IEEE

SDSimPoint: Shallow-Deep Similarity Learning for Few-Shot Point Cloud Semantic Segmentation

Abstract: Three-dimensional point cloud semantic segmentation is a fundamental task in computer vision. As the fully supervised approaches suffer from the generalization issue with limited data, ...
GitHub

TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling" (ICLR 2025)

This is the official repository of the paper "TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling". It consists of two parts: One dot represents a performance score on one ...
IEEE

Hierarchical Point Cloud Transformer: A Unified Vegetation Semantic Segmentation Model for Multisource Point Clouds Based on Deep Learning

Abstract: The semantic segmentation of vegetation point clouds has very important application value in the field of geosciences. It can distinguish vegetation regions from other regions, further ...
Microsoft

Accurate and scalable exchange-correlation with deep learning

Density Functional Theory (DFT) is the most widely used electronic structure method for predicting the properties of molecules and materials. Although DFT is, in principle, an exact reformulation of ...
Smithsonian Magazine

Deep-Sea Mining Test in the Pacific Drastically Reduced Biodiversity and Animal Populations

The study inventoried thousands of mollusks, worms, crustaceans and other small marine creatures. Natural History Museum, London and University of Gothenburg As demand soars for critical minerals for ...