Search Results for author:
Found 6 papers, 2 papers with code
ScaleFold: Reducing AlphaFold Initial Training Time to 10 Hours
In this work, we conducted a comprehensive analysis on the AlphaFold training procedure based on Openfold, identified that inefficient communications and overhead-dominated computations were the key factors that prevented the AlphaFold training from effective scaling.
Zoom Out and Observe: News Environment Perception for Fake News Detection
To differentiate fake news from real ones, existing methods observe the language patterns of the news post and "zoom in" to verify its content with knowledge sources or check its readers' replies.
Confidence Propagation Cluster: Unleash Full Potential of Object Detectors
It has been a long history that most object detection methods obtain objects by using the non-maximum suppression (NMS) and its improved versions like Soft-NMS to remove redundant bounding boxes.
The Bright Side and the Dark Side of Hybrid Organic Inorganic Perovskites
The previously developed bistable amphoteric native defect (BAND) model is used for a comprehensive explanation of the unique photophysical properties and for understanding the remarkable performance of perovskites as photovoltaic materials.
Applied Physics Materials Science
GQ-Net: Training Quantization-Friendly Deep Networks
Network quantization is a model compression and acceleration technique that has become essential to neural network deployment.
Fully Quantized Network for Object Detection
Efficient neural network inference is important in a number of practical domains, such as deployment in mobile settings.
