Large genome model: Open source AI trained on trillions of bases

Late in 2025, we covered the development of an AI system called Evo that was trained on massive numbers of bacterial genomes. So many that, when prompted with sequences from a cluster of related genes ...

HETDEX data reveal a vast 'sea of light' between early galaxies

Astronomers with the Hobby-Eberly Telescope Dark Energy Experiment (HETDEX) have used data from the project to make the ...
IEEE

BGC-Net: Bilateral Graph Convolutional Network for Weakly-supervised Semantic Segmentation of Large-scale Point Clouds

Abstract: Weakly-supervised point cloud semantic segmentation (WS-PCS) has attracted increasing attention due to the challenge of sparse annotations. A central problem is how to effectively extract ...
IEEE

MCGC-Net: Multi-scale Controllable Graph Convolutional Network on Music Emotion Recognition

Abstract: This paper introduces a novel dynamic graph learning approach for frequency graphs, underpinned by a suite of baseline methodologies and the Multi-scale Controllable Graph Convolutional ...
Neowin

Microsoft is retiring some Graph components

Microsoft Graph is a very useful platform for interconnecting Microsoft services and devices, but the Redmond tech firm is now retiring two Graph components. Microsoft Graph is a very powerful API ...
InfoWorld

Microsoft .NET Aspire adds resource graph, publishers

Publishers, now in preview, are a new type of integration that help developers package and deploy .NET Aspire apps to Docker Compose, Kubernetes, Azure, and other destinations. Microsoft has released ...
Scientific Research Publishing

Baldassarre, F. and Azizpour, H. (2019) Explainability Techniques for Graph Convolutional Networks. arXiv: 1905.13686.

ABSTRACT: Predicting molecular properties is essential for advancing for advancing drug discovery and design. Recently, Graph Neural Networks (GNNs) have gained prominence due to their ability to ...