7 papers
phepy: Visual benchmarks and improvements for out-of-distribution detectors
Felix Krumbiegel, Juniper Tyree, Michael Boy +2
Applying machine learning to increasingly high-dimensional problems with sparse or biased training data increases the risk that a model is used on inputs outside its training domai…
Inverse Neural Operator for ODE Parameter Optimization
Zhi-Song Liu, Wenqing Peng, Helmi Toropainen +5
We propose the Inverse Neural Operator (INO), a two-stage framework for recovering hidden ODE parameters from sparse, partial observations. In Stage 1, a Conditional Fourier Neural…
Downscaling Neural Network for Coastal Simulations
Zhi-Song Liu, Markus Büttner, Matthew Scarborough +4
Learning the fine-scale details of a coastal ocean simulation from a coarse representation is a challenging task. For real-world applications, high-resolution simulations are neces…
PUFM++: Point Cloud Upsampling via Enhanced Flow Matching
Zhi-Song Liu, Chenhang He, Roland Maier +1
Recent advances in generative modeling have demonstrated strong promise for high-quality point cloud upsampling. In this work, we present PUFM++, an enhanced flow-matching framewor…
Multiscale Corrections by Continuous Super-Resolution
Zhi-Song Liu, Roland Maier, Andreas Rupp
Finite element methods typically require a high resolution to satisfactorily approximate micro and even macro patterns of an underlying physical model. This issue can be circumvent…
Cellular Automaton With CNN
Valery Ashu, Zhisong Liu, Heikki Haario +1
Cellular automata (CA) models are widely used to simulate complex systems with emergent behaviors, but identifying hidden parameters that govern their dynamics remains a significan…