Large Scale
Large-scale data processing and analysis are central to addressing numerous scientific and engineering challenges, focusing on efficient handling of massive datasets and complex systems. Current research emphasizes developing novel algorithms and model architectures, such as graph neural networks, deep learning models, and physics-guided machine learning, to improve efficiency, accuracy, and scalability in diverse applications. These advancements are crucial for tackling problems ranging from traffic optimization and robot navigation to astronomical surveys and the development of more energy-efficient AI systems. The resulting insights and tools have significant implications across various fields, enabling more effective data-driven decision-making and scientific discovery.
Papers
Using Social Media Images for Building Function Classification
Eike Jens Hoffmann, Karam Abdulahhad, Xiao Xiang Zhu
Neural Architecture Search for Dense Prediction Tasks in Computer Vision
Thomas Elsken, Arber Zela, Jan Hendrik Metzen, Benedikt Staffler, Thomas Brox, Abhinav Valada, Frank Hutter
On the Origins of the Block Structure Phenomenon in Neural Network Representations
Thao Nguyen, Maithra Raghu, Simon Kornblith