nttmdlab-nlp/InstructDoc

by nttmdlab-nlp · VLM & Understanding · updated 2y ago

InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)

More in VLM & Understanding

html-to-markdown

kreuzberg-dev

36

VLM & Understanding

High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kr

INF-MLLM

infly-ai

70

VLM & Understanding

INF Tech's open-source MLLMs for SOTA visual-language understanding and advanced document

ARGUS

Azure-Samples

80

VLM & Understanding

Automated Retrieval and GPT Understanding System by utilizing Azure Document Intelligence

dots.mocr

rednote-hilab

83

VLM & Understanding

Multimodal OCR: Parse Anything from Documents