New Gemini Agentic Vision Update : Plans, Acts & Checks Its Own Visual Work

Gemini 3 Flash adds active vision with Python code execution, lifting accuracy by 5 to 10%, so you can trust verified results.
GitHub

UrbanGraph: Physics-Informed Spatio-Temporal Dynamic Heterogeneous Graphs for Urban Microclimate Prediction

This repository contains the official PyTorch implementation and the UMC4/12 Dataset for the paper: [UrbanGraph: Physics-Informed Spatio-Temporal Dynamic Heterogeneous Graphs for Urban Microclimate ...
IEEE

ScaDyG: A New Paradigm for Large-Scale Dynamic Graph Learning

Abstract: Dynamic graphs (DGs), which capture time-evolving relationships between graph entities, have widespread real-world applications. To efficiently encode DGs for downstream tasks, most DG ...
IEEE

Dynamic Graph Variational Sparse Coding for Power Distribution Network Fault Location and Classification

Abstract: Fault location and classification are crucial to the reliable and resilient operation of power distribution networks (PDNs). Current machine learning works cannot provide accurate and ...
Frontiers

Resilience optimization and dynamic stability defense in active distribution networks under extreme disasters: a graph learning and cooperative control approach

1 Guangdong Power Grid Corporation Foshan Power Supply Bureau, Foshan, China 2 Electric Power Research Institute of China Southern Power Grid, Guangzhou, Guangdong, China Introduction: The escalating ...