IEEE

Predicting the Materials Properties Using a 3D Graph Neural Network With Invariant Representation

Abstract: Accurate prediction of physical properties is critical for discovering and designing novel materials. Machine learning technologies have attracted significant attention in the materials ...
GitHub

MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation

Given an RGB-D scan and a reconstructed point cloud, MaskClustering leverages multi-view verification to merge 2D instance masks in each frame into 3D instances, achieving strong zero-shot ...
IEEE

Situationally-Aware Path Planning Exploiting 3D Scene Graphs

Abstract: 3D Scene Graphs integrate both metric and semantic information, yet their structure remains underexploited for improving path planning efficiency and interpretability. In this work, we ...
GitHub

GraphStorm: Enterprise graph machine learning framework for billion-scale graphs

GraphStorm is an enterprise-grade graph machine learning (GML) framework designed for scalability and ease of use. It simplifies the development and deployment of GML models on industry-scale graphs ...