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 ...

Encoding adaptive intelligence in molecular matter by design

For more than 50 years, scientists have sought alternatives to silicon for building molecular electronics. The vision was ...
IEEE

Deep Quasi-Recurrent Self-Attention With Dual Encoder-Decoder in Biomedical CT Image Segmentation

Abstract: Developing deep learning models for accurate segmentation of biomedical CT images is challenging due to their complex structures, anatomy variations, noise, and unavailability of sufficient ...
GitHub

SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation

We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...
IEEE

Random Walk Graph Auto-Encoders With Ensemble Networks in Graph Embedding

Abstract: Recently graph auto-encoders have received increasingly widespread attention as one of the important models in the field of deep learning. Existing graph auto-encoder models only use graph ...