AWESOME-OCR-LLM
A curated, continuously updated reading list about OCR in the era of large language models, tracking research from the past five years on document parsing, document understanding and text-rich visual understanding.
AWESOME-OCR-LLM is a curated, continuously updated reading list about OCR in the era of large language models. It tracks work that applies vision-language and multimodal models to text-rich images and documents, covering document parsing, document understanding, visual text generation, specialized models, and benchmarks and evaluation.
The list scopes itself narrowly: it excludes general document-AI or generic multimodal-model lists unless the work directly concerns text-rich visual understanding. It keeps a running table of recent papers with venue, title, affiliation and links, and notes that most reported benchmark numbers are not directly comparable across papers because of private test sets and inconsistent protocols.