Zebra: In-Context Generative Pretraining for Solving Parametric PDEs
Solving time-dependent parametric partial differential equations (PDEs) is challenging for data-driven methods, as these models must adapt to variations in parameters such as coefficients, forcing ter...
Leveraging LLMs' in-context learning for modeling physical dynamics. Paper #ICML2025.
"Zebra: In-Context Generative Pretraining for Solving Parametric PDEs", Louis Serrano, Armand Kassai, Thomas Wang, Pierre ERBACHER, Patrick Gallinari
📄 arxiv.org/abs/2410.03437
🖥️ github.com/LouisSerrano...
21.07.2025 08:52 — 👍 0 🔁 1 💬 0 📌 0
Open positions – ISIR – Patrick Gallinari
We're recruiting a PhD student in machine learning at Sorbonne University (Paris) for Fall 2025!
Topic: AI4Science & Generative Models
Title: Deep Generative Models of Physical Dynamics
🔗 pages.isir.upmc.fr/gallinari/op...
#PhDPosition #AI4Science #DeepLearning #PhysicsML
26.05.2025 15:50 — 👍 1 🔁 1 💬 0 📌 0
08.05.2025 13:11 — 👍 1 🔁 0 💬 0 📌 0
08.05.2025 13:10 — 👍 2 🔁 0 💬 0 📌 0
#ICLR2025 recap' 🇸🇬
Great time at ICLR2025 for our team, who presented their work during the poster sessions!
➡️ SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation iclr.cc/virtual/2025...
05.05.2025 12:34 — 👍 0 🔁 1 💬 1 📌 1
ML4CFD Competition #neurips2024
neurips.cc/virtual/2024...
14.12.2024 21:49 — 👍 5 🔁 0 💬 1 📌 0
Two papers #NeurIPS2024 from my group on physics-aware ML
AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
openreview.net/pdf?id=Aj8RK...
Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
openreview.net/pdf?id=GuY0z...
13.12.2024 17:17 — 👍 5 🔁 1 💬 0 📌 0
MLIA research team at CNRS/ISIR lab in Sorbonne University @sorbonne-universite.fr
https://www.isir.upmc.fr/equipes/mlia/
The PolymathicAI Collaboration is building generalist foundation models for science.
https://polymathic-ai.org/
Professor @ TUM | Making numerical methods and deep learning play nicely together | Fluids | Computer Graphics
Research Scientist Meta/FAIR, Prof. University of Geneva, co-founder Neural Concept SA. I like reality.
https://fleuret.org
PhD student @MIT ChemE & CompSci | MSc ETH Chemistry @ETH Zurich | prev ML scientist @entalpicai
passionate about spectroscopy, improv theatre, and everything in between.
Professor, Head of Digital and Data-Driven Chemistry, School of Chemistry and Chemical Engineering at @unisouthampton.bsky.social
Associate Editor at Chemical Science (@roysocchem.bsky.social)
structure prediction, materials discovery
Co-Founder & Product Lead at DeepMirror | Empowering Scientists with Transformative Products | PhD in Physics & Biology
Staff Research Engineer in BioAI at InstaDeep (part of @biontech.bsky.social)- machine learning for personalized cancer vaccines, de novo peptide sequencing and signal peptides.
From Belgium 🇧🇪 currently living in Cape Town 🇿🇦
#bioML #TeamMassSpec
Chemistry Professor at Dartmouth. Into adaptive materials using tiny switches and machines
CTO at Birch Biosciences - Bringing plastic into the circular economy: https://www.birchbiosciences.com
SynBio+AI/ML - engineering biology to do cool stuff. Synthetic biologist and a Seattle sports fan.
https://www.linkedin.com/in/mileswgander
COO @ Cytodiagnostics | Former #McMasterU | Biosensors & Nanotechnology | Infectious Disease Diagnostics | AI/ML in HealthTech | 🇨🇦
Assistant Professor of Digital Chemistry at @ethzurich.bsky.social. Making chemistry more sustainable within NCCR Catalysis. Views my own.
https://dcl.ethz.ch
https://www.valencekjell.com
Tenure-track astronomer at STScI/JHU working on galaxies, machine learning, and AI for scientific discovery. Opinions my own. He/him.
Website: https://jwuphysics.github.io/
🧬 Structural Bioinformatics | 💊 AI/ML for Drug Discovery | Geometric DL
🔬 @iocbprague.bsky.social, prev. PhD @cusbg.bsky.social @mff.unikarlova.cuni.cz
Postdoctoral Fellow, Collins Lab @ Broad Institute and Wyss Institute at Harvard and MIT | AI in drug discovery
NeuroAI, vision, open science. NeuroAI researcher at Amaranth Foundation. Previously engineer @ Google, Meta, Mila. Updates from http://neuroai.science
biology + computers + a leavening of snark | 👨👨👧👧🏳️🌈| nanomedicine | cancer genomics 🧬 | ML | biomaterials | #compchem #matsky #chemsky #ai4science #materialsinformatics #md | startups | @Cal 🐻 @Stanford @UniversityOfOxford @OxfordNano (swimsf on the Bad Place)
AI Educator, Speaker & Advisor | PhD Artificial Intelligence | Co-founder & Head of @ailab.world & koolth | Honorary Doctor of Science
UK | Australia | New Zealand
https://www.ailab.world/dr-john-flackett
