mila researchers for their paper "Amortizing intractable inference in large language models", which received an Honorable Mention at #ICLR2024! Edward Hu Moksh Jain Eric Elmoznino Younesse Kaddar Guillaume Lajoie, Yoshua Bengio, Nikolay Malkin ICLR 2026

We are presenting this work at #UAI2024 💃! Come see us tomorrow (16/07) during the poster session to learn more about the connections between GFlowNets & maximum entropy RL. Hope to see you there!

This week I successfully defended my PhD! 🎓🎊 Many thanks to my committee Dhanya Sridhar Simon Lacoste-Julien Kevin Patrick Murphy, and a particularly huge thanks to my advisor Yoshua Bengio for his incredible support throughout my PhD.

My PhD thesis entitled "Generative Flow Networks: Theory and Applications to Structure Learning" is now available on Arxiv 🎓 📖 arxiv.org/abs/2501.05498 🔖 Want to learn what GFlowNets are? Check out Chapters 2, 3 & 4!