The 2nd Generative AI and Biology workshop will collocate with ICML 2025 in Vancouver this year (July 18/19, 2025). CFP: genbio-workshop.github.io/2025/ We have a fantastic lineup of speakers. Mengdi Wang Eric Xing Marinka Zitnik Stefano Ermon Minkai Xu Zhenqiao Song

Bootstrapped neural samplers ought to be better than MCMC methods for sampling unnormalized distributions. Using Sequential Monte Carlo as a baseline, we find that 2 recent methods (based on diffusion and flow matching) are NOT. We need stronger baselines and to rethink what

Exited to share our new paper accepted by ICML 2025 👉 “PTSD: Progressive Tempering Sampler with Diffusion” , which aims to make sampling from unnormalised densities more efficient than state-of-the-art methods like parallel tempering. Check our threads below 👇

NeurIPS Conference, why take the option to provide figures in the rebuttals away from the authors during the rebuttal period? Grounding the discussion in hard evidential data (like plots) makes resolving disagreements much easier for both the authors and the reviewers. Left: NeurIPS

This is deeply concerning and not what we would expect from a high-quality conference like NeurIPS Conference! The rebuttal guidelines explicitly allowed one optional PDF before (see archive.org as of July 16). Removing this option (even without prior notice) is not fair

The part I find most bizarre here is the ban on providing any external links, with the highly implausible justification that authors might screw up anonymity. They do realise that submitted papers contain external links, right? Why not ban that too, if you don't trust authors?

Latest ChemRxiv preprint! "Scalable Low-Energy Molecular Conformer Generation with Quantum Mechanical Accuracy" Collaboration w/ NVIDIA Healthcare We created ChEMBL3D, largest dataset of molecular 3D structures with 250M+ conformers for 1.8M drug-like molecules from ChEMBL. All

Consistency models, CTMs, shortcut models, align your flow, mean flow... What's the connection, and how should you learn them in practice? We show they're all different sides of the same coin connected by one central object: the flow map. arxiv.org/abs/2505.18825 🧵(1/n)

After two years of work, we’ve made an AI Scientist that runs for days and makes genuine discoveries. Working with external collaborators, we report seven externally validated discoveries across multiple fields. It is available right now for anyone to use. 1/5

Come by and check out our poster today at NeurIPS (4:30-7:30pm) board #2110. I’m in San Diego till Sunday feel free to reach out!

One small step towards solving the "real" protein folding problem! 🤓

Can we get accurate likelihoods from flow maps? Almost! Happy to present FALCON! Likelihoods for flow maps by enforcing approximate invertibility.