← Search

David M Knigge

4 accepted papers

2025

Grounding Continuous Representations in Geometry: Equivariant Neural Fields

ICLR 2025poster

Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal representations, by associating each data-sample with a latent variable that conditions a shared backbone Neural Field (NeF) to reconstruct the sample. However, existing CNF architectures face limitations when usi…

2024

Space-Time Continuous PDE Forecasting using Equivariant Neural Fields

NeurIPS 2024poster

Recently, Conditional Neural Fields (NeFs) have emerged as a powerful modelling paradigm for PDEs, by learning solutions as flows in the latent space of the Conditional NeF. Although benefiting from favourable properties of NeFs such as grid-agnosticity and space-time-continuous dynamics modelling,…

Cited by 7SourcePDFScholar
2023

Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN

ICLR 2023poster

Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In this work, we tackle the need for problem-specific CNN architectures. We present the Continuous Convolutional Neural Ne…

2022

Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups

ICML 2022spotlight

Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy by incorporating geometric inductive biases. In this work, we investigate the properties of representations learned by regular G-CNNs, and show considerable parameter redundancy in group…