Robuta

Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through...

Abstract page for arXiv paper 2501.19216v4: E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products

Equivariant Graph Neural Networks (EGNNs) have demonstrated significant success in modeling microscale systems, including those in chemistry, biology and...

Abstract page for arXiv paper 1610.03114: Equivariant symmetric monoidal structures

Abstract page for arXiv paper 2503.07576: Analyzing Symmetries of Swarms of Mobile Robots Using Equivariant Dynamical Systems

Machine learning interatomic potentials (MLIPs) can predict energy, force, and stress of materials and enable a wide range of downstream discovery tasks. A key...

Equivariant Graph Neural Networks (EGNNs) have demonstrated significant success in modeling microscale systems, including those in chemistry, biology and...

We propose Equivariance by Contrast (EbC) to learn equivariant embeddings from observation pairs without relying on group-specific inductive biases.

Mesh-based 3D static analysis methods have recently emerged as efficient alternatives to traditional computational numerical solvers, significantly reducing...

Many modeling tasks from disparate domains can be framed the same way, computing spherical signals from geometric inputs, for example, computing the radar...

We introduce recently proposed Equivariant Descriptor Fields (EDFs), focusing on the four key model properties: generative modeling, bi-equivariance, steerable...

Abstract page for arXiv paper 2508.16359: RotaTouille: Rotation Equivariant Deep Learning for Contours