4 papers
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…
Fighting MRI Anisotropy: Learning Multiple Cardiac Shapes From a Single Implicit Neural Representation
Carolina Brás, Soufiane Ben Haddou, Thijs P. Kuipers +5
The anisotropic nature of short-axis (SAX) cardiovascular magnetic resonance imaging (CMRI) limits cardiac shape analysis. To address this, we propose to leverage near-isotropic, h…
Longitudinal Flow Matching for Trajectory Modeling
Mohammad Mohaiminul Islam, Thijs P. Kuipers, Sharvaree Vadgama +4
Generative models for sequential data often struggle with sparsely sampled and high-dimensional trajectories, typically reducing the learning of dynamics to pairwise transitions. W…
Learning Symmetries via Weight-Sharing with Doubly Stochastic Tensors
Putri A. van der Linden, Alejandro GarcÃa-Castellanos, Sharvaree Vadgama +2
Group equivariance has emerged as a valuable inductive bias in deep learning, enhancing generalization, data efficiency, and robustness. Classically, group equivariant methods requ…