ScaleGNN: Scalable Mini-batch GNN Training with 4D Parallelism
Discover ScaleGNN's communication-free sampling and 4D hybrid parallelism for efficient, scalable mini-batch training of graph neural networks on large dat...
GBQA Benchmark: Testing LLMs for Bug Detection in Games
Explore GBQA, a benchmark evaluating large language models' ability to detect software bugs in games, highlighting current AI challenges in QA engineering.
Metalanguage Research in NLP: Enhancing Language Models
Explore how metalanguage research advances NLP and improves large language models for better interpretability and human-AI interaction.
Self-Supervised 3D Depth Estimation for Articulated Vehicles
Discover ArticuSurDepth, a novel self-supervised method for accurate 3D surround depth estimation on articulated vehicles using cross-vehicle geometric con...
Analytic Drift Resister for Improved Continual Graph Learning
Discover how Analytic Drift Resister enhances Non-Exemplar Continual Graph Learning by preventing feature drift and boosting model adaptability.