Physics-informed machine learning

GE Karniadakis, IG Kevrekidis, L Lu… - Nature Reviews …, 2021‏ - nature.com
Despite great progress in simulating multiphysics problems using the numerical
discretization of partial differential equations (PDEs), one still cannot seamlessly incorporate …

Machine learning for climate physics and simulations

CY Lai, P Hassanzadeh, A Sheshadri… - Annual Review of …, 2024‏ - annualreviews.org
We discuss the emerging advances and opportunities at the intersection of machine
learning (ML) and climate physics, highlighting the use of ML techniques, including …

Implicit diffusion models for continuous super-resolution

S Gao, X Liu, B Zeng, S Xu, Y Li… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
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 …

Co-slam: Joint coordinate and sparse parametric encodings for neural real-time slam

H Wang, J Wang, L Agapito - Proceedings of the IEEE/CVF …, 2023‏ - openaccess.thecvf.com
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 …

Why do tree-based models still outperform deep learning on typical tabular data?

L Grinsztajn, E Oyallon… - Advances in neural …, 2022‏ - proceedings.neurips.cc
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 …

Encoder-based domain tuning for fast personalization of text-to-image models

R Gal, M Arar, Y Atzmon, AH Bermano… - ACM Transactions on …, 2023‏ - dl.acm.org
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 …

An expert's guide to training physics-informed neural networks

S Wang, S Sankaran, H Wang, P Perdikaris - arxiv preprint arxiv …, 2023‏ - arxiv.org
Physics-informed neural networks (PINNs) have been popularized as a deep learning
framework that can seamlessly synthesize observational data and partial differential …

Implicit neural representation for cooperative low-light image enhancement

S Yang, M Ding, Y Wu, Z Li… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
The following three factors restrict the application of existing low-light image enhancement
methods: unpredictable brightness degradation and noise, inherent gap between metric …

Deep neural networks and tabular data: A survey

V Borisov, T Leemann, K Seßler, J Haug… - IEEE transactions on …, 2022‏ - ieeexplore.ieee.org
Heterogeneous tabular data are the most commonly used form of data and are essential for
numerous critical and computationally demanding applications. On homogeneous datasets …

Pointavatar: Deformable point-based head avatars from videos

Y Zheng, W Yifan, G Wetzstein… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
The ability to create realistic animatable and relightable head avatars from casual video
sequences would open up wide ranging applications in communication and entertainment …