Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
In a recent interview I talk about what it takes for AI to make new scientific discoveries. tldr: it won’t be just LLMs. newindiaabroad.com/english/techno…
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning
2.3K posts
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning
@ScientificML
{ Visual & Tensor Computing; Grad student in ML4Science; Vision, Deep Neural Networks, Optimization, and SciML Simulation; Python/NumPy, PyTorch, JAX, *nix,git}
Mars Katılım Şubat 2010
3K Takip Edilen392 Takipçiler
More details can be found on the project web page: kmario23.github.io/loglo-fno
English
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
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
Poster: iclr.cc/virtual/2025/p…
Hall 3 + Hall 2B #32, 10am Singapore time
Paper: arxiv.org/abs/2408.01536
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
🚨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.!
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
Thrilled to receive the outstanding paper award together with @Mangal_Prakash_ for our work on SE(3)-Hyena arxiv.org/abs/2407.01049 !🤘 Go long-convolutions!
Sharvaree Vadgama@SharvVadgama
Here's @erikjbekkers with the awardees.
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
📢 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
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
The WaterLily.jl preprint is now available on arXiv! 📰
arxiv.org/abs/2407.16032
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
GIF
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
Please come to the poster and chat with Jan and @ScientificML Mario!
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: jhagnberger.github.io/vectorized-con… Code: github.com/jhagnberger/vc… Paper: arxiv.org/abs/2406.03919
English
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.
English
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.
English
📢#AI4Science Vectorized Conditional Neural Field (VCNeF) for Time-dependent Parameterized Partial Differential Equations at #ICML2024. VCNeF marries Neural Operators & Neural Fields.
Project: jhagnberger.github.io/vectorized-con…
Code: github.com/jhagnberger/vc…
Paper: arxiv.org/abs/2406.03919
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
“Starship is the kind of thing that makes people from little kids to seniors excited about the future.”
— Elon Musk
English
@KyleCranmer @jmtomczak One of the amazing human beings I've met!! 😊
English
Great talk by @jmtomczak at our workshop on Simulation-based Inference. Jakub is always smiling, I love it
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
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!
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
📢#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:
ai4sciencetalks.github.io/projects/pips_…
#ML4science #MDSimulations
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
🚨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: mlschool.princeton.edu
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
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
Please join us tomorrow for this interesting presentation if you're interested to learn about self-supervised learning applied to PDEs. #AI4Science #ML4Science #PDEs
AI4Science Talks@AI4scienceTalks
📢#AI4Science Talk on 30.11.23 at 15:00 (CET) / 09:00 (ET) on “Self-Supervised Learning with Lie Symmetries for Partial Differential Equations” by @garridoq_. Please join us on Zoom if you're interested! Details: ai4sciencetalks.github.io/projects/ssl4p… #ML4science #AI4Science #Simulations #PDEs
English
Mario 🇺🇦 💙💛 🇮🇱 + Scientific Machine Learning retweetledi
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)
jobs.careers.microsoft.com/global/en/job/…
English