Emmanuel de Bézenac

[Emmanuel de Bézenac @EBezenac]

@LumaLabsAI "we match all moments" then proceeds to compute estimate the MMD with 4 samples

[Emmanuel de Bézenac @EBezenac]

@marktenenholtz maybe it's the time-series problem itself that is ill-posed? tiny amounts of data for an incredibly high underlying dimensionality? would you expect anything else? that being said fine-tuned transformers are SOTA

[Emmanuel de Bézenac @EBezenac]

@fly51fly what does it mean freezing is harmless? the graph seems to say otherwise

[Johannes Brandstetter @jo_brandstetter]

Poseidon: Efficient Foundation Models for PDEs

Exciting new multiscale operator transformer from ETH PDE folks:

arXiv: https://t.co/gI8abmKg8P

[Julyan Arbel @JulyanArbel]

Learning a lot about AI for physical sciences at the GAP workshop in Grenoble today
✅PINNs with @EBezenac
✅Neural ODEs & DL training with @juliagusak502
https://t.co/KGRwQkg037

[Emmanuel de Bézenac @EBezenac]

@hannawav ?

[Ben Moseley @benm_oseley]

Very excited to announce that our entire ETH Zürich Deep Learning in Scientific Computing Master's course is now on YouTube! 📖

Prof. Siddhartha Mishra and I will talk you through PINNs, neural operators, neural ODEs, differentiable physics and more https://t.co/pj37b2RHAw

[Antoine Wehenkel @WehenkelAntoine]

A bit too tight for NeurIPS? 😵
Relax! 😎
You still have one week left to submit your great work that combines scientific models and machine learning to SynS & ML 2023!
🧪 + 🤖 = 💖
PS: this will give you a good excuse to visit Hawaï 🍹🏝️🌊

[jörn jacobsen @jh_jacobsen]

Reminder: Deadline for paper and scientific model tracks quickly approaching - 24th of May

[Emmanuel de Bézenac @EBezenac]

📣 Join us for the Synergy of Scientific and Machine Learning Modeling workshop at #ICML2023! 🧪💻 Share your latest work on combining scientific and ML models and win awards sponsored by our partners. Submit contributions by May 24th AoE.

For more info https://t.co/DvCi1JxVjM

[Sharon (Colubmia) @Sharon64803136]

@WehenkelAntoine @EBezenac @jh_jacobsen @anujkarpatne @glouppe @naoya_takeishi Please contribute to our workshop on the Synergy of Scientific and Machine Learning Modelling (SynS & ML 2023) by submitting your models, papers, and becoming reviewers! #ICML2023

[Emmanuel de Bézenac @EBezenac]

Come join us at our #ICLR2023 workshop on "Physics for Machine Learning" #physics4ml🔥

Kicking off the workshop with the talk of @mmbronstein "Physics inspired learning on Graphs"

[jörn jacobsen @jh_jacobsen]

Lots of AI research focuses on massive un-curated data - what about highly curated data? Scientific models are just that: large amounts of carefully curated and summarized experimental data. But how can ML leverage them effectively? Join our ICML workshop: https://t.co/er5VdjRUbO

[Gilles Louppe @glouppe]

Big news! 🚨 Our workshop got accepted at ICML 2023! Join us to discuss how to combine scientific ⚗️ and ML 🤖 models into hybrid models 🧌. Let's bridge the gap between fields! 🤝 Stay tuned for more details 📻 #ICML2023

[Ben Chamberlain @DrBPChamberlain]

Due to the very high number of submissions for our #iclr2023 workshop on Physics for ML we are now in need of extra reviewers. Please message me / the other organisers if willing to review a couple of 4 page papers. You will have out eternal gratitude ❤️.

[Konstantin Rusch @tk_rusch]

Quick reminder that the deadline of our #ICLR2023 workshop on "physics for ML" is already in one week ⚡

If the topic of your recent #ICML2023 submission is suitable for the workshop, you can submit it in parallel to the ICML conference track.

Site: https://t.co/5miSgb6D3c