GitHub - vlm-run/vlmrun-hub: A hub for various industry-specific schemas to be used with VLMs.

VLM Run Hub offers pre-defined Pydantic schemas for extracting structured data from visual content using Vision Language Models, featuring industry-specific templates and automatic data validation. The platform supports multiple VLM providers and includes comprehensive documentation for seamless integration across various use cases.

Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments

A new benchmark evaluates Vision-Language Models against traditional OCR systems for text recognition in video environments, using a dataset of 1,477 annotated frames from diverse sources. Advanced models like Claude-3, Gemini-1.5, and GPT-4o demonstrate superior performance in many scenarios, though challenges with hallucinations and occluded text persist.