GitHub

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieval Results in RAG Systems

We propose HtmlRAG, which uses HTML instead of plain text as the format of external knowledge in RAG systems. To tackle the long context brought by HTML, we propose Lossless HTML Cleaning and Two-Step ...
IEEE

Open-Set Domain Adaptation for Hyperspectral Image Classification Based on Reconstruction Discrepancy and Feature Alignment

Abstract: For hyperspectral image classification, domain adaptation algorithms often assume that the source domain and target domain share the same label space, and thus, classify all samples in the ...
GitHub

A toolkit for synthesis, analysis, and digitization of electrocardiogram images

The ECG (Electrocardiogram) is a widely used and accurate diagnostic tool for cardiovascular diseases. Traditionally recorded in printed formats, the digitization of ECGs holds immense potential for ...

MySA 25: Celebrating 25 years of impacts in San Antonio and across Texas

A quarter century after the year 2000, San Antonio and the surrounding regions have experienced significant changes. The last ...