The Document Index / VLM & Understanding / #165
aiming-lab/MDocAgent
by aiming-lab · VLM & Understanding · updated 1y ago
MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
28
momentum
357
stars
34
forks
#165
rank
More in VLM & Understanding
html-to-markdown
xberg-io
High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kr
thepipe
emcf
Get clean data from tricky documents, powered by vision-language models ⚡
ExtractThinker
enoch3712
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction
INF-MLLM
infly-ai
INF Tech's open-source MLLMs for SOTA visual-language understanding and advanced document