Hui Sun

AUNet: attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms

2019 · Physics in Medicine and Biology

Mammography is one of the most commonly applied tools for early breast cancer screening. Automatic segmentation of breast masses in mammograms is essential but challenging due to the low signal-to-noise ratio and the wide variety …

PQSDC: a parallel lossless compressor for quality scores data via sequences partition and run-length prediction mapping

2024 · Bioinformatics

MOTIVATION: The quality scores data (QSD) account for 70% in compressed FastQ files obtained from the short and long reads sequencing technologies. Designing effective compressors for QSD that counterbalance compression ratio, time cost, and memory …

Evaluating Long-Context Understanding via Latent and Positional Structure Queries in Large Language Models

2024

The ability to handle long-context dependencies is a critical challenge for modern language models, especially in tasks that require the retention of information over extended input sequences. Differentiating between latent and positional queries introduces a …