Can your AI surpass the simulator that taught it? What if the key to more accurate PDE modeling lies in questioning your training data's origins? 🤔

Excited to share my #NeurIPS 2025 paper with @thuereygroup.bsky.social: "Neural Emulator Superiority"!

Another important contribution is that APEBench defines most of its PDEs via a new parameterization that we call "difficulties". Those allow for expressing a wide range of different dynamics with a reduced and interpretable set of numbers.

This allows for investigating how unrolled training helps with long-term accuracy.

One core motivation for APEBench was the temporal axis in emulator learning (hence the "autoregressive" in APE). We focus on rollout metrics and sample rollouts to truly understand temporal generalization via long-term stability and accuracy in more than 20 metrics.

The key innovation is to tightly integrate a classical numerical solver that produces all the synthetic training data with incredible efficiency and allows for easy scenario customization.