5 papers
Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions
David R. Wessels, Farhad Ramezanghorbani, David W. Romero +9
Subquadratic alternatives to attention require compromises when applied to multi-dimensional data: standard convolutions lack global receptive fields and input dependency, while re…
Platonic Transformers: A Solid Choice For Equivariance
Mohammad Mohaiminul Islam, Rishabh Anand, David R. Wessels +7
While widespread, Transformers lack inductive biases for geometric symmetries common in science and computer vision. Existing equivariant methods often sacrifice the efficiency and…
Uncertainty-aware Machine Learning Interatomic Potentials via Learned Functional Perturbations
Olga Zaghen, Maksim Zhdanov, Dario Coscia +2
Machine Learning Interatomic Potentials (MLIPs) achieve near ab initio accuracy at a fraction of the cost of quantum-mechanical simulations, yet they remain prone to silent failure…
Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces
Alejandro GarcÃa-Castellanos, David R. Wessels, Nicky J. van den Berg +3
We introduce Equivariant Neural Eikonal Solvers, a novel framework that integrates Equivariant Neural Fields (ENFs) with Neural Eikonal Solvers. Our approach employs a single neura…
Grounding Continuous Representations in Geometry: Equivariant Neural Fields
David R Wessels, David M Knigge, Samuele Papa +4
Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal representations, by associating each data-sample with a latent variable that conditions a sha…