Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics, Revealing a Three-Stage In-Context Learning Mechanism

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bao, Jiajun, Boullé, Nicolas, Liu, Toni J. B., Sarfati, Raphaël, Earls, Christopher J.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.06322