A visual OCR model fine-tuned based on Qwen2.5-VL-3B-Instruct, focusing on document-level OCR, long-context visual language understanding, and mathematical LaTeX format conversion.

MultimodalTransformersEnglish

A multimodal model fine-tuned based on Qwen/Qwen2-VL-2B-Instruct, optimized for OCR, image-to-text conversion, LaTeX math solving, and handwriting recognition

MultimodalGgufMultiple Languages

docscopeOCR-7B-050425-exp is a model fine-tuned based on Qwen/Qwen2.5-VL-7B-Instruct, focusing on document-level OCR, long-context visual language understanding, and accurate image-to-text conversion of mathematical LaTeX formats.

MultimodalTransformersMultiple Languages

coreOCR-7B-050325-preview is a vision-language model fine-tuned based on Qwen/Qwen2-VL-7B, focusing on document-level OCR, long-context vision-language understanding, and accurate image-to-text conversion (supporting mathematical LaTeX format).

MultimodalTransformersEnglish

A BERT fine-tuned academic writing intent classification model for predicting next-step writing intentions in LaTeX paper writing

Natural Language ProcessingTransformersEnglish

A Transformer-based optical character recognition model optimized for processing handwritten math images and structured math syntax.

Computer VisionTransformers

A VisionEncoderDecoder model for generating LaTeX formulas from images, utilizing Swin Transformer encoder and GPT-2 decoder architecture

MultimodalTransformers

A multimodal table recognition model based on InternVL2-1B, supporting conversion of table images to LaTeX/HTML/Markdown formats

MultimodalSafetensorsMultiple Languages

TexTeller is an end-to-end formula recognition model based on the ViT architecture, capable of directly converting mathematical formulas in natural scene images into LaTeX format.

MultimodalSafetensors

StructEqTable-Deploy is an efficient open-source tool for converting table images to LaTeX code and performing various table-related inference tasks.

MultimodalTransformersMultiple Languages

A baseline model based on VisionEncoderDecoderModel, fine-tuned on datasets for generating LaTeX formulas from images.

MultimodalTransformers

An OCR model specialized in recognizing Chinese-English mixed LaTeX formulas, supporting local offline CPU inference

MultimodalTransformers

Pix2Text's Mathematical Formula Recognition (MFR) model, trained based on the TrOCR architecture, can convert mathematical formula images into LaTeX text representations.

Computer VisionTransformers

Cephalo is a series of vision-language large models focused on multimodal materials science. The current version specializes in converting mathematical formula images into LaTeX code.

MultimodalTransformers

Sumen is an end-to-end Transformer-based model specifically designed for converting mathematical formula images into LaTeX sequences, supporting both printed and handwritten formula recognition.

MultimodalTransformers

Pix2Text's Mathematical Formula Recognition (MFR) model, trained based on the TrOCR architecture, capable of converting mathematical formula images into LaTeX text representations.

Computer VisionTransformers

TexTeller is an end-to-end formula recognition model based on the ViT architecture, capable of recognizing mathematical formulas in natural images and converting them into LaTeX format.

Computer VisionTransformers

A fine-tuned mathematical formula recognition model based on Nougat-small, excelling in extracting LaTeX formula code from images

MultimodalTransformers

Texify is an OCR tool specifically designed to convert formula images and text into LaTeX format.

Computer VisionTransformers

This model is a LaTeX OCR model fine-tuned based on Nougat-base, specifically designed to generate LaTeX code from images, with a particular optimization for the recognition ability of mathematical formula images.

MultimodalTransformersEnglish