The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

A hub for various industry-specific schemas to be used with VLMs.

Open-source tools for training and evaluating Vision Language Models for OCR

Yet another self-hosted AI voice assistant. GlaDOS' blazing fast pipeline with Kokoro TTS voice and vision.

Benchmarking Vision-Language Models on OCR tasks in Dynamic Video Environments

Redact PDF/image-based documents, Word, or CSV/XLSX files using a graphical user interface. Demo: https://huggingface.co/spaces/seanpedrickcase/document_redaction or with try with VLMs: https://huggingface.co/spaces/seanpedrickcase/document_redaction_vlm

IFTG (ImageFromTextGenerator) is a Python package that simplifies creating robust datasets for OCR models. Generate images from text, apply over 10 built-in noise effects, and customize fonts and layouts. IFTG supports all languages and offers endless noise combinations, including custom noise creation.

OCR it on macOS with DeepSeek-OCR

Document image retrieval via MCP or API for agentic systems using semantic embeddings, YOLO, and VLM classification.

DocuLingo is a powerful document parsing tool built with multimodal large language models to enhance RAG (Retrieval Augmented Generation) workflows.

The CyberTech VLM Detector is a computer vision system designed to run entirely on edge devices, without requiring cloud access. The system uses vision-language models (VLM) to detect and locate objects in images based on natural language commands and development, including my creation of HIM™ and MAIC™

Развитие идей прототипа проекта SmartGrant, созданного во время Young Scientist Hackathon 2025. Система автоматизированной генерации смарт-контрактов на основе анализа бюджетных смет с применением LLM для обеспечения прозрачности целевого использования грантовых средств.

Korean olmOCR

VLM-first video frame scanner that analyzes video frames with a vision-language model and optional OCR.