
Finally getting around to sharing our Riemannian Metric Matching paper! We presented it as an oral at ICML this summer, and it also received the Best Short Paper Award at the ICLR GRAM workshop 🎉

Looking for geometry where it shouldn’t be. PhD student @UniofOxford. Interested in Geometric Deep Learning

Finally getting around to sharing our Riemannian Metric Matching paper! We presented it as an oral at ICML this summer, and it also received the Best Short Paper Award at the ICLR GRAM workshop 🎉

I wonder if a geometric analysis that is finer than global covariance could further help here 🤔
What should a pixel flow model predict? Data, velocity, or others? New paper: AnisoFlow🔥 • A fully learnable anisotropic target • Theory that explains what it learns Results: • ImageNet: FID 1.90 → 1.55 over JiT, no REPA • Pixel T2I without patch artifacts, even in 8-bit

FYI @OpenAI silently turned back on using my data for model training, wtf is this trickery, happened to a bunch of my colleagues too

I am recruiting PhD students for Fall 2027!😃 You want to find the mathematical laws of intelligence in brains and machines? 🌐🧠🤖 Apply to the UCSB Geometric Intelligence Lab✨ This is the view you'll have from.... your desk 🌴

Banger! Congrats @rom_pas_ and team 🎉
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 👇

Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30

🚨 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

Continuous Diffusion LMs went from niche to contender this year, but the recipe is shaky: why self-conditioning? How to embed tokens? 🤨 Our new work takes your one-hot flow from 4% to 50% on TinyGSM without self-conditioning, and explores the design space of CDLMs. 🔥🚀 (1/6)

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

It was a pleasure to present the recent works on diffusion geometry with @jacobbamb @iolo_jones @AGosztolai @trekkinglemon at the Erlangen AI Hub conference in Oxford. Predictably, there were horses 🐎

We’re in! See you @NeurIPSConf! (thread coming soon) arxiv.org/abs/2605.28075

😱 A #neurosymbolic paper as a spotlight at #NeurIPS!?! 😱 We must have done something right to please the #ML gods, @GdiGiotto @lohithkonathala! 🙏 Stay tuned to find out how we get scalable and guaranteed constraint satisfaction 👀


Our wet-lab validation campaign for Proteina-Complexa is now on bioRxiv! It includes some new exciting experimental results, from large protein structures (fully codesigned!) to functional carbohydrate binders. biorxiv.org/content/10.64898… Thread with some of the additions 🧵1/n

Kernel/graph based geometry can only go so far and it’s a big challenge to replace it with deep learning. We’re so excited to share this step towards neural diffusion geometry! Plus lots more to come.
Finally getting around to sharing our Riemannian Metric Matching paper! We presented it as an oral at ICML this summer, and it also received the Best Short Paper Award at the ICLR GRAM workshop 🎉

We’ve also put together code, pretrained models and tutorial notebooks 👇 Joint work with @AGosztolai , @trekkinglemon, @mmbronstein, @iolo_jones 📰 Paper: arxiv.org/abs/2606.14334 💻Code: github.com/jacobbamb/metric-…