Physics-informed machine learning
Despite great progress in simulating multiphysics problems using the numerical
discretization of partial differential equations (PDEs), one still cannot seamlessly incorporate …
discretization of partial differential equations (PDEs), one still cannot seamlessly incorporate …
Machine learning for climate physics and simulations
We discuss the emerging advances and opportunities at the intersection of machine
learning (ML) and climate physics, highlighting the use of ML techniques, including …
learning (ML) and climate physics, highlighting the use of ML techniques, including …
Implicit diffusion models for continuous super-resolution
Image super-resolution (SR) has attracted increasing attention due to its wide applications.
However, current SR methods generally suffer from over-smoothing and artifacts, and most …
However, current SR methods generally suffer from over-smoothing and artifacts, and most …
Co-slam: Joint coordinate and sparse parametric encodings for neural real-time slam
We present Co-SLAM, a neural RGB-D SLAM system based on a hybrid representation, that
performs robust camera tracking and high-fidelity surface reconstruction in real time. Co …
performs robust camera tracking and high-fidelity surface reconstruction in real time. Co …
Why do tree-based models still outperform deep learning on typical tabular data?
While deep learning has enabled tremendous progress on text and image datasets, its
superiority on tabular data is not clear. We contribute extensive benchmarks of standard and …
superiority on tabular data is not clear. We contribute extensive benchmarks of standard and …
Encoder-based domain tuning for fast personalization of text-to-image models
Text-to-image personalization aims to teach a pre-trained diffusion model to reason about
novel, user provided concepts, embedding them into new scenes guided by natural …
novel, user provided concepts, embedding them into new scenes guided by natural …
An expert's guide to training physics-informed neural networks
Physics-informed neural networks (PINNs) have been popularized as a deep learning
framework that can seamlessly synthesize observational data and partial differential …
framework that can seamlessly synthesize observational data and partial differential …
Implicit neural representation for cooperative low-light image enhancement
The following three factors restrict the application of existing low-light image enhancement
methods: unpredictable brightness degradation and noise, inherent gap between metric …
methods: unpredictable brightness degradation and noise, inherent gap between metric …
Deep neural networks and tabular data: A survey
Heterogeneous tabular data are the most commonly used form of data and are essential for
numerous critical and computationally demanding applications. On homogeneous datasets …
numerous critical and computationally demanding applications. On homogeneous datasets …
Pointavatar: Deformable point-based head avatars from videos
The ability to create realistic animatable and relightable head avatars from casual video
sequences would open up wide ranging applications in communication and entertainment …
sequences would open up wide ranging applications in communication and entertainment …