Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Efficient Generative Transformer Operators For Million-Point PDEs

About

We introduce ECHO, a transformer-operator framework for generating million-point PDE trajectories. While existing neural operators (NOs) have shown promise for solving partial differential equations, they remain limited in practice due to poor scalability on dense grids, error accumulation during dynamic unrolling, and task-specific design. ECHO addresses these challenges through three key innovations. (i) It employs a hierarchical convolutional encode-decode architecture that achieves a 100 $\times$ spatio-temporal compression while preserving fidelity on mesh points. (ii) It incorporates a training and adaptation strategy that enables high-resolution PDE solution generation from sparse input grids. (iii) It adopts a generative modeling paradigm that learns complete trajectory segments, mitigating long-horizon error drift. The training strategy decouples representation learning from downstream task supervision, allowing the model to tackle multiple tasks such as trajectory generation, forward and inverse problems, and interpolation. The generative model further supports both conditional and unconditional generation. We demonstrate state-of-the-art performance on million-point simulations across diverse PDE systems featuring complex geometries, high-frequency dynamics, and long-term horizons.

Armand Kassa\"i Koupa\"i, Lise Le Boudec, Patrick Gallinari• 2025

Related benchmarks

TaskDatasetResultRank
Forward (initial value problem)Rayleigh-Benard (test)
Relative MSE0.0928
14
Inverse (temporal conditioning)Rayleigh-Benard (test)
Relative MSE0.116
14
Forward (initial value problem)Active Matter (test)
Relative MSE0.132
13
Forward forecastingActive Matter forward task (test)
Relative MSE0.132
13
Inverse (temporal conditioning)Active Matter (test)
Relative MSE0.112
13
Inverse forecastingActive Matter inverse task (test)
Relative MSE0.112
13
Forward (initial value problem)Gray-Scott (test)
Relative MSE0.0512
12
Forward GenerationVorticity (test)
Relative MSE0.171
12
Forward GenerationShallow-Water (test)
Relative MSE0.0196
12
Forward GenerationEagle (test)
Relative MSE0.255
12
Showing 10 of 23 rows

Other info

Follow for update