Related papers: PAINET: A Principled Efficient Transformer for 3D …

Nonlinear physical phenomena often show complex multiscale interactions; motivated by the principles of multiscale modeling in scientific computing, we propose PAS-Net, a physics-informed Adaptive-Scale Deep Operator Network for learning…

Vision transformers are effective deep learning models for vision tasks, including medical image segmentation. However, they lack efficiency and translational invariance, unlike convolutional neural networks (CNNs). To model long-range…

Recent advances in scientific machine learning have shed light on the modeling of pattern-forming systems. However, simulations of real patterns still incur significant computational costs, which could be alleviated by leveraging large…

Monocular 3D pose estimators produce camera-centered skeletons, creating view-dependent kinematic signals that complicate comparative analysis in applications such as health and sports science. We present 3DPCNet, a compact,…

In multi-body dynamics, the motion of a complicated physical object is described as a coupled ordinary differential equation system with multiple unknown solutions. Engineers need to constantly adjust the object to meet requirements at the…

Modern deep learning models operating on multi-modal visual signals often rely on inductive biases that are poorly aligned with the physical processes governing signal formation, leading to brittle performance under cross-spectral and…

The rapid advancement of deep learning models often attributes to their ability to leverage massive training data. In contrast, such privilege has not yet fully benefited 3D deep learning, mainly due to the limited availability of…

As researchers teach robots to perform more and more complex tasks, the need for realistic simulation environments is growing. Existing techniques for closing the reality gap by approximating real-world physics often require extensive real…

Transformer-based architectures have advanced medical image analysis by effectively modeling long-range dependencies, yet they often struggle in 3D settings due to substantial memory overhead and insufficient capture of fine-grained local…

We develop a novel physics informed deep learning approach for solving nonlinear drift-diffusion equations on metric graphs. These models represent an important model class with a large number of applications in areas ranging from transport…

Accurate segmentation is a crucial step in medical image analysis and applying supervised machine learning to segment the organs or lesions has been substantiated effective. However, it is costly to perform data annotation that provides…

Predicting the future motion of actors in a traffic scene is a crucial part of any autonomous driving system. Recent research in this area has focused on trajectory prediction approaches that optimize standard trajectory error metrics. In…

We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be…

Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to specific symmetries. While graph neural networks (GNNs) have proven successful in such tasks, they…

Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment comes from the facts that the mapping from…

Operator learning has emerged as a promising tool for accelerating the solution of partial differential equations (PDEs). The Deep Operator Networks (DeepONets) represent a pioneering framework in this area: the "vanilla" DeepONet is valued…

3D LiDAR-based single object tracking (SOT) has gained increasing attention as it plays a crucial role in 3D applications such as autonomous driving. The central problem is how to learn a target-aware representation from the sparse and…

We address the important problem of generalizing robotic rearrangement to clutter without any explicit object models. We first generate over 650K cluttered scenes - orders of magnitude more than prior work - in diverse everyday…

The accurate modeling of semiconductor devices plays a critical role in the development of new technology nodes and next-generation devices. Semiconductor device designers largely rely on advanced simulation software to solve the…

Neural networks that incorporate geometric relationships respecting SE(3) group transformations (e.g. rotations and translations) are increasingly important in molecular applications, such as molecular property prediction, protein structure…