# Scientific Literature Processing

KAILAS is a Transformer model based on the RoBERTa architecture, specifically adapted for NASA's Science Mission Directorate applications to annotate Unified Astronomy Thesaurus labels.

A document OCR model fine-tuned based on Qwen2-VL-7B-Instruct, supporting multilingual document recognition and metadata extraction

A sentence embedding model based on BioBERT, trained on multiple NLI datasets, suitable for sentence similarity calculation and semantic search tasks

Nougat is a vision-based academic document understanding model capable of converting scientific PDF images into Markdown-formatted text.

An extractive summarization model fine-tuned on the MS^2 dataset based on the PubMedBERT pre-trained model, specifically designed for biomedical text summarization tasks.

This is a sentence-transformers-based model that maps sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

This is a model based on sentence-transformers that can map sentences and paragraphs into a 384-dimensional dense vector space, suitable for tasks such as clustering or semantic search.