🔥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

Really excited about this new paper. As someone who spent a ton of time training regular flows with MLE and got burned FORT training actually works making flows cool again 🌊

The supervision signal in AI4Science is so crisp that we can solve very complicated problems almost without any data or RL! In this project, we train a model to solve the Schrödinger equation for different molecular conformations using Density Functional Theory (DFT) In the

Using ESM2 through hugging face? Might as well speed it up with flash attention!

Why do we keep sampling from the same distribution the model was trained on? We rethink this old paradigm by introducing Feynman-Kac Correctors (FKCs) – a flexible framework for controlling the distribution of samples at inference time in diffusion models! Without re-training

Check out FKCs! A principled flexible approach for diffusion sampling. I was surprised how well it scaled to high dimensions given its reliance on importance reweighting. Thanks to great collaborators Mila - Institut québécois d'IA Vector Institute Imperial College London and Google DeepMind. Thread👇🧵

Given q_t, r_t as diffusion model(s), an SDE w/drift β ∇ log q_t + α ∇ log r_t doesn’t sample the sequence of geometric avg/product/tempered marginals! To correct this, we derive an SMC scheme via PDE perspective Resampling weights are ‘free’, depend only on (exact) scores!

🚨 I heard people saying that Diffusion Samplers are actually not more efficient than MD? Well, if that's you, check out our new paper PITA done in collab with a dream team in the 🧵 below👇. Finally, a diffusion sampler that is more efficient in # energy evals compared to

Yes! We were heavily influenced by your work James Thornton although I think still quite challenging to train energy based models

New OpenProblems paper out! 📝 Led by Malte Lücken with Smita Krishnaswamy, we present openproblems.bio – a community-driven platform benchmarking single-cell analysis methods. Excited about transparent, evolving best practices for the field! 🔗 nature.com/articles/s4158…

🎉Personal update: I'm thrilled to announce that I'm joining Imperial College London Imperial College London as an Assistant Professor of Computing Imperial Computing starting January 2026. My future lab and I will continue to work on building better Generative Models 🤖, the hardest

Thrilled to be co-organizing FPI at #NeurIPS2025! I'm particularly excited about our new 'Call for Open Problems'track. If you have a tough, cross-disciplinary challenge, we want you to share it and inspire new collaborations. A unique opportunity! Learn more below.

🚨 Our workshop on Frontiers of Probabilistic Inference: Learning meets Sampling got accepted to #NeurIPS2025!! After the incredible success of the first edition. The second edition is aimed to be bolder, bigger, and more ambitious in outlining key challenges in the natural

🚨 ICML 2025 Paper 🚨 "On Measuring Long-Range Interactions in Graph Neural Networks" We formalize the long-range problem in GNNs: 💡Derive a principled range measure 🔧 Tools to assess models & benchmarks 🔬Critically assess LRGB 🧵 Thread below 👇 #ICML2025

Come check out SBG happening now! W-115 11-1:30 with charliebtan Joey Bose Chen Lin Leon Klein Michael Bronstein

we’re not kfc but come watch us cook with our feynman-kac correctors, 4:30 pm today (july 16) at ICML Conference poster session — east exhibition hall #3109 Kirill Neklyudov Alex Tong Tara Akhound Sadegh Viktor Ohanesian