Partial observability is a key challenge in predicting physical systems, where only part of the state is observed. Check out our poster #2213 at #neurips2025 on Thu, Dec 4, 4:30pm! We propose a multiscale inference scheme for diffusion models to better predict these systems.

Applications are now open for our summer research internships! Positions are available for undergrad + grad students interested in computational #science research. https://t.co/02R80lc3L2

1/ How can we improve our models of the physical world? We develop EddyFormer: integrating spectral methods w/ the Transformer architecture. We can accelerate 3D turbulence simulation by up to 30x compared to top numerical solvers, at the same level of accuracy! At #NeurIPS2025

🚀We’re looking for amazing scientists and engineers to join @PolymathicAI (NYC)! Want to work on scientific foundation models + ML for physics, biology, astronomy, solar physics & more? Want to contribute to frontier research in AI with the most brilliant and fun crowd?

Paper:

Results: It reduces prediction bias and improves the stability of predicted trajectories.

This multiscale inference scheme allows conditioning on distant past time steps without increasing computational cost.

Want to do fundamental ML research in NYC? 🧠 The Center for Computational Mathematics @FlatironInst @SimonsFdn is hiring! – Flatiron Research Fellow (postdoc, by Dec 1): https://t.co/AZ9bCrAaRQ – Open Rank (by Jan 15):

The Walrus is released! 🦭 Meet our new 1.3B parameter physics foundation model for 2D and 3D systems. Walrus is trained on 19 diverse dynamical systems from supernova explosions to viscoelastic gels. It is open-source, open-weights, and open-data. 🧵

So proud to see the culmination of effort led by @mikemccabe210 @PayelMukhopadh3 @__tm__157 @BrunoRegaldo @FrancoisRozet along with the amazing team at @PolymathicAI to produce The first "Polymathic"/cross-disciplinary AI model for fluid dynamics! We started with creating

🚀We’re looking for 2026 interns at @PolymathicAI (NYC)! Want to work on scientific foundation models + ML for physics, biology, astronomy, & more? Want to contribute to frontier research with a brilliant, fun, and friendly team? Please sign up on our interest form 👉

1/ Today with my colleagues @PolymathicAI, I'm excited to release our latest project, Walrus, a cross-domain foundation model for physical dynamics, into the world. https://t.co/ihv1MZGQM3 Paper: https://t.co/d6ah9LO4ud Git: https://t.co/s3p8qGhZQR HF: https://t.co/RufaBD9eJk

I’m excited to announce that @PolymathicAI new astrophysics model, AION-1, has been accepted to #neurips2025 ! 🎉 Come see our poster on Dec 5 (Friday) at 1-4pm PT, poster session 5 OR hear our talk from @liamhparker and Francois Lanusse at #AI4Science workshop It’s the

Can your AI surpass the simulator that taught it? What if the key to more accurate PDE modeling lies in questioning your training data's origins? 🤔 Excited to share my #NeurIPS 2025 paper with @thuereyGroup: "Neural Emulator Superiority"!

Join @FlatironInst @SimonsFdn as a Research Fellow in Manhattan 🚀 https://t.co/dl8UF4p5NM Lead cutting-edge work in computational science & ML with top collaborators. Apply by Dec 15. More about ML@CCM 👉 https://t.co/YQsOMLVgRi DM if you’re into #AIforScience or #GenerativeAI

I'm on the academic job market! I design and analyze probabilistic machine-learning methods---motivated by real-world scientific constraints, and developed in collaboration with scientists in biology, chemistry, and physics. A few highlights of my research areas are:

Extremely proud and honored to be named among the great minds of @schmidtsciences AI2050 Senior fellows! A special shout-out to my team @PolymathicAI! For building out amazing foundation models for the sciences! HUGE thanks to my team at @SimonsFdn and my mentors

Diffusion models learn probability densities by estimating the score with a neural network trained to denoise. What kind of representation arises within these networks, and how does this relate to the learned density? @EeroSimoncelli @StephaneMallat and I explored this question.

Wanna really fundamentally change science using ML? Come join the @PolymathicAI initiative at our Cambridge (UK) location!

Does a smaller latent space lead to worse generation in latent diffusion models? Not necessarily! We show that LDMs are extremely robust to a wide range of compression rates (10-1000x) in the context of physics emulation. We got lost in latent space. Join us 👇