Raúl retweeted
A model that generates an enzyme's reaction mechanism from its sequence, catalytic residues, substrates, and cofactors.
@arianemora_
Raúl retweeted
Happy to share our new work: Distributional Functional Rewards (DFR)! 🎉
We improve diversity and fidelity in diffusion fine-tuning 🔧✨
Big thanks to my coauthors @JeongjaeLee0, Jong Chul Ye, @mmbronstein, @Yoshua_Bengio, @AlexanderTong7 and @danyalrehman17! 🙏 Thread below 👇
🚨 New paper alert!
Despite recent advances in reward fine-tuning for diffusion and flow models, achieving high rewards remains challenging without sacrificing sample diversity or substantially drifting away from the pretrained distribution.
We address this with DFR: Distributional Functional Rewards, a framework that balances reward optimization with preserving desirable properties of the generated distribution! 🧵
Raúl retweeted
Excited to announce the follow-up to our NeurIPS 2026 Oral: Improved Training of Strong Stochastic Flow Maps!
We improve the training of SSFMs by unlocking derivative-based losses!
Joint work with @antoniofrancaib @rmincam @ChristianKoke @Niklas_TR and @AlexanderTong7
Raúl retweeted
🚨 New Paper Alert, 🎤 Accepted for an oral presentation at the NeurIPS 2026 STODY workshop!
📣 Introducing: Normalizing Flow Maps (NFM): Combining few-step transport from Flow maps with tractable likelihoods from Normalizing Flows.
This is my first work with my first crop of new PhD students, @francescoshox and @tim_hitge, who genuinely knocked this project out of the park.
📄 Paper: arxiv.org/abs/2610.22711
📝 Blog: the-bose-lab.github.io/norma…
💻 Code: github.com/francescoshox/Nor…
🧵
1/8
Raúl retweeted
Introducing Langevin Flow Maps
TLDR: Neural Network Potentials that learn their own stochastic pathwise solution for faster simulation.
- Transferable across molecular systems.
- Transition dynamics are preserved.
- No trajectory data are required.
Work together with @sgmccallum, supervised by @AlexanderTong7, and @JamesFosterBath.
Arxiv: arxiv.org/abs/2610.05998
Data: huggingface.co/datasets/nikl…
Code: github.com/sammccallum/lfm
Raúl retweeted
New preprint: 🚀 Global Transport (GT) couplings for classifier-free guided flows!
Surprisingly, a simple label-free optimal transport coupling beats both class-conditional OT and independent couplings once we push the CFG scale up 🧗 reaching 1.91 FID on ImageNet-256
Raúl retweeted
Happy to announce I've been named a 2026 #AI2050 Early Career Fellow by @SchmidtSciences. I’ll investigate generative models for molecules as part of a global cohort working to ensure AI benefits society by 2050.
Raúl retweeted
"No man ever runs an experiment on the same infra twice, for it's not the same infra and he's not the same man." - Heraclitus
Raúl retweeted
Strong Stochastic Flow Maps has been accepted to #NeurIPS2026 as an Oral! 🎉
1/5 New paper 🎉Strong Stochastic Flow Maps!
We learn the stochastic integral, not just the transition kernel of an SDE
Huge shout out to my fellow first author Sam McCallum and the rest of the amazing team: Timothy Herschell, @Niklas_TR, @AlexanderTong7, and @JamesFosterBath
Raúl retweeted
Happy to share our preprint: "A Unified 3D Generative Model for Synthesizable Structure-Based Drug Design". Highlights, preprint, and code below: 🧵1/10
Raúl retweeted
Can neural networks learn to think by denoising?
Excited to share Thinking with Looped Flows!
We train recurrent reasoning with local denoising objectives. It is a new approach for reasoning that achieves SoTA on ARC-AGI-1 and 2 among looped models.
In collaboration with @chandavidlee, @FEijkelboom, @nmboffi, @ismaililkanc, @jw9730.
1/🧵
Raúl retweeted
We're recruiting PhD students at #AITHYRA in Vienna! Working on ML methods at the intersection of AI and biology.
Details & apply: phd.aithyra.at
Feel free to reach out if you have questions!
Raúl retweeted
New blog post: continuous diffusion for language is back!
This research direction receded into the background for a while, but as of this year, it is once again a hot topic. I wrote down a historical perspective and some thoughts on the recent revival.
sander.ai/2026/08/24/continu…
Raúl retweeted
New preprint: Do more complex single cell perturbation models generalize better to unseen perturbations and cellular contexts? Not necessarily.
We find that generalization depends more on aligning model inputs with the response being predicted.
biorxiv.org/content/10.64898…
1/7
Raúl retweeted
💠Introducing Clari, a generative model to predict organic crystal structure in seconds.
Clari’s speed makes it feasible to do virtual screening of organic molecules on the basis of solid-state properties.
co-first with Alston Lo @alston1o and Luka Mucko @srboljubbosanac
Raúl retweeted
🚀Strong Stochastic Flow Maps at @icmlconf tomorrow!
Drop by our SPIGM workshop poster:
📌 Poster in Hall A | 11:40-13:30
Joint work with @sgmccallum and the rest of the amazing team: Timothy Herschell, @Niklas_TR, @AlexanderTong7, @JamesFosterBath
Introducing Strong Stochastic Flow Maps
TLDR: Stochastic Flow Maps where we learn the stochastic solution path.
Work led by Sam McCallum, @zwblasingame, with Timothy Herschelll, @AlexanderTong7, and @JamesFosterBath
Arxiv: arxiv.org/pdf/2606.01086
Code: github.com/sammccallum/ssfm
Raúl retweeted
Tomorrow, I'm at #ICML2026 presenting our paper at the Structured Probabilistic Inference & Generative Modeling (SPIGM) workshop:
📄 "Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics"
w/ @AlexanderTong7
🧵👇
Raúl retweeted
🚨GNNs are not continous across Graph Resolutions🚨
#ICML2026
🧵1/5 Should GNNs produce similar representations for the same object at different resolutions?
A social network of individual users vs one of interacting groups.
A molecule with all atoms vs just heavy atoms.
Raúl retweeted
Next week our lab will present 6 works at #ICML2026, 3 main papers including an Oral and Spotlight and 3 workshop papers. So proud of the team! Come find us👇
@zwblasingame @danyalrehman17 @antoniofrancaib @AlaMaksymiuk
See you in Seoul! 🇰🇷 #ICML
