VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics

This repository contains pretrained model weights for the VICON model (paper). The code is available at: https://github.com/Eydcao/VICON.

Citation

@article{cao2026vicon,
 author = {Cao, Y. and Liu, Y. and Yang, L. and Yu, R. and Schaeffer, H. and Osher, S.},
 title = {{VICON}: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics Prediction},
 journal = {Transactions on Machine Learning Research},
 year = {2026},
 issn = {2835-8856},
 url = {https://openreview.net/forum?id=6V3YmHULQ3}
}