Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning

{ Visual & Tensor Computing; Grad student in ML4Science; Vision, Deep Neural Networks, Optimization, and SciML Simulation; Python/NumPy, PyTorch, JAX, *nix,git}

[Prof. Anima Anandkumar @AnimaAnandkumar]

In a recent interview I talk about what it takes for AI to make new scientific discoveries. tldr: it won’t be just LLMs. https://t.co/kdnYfFJwP4

[Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning @ScientificML]

More details can be found on the project web page: https://t.co/YFf7Q2CqIZ

[Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning @ScientificML]

Please join this timely workshop on Multi-scale Modeling for (Physical & Chemical) Sciences and Engineering problems.

We propose LOGLO-FNO, an improvement to the popular FNO arch, specifically targeted towards modeling high frequencies in turbulence simulations. #ai4science #pde

[Multiscale AI @MultiscaleAI]

🚀Continuing the spotlight series with the next
@iclr_conf MLMP 2025 Oral presentation!
📝LOGLO-FNO: Efficient Learning of Local and Global Features in Fourier Neural Operators
📷 Join us on April 27 at #ICLR2025!
#AI #ML #ICLR #AI4Science

[David Holzmüller @DHolzmueller]

Poster: https://t.co/F4KrrR1YER
Hall 3 + Hall 2B #32, 10am Singapore time
Paper: https://t.co/xQXSWopr8x

[David Holzmüller @DHolzmueller]

🚨ICLR poster in 1.5 hours, presented by Daniel Musekamp:
Can active learning help to generate better datasets for neural PDE solvers?
We introduce a new benchmark to find out!
Featuring 6 PDEs, 6 AL methods, 3 architectures and many ablations - transferability, speed, etc.!

[Artem Moskalev @artemmoskalev]

Thrilled to receive the outstanding paper award together with @Mangal_Prakash_ for our work on SE(3)-Hyena https://t.co/qAqNTxM3eu !🤘 Go long-convolutions!

[Miguel Liu-Schiaffini @mliuschi]

📢 Come by our #ICML2024 poster "Neural Operators with Localized Integral and Differential Kernels"!

🚀 We propose two extensions of standard convolutional layers to operator learning!

Location: Poster #216, 11:30 - 13:00 CEST

@AnimaAnandkumar @julberner @Azizzadenesheli

[Bernat Font @bernat_font]

The WaterLily.jl preprint is now available on arXiv! 📰
https://t.co/Cc7yVwCEZG
WaterLily is a #CFD solver written in the #JuliaLang for incompressible flow and moving bodies. Together with @gabrielweymouth, we provide the main numerical methods, the design behind the
1/2

[Mathias Niepert @Mniepert]

Please come to the poster and chat with Jan and @ScientificML Mario!

[Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning @ScientificML]

The proposed VCNeF architecture marries the two worlds, #NeuralOperators & #NeuralFields, and outperforms several SOTA methods such as Transformers, Neural Fields, Graph Neural Networks, and Fourier Neural Operators for solving parametric PDEs, e.g. Compressible Navier-Stokes.

[Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning @ScientificML]

📢#AI4Science Vectorized Conditional Neural Field (VCNeF) for Time-dependent Parameterized Partial Differential Equations at #ICML2024. VCNeF marries Neural Operators & Neural Fields.

Project: https://t.co/nLFkz6RJGM
Code: https://t.co/972ySyAXTG
Paper: https://t.co/IwCC1LSmuy

[Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning @ScientificML]

To develop a model that encompasses these ideal characteristics, we propose VCNeF. This linear transformer-based conditional neural field continuously solves PDEs in space and time, endowing the model with spatial and temporal zero-shot super-resolution capabilities.

[Dima Zeniuk @DimaZeniuk]

“Starship is the kind of thing that makes people from little kids to seniors excited about the future.”

— Elon Musk

[Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning @ScientificML]

@KyleCranmer @jmtomczak One of the amazing human beings I've met!! 😊

[Maksym Andriushchenko @maksym_andr]

Super excited to share that I successfully defended my PhD thesis "Understanding Generalization and Robustness in Modern Deep Learning" today 👨‍🎓

A huge thanks to the thesis examiners @SebastienBubeck, @zicokolter, and @KrzakalaF, jury president Rachid Guerraoui, and, of course, Nicolas @tml_lab for all the supervision during these years!

Seems like my 5-year journey at EPFL slowly comes to its end :-) Very excited for what comes next!

[AI4Science Talks @AI4scienceTalks]

📢#AI4Science Talk on 12.02.24 at 15:00 (CET) / 09:00 (ET) on “Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths” by Lars Holdijk. Join us on Zoom if you're interested! Details:
https://t.co/jRy5km7g1W

#ML4science #MDSimulations

[Boris Hanin @BorisHanin]

🚨Princeton ML Theory Summer School🚨

Aug 6 - 15, 2024

Speakers:

* F. Krzakala/L. Zdeborova @KrzakalaF @zdeborova
* S. Rakhlin
* B. Lourerio @_brloureiro
* M. Austern
* D. Krotov @DimaKrotov
* J. Altschuler

Details: https://t.co/UjllmH6WA2

Sponsors: @NSF and @Princeton: ORFE, @EPrinceton, PACM, CSML, @PrincetonPLI, PCTS

Please consider retweeting: @boazbaraktcs, @pfau, @shaunmmaguire, @Andrea__M, @NSF, @prfsanjeevarora, @jasondeanlee, @ArthurJacot3, @CPehlevan, @HSompolinsky, @SoledadVillar5, @SebastienBubeck, @tengyuma

[AI4Science Talks @AI4scienceTalks]

Please join us tomorrow for this interesting presentation if you're interested to learn about self-supervised learning applied to PDEs. #AI4Science #ML4Science #PDEs

[Sebastien Bubeck @SebastienBubeck]

My group is hiring a large cohort of interns for the summer of 2024 to work on the Foundations of Large Language Models! Come help us uncover the new physics of A.I. to improve the LLM building practices! (Pic below from our NeurIPS 2023 paper w. interns)

https://t.co/EnohqDw2qi