Xuan Zhang @floatlazer

PhD student @TAMU. Working on AI for science. Previously @sjtu1896 and @ENSTAParis. floatlazer.github.io Joined January 2014

Tweets

23
Followers

99
Following

257
Likes

203

Shuiwang Ji @ShuiwangJi

a month ago

Our 500+ page AI4Science paper is finally published: Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems. Foundations and Trends® in Machine Learning, Vol. 18, No. 4, 385–912, 2025 nowpublishers.com/article/Detail…

6 21 93 15K 27

Download Image

Jacob Helwig @JacobHelwig

9 months ago

(2/2) I'll be presenting GeoMPNN at the competition workshop this Saturday, 12/13, at 3:40 PM PST in West Meeting Room 208. GeoMPNN Team: @floatlazer @haiyangyu14 @ShuiwangJi

0 2 4 779 0

Jacob Helwig @JacobHelwig

9 months ago

We recently developed GeoMPNN (arxiv.org/abs/2412.09399), a machine-learned simulator for airfoil flows. GeoMPNN is designed to generalize across different airfoil shapes and flow conditions and won best student solution at the NeurIPS 2024 ML4CFD Competition. (1/2)

1 4 9 1K 3

Xuan Zhang @floatlazer

a year ago

Come chat with Jacob and me about SineNet and neural PDE solvers in Friday morning’s poster session!

Jacob Helwig @JacobHelwig

a year ago

Come chat with Jacob and me about SineNet and neural PDE solvers in Friday morning’s poster session!

0 4 39 3K 8

0 1 2 252 1

Johannes Brandstetter @jo_brandstetter

a year ago

This is a super interesting paper, proving once more how important residual connections are. In this case residuals are interpreted as small transformations over time, strongly improving the UNet idea for spatio-temporal problems! I learned a lot when reading this :)

Jacob Helwig @JacobHelwig

a year ago

3 47 276 38K 169

Download Image

1 17 142 14K 85

Jacob Helwig @JacobHelwig

a year ago

Check out our #ICLR2024 paper, “SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations” (openreview.net/forum?id=LSYhE…), where we improve the U-Net architecture for modeling time-evolving PDEs. (1/4)

3 47 276 38K 169

Download Image

Maurice Weiler @maurice_weiler

2 years ago

We proudly present our 524 page book on equivariant convolutional networks. Coauthored by Patrick Forré, @erikverlinde and @wellingmax. maurice-weiler.gitlab.io/#cnn_book [1/N]