Recent advances in machine learning have led to increased interest in solving visual
computing problems using methods that employ coordinate‐based neural networks. These …

Learning to predict agent motions with relationship reasoning is important for many
applications. In motion prediction tasks, maintaining motion equivariance under Euclidean …

We present Theseus, an efficient application-agnostic open source library for differentiable
nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …

Including covariant information, such as position, force, velocity or spin is important in many
tasks in computational physics and chemistry. We introduce Steerable E (3) Equivariant …

We present a novel method for reconstructing a 3D implicit surface from a large-scale,
sparse, and noisy point cloud. Our approach builds upon the recently introduced Neural …

Graph neural networks that model 3D data, such as point clouds or atoms, are typically
desired to be $ SO (3) $ equivariant, ie, equivariant to 3D rotations. Unfortunately …

Abstract 3D object detection received increasing attention in autonomous driving recently.
Objects in 3D scenes are distributed with diverse orientations. Ordinary detectors do not …

Most molecular generative models based on artificial intelligence for de novo drug design
are ligand-centric and do not consider the detailed three-dimensional geometries of protein …

We present Neural Descriptor Fields (NDFs), an object representation that encodes both
points and relative poses between an object and a target (such as a robot gripper or a rack …

Structure-based drug design (SBDD) utilizes the three-dimensional geometry of proteins to
identify potential drug candidates. Traditional methods, grounded in physicochemical …