minjiyoon/MMGL
Multimodal Graph Learning: how to encode multiple multimodal neighbors with their relations into LLMs
This project helps content creators and researchers generate more accurate and contextually rich summaries. It takes diverse information sources like text and images that are connected in complex ways, and produces concise text summaries. Anyone who needs to summarize large amounts of multimodal content, such as a content strategist or a data analyst, would find this useful.
No commits in the last 6 months.
Use this if you need to summarize information where text and images are intricately linked, and simple one-to-one pairings aren't enough to capture the full context.
Not ideal if your data consists only of simple text-only or image-only inputs, or if the relationships between different types of information are straightforward.
Stars
67
Forks
5
Language
Python
License
—
Category
Last pushed
Jul 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/minjiyoon/MMGL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RManLuo/reasoning-on-graphs
Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable...
alibaba/GraphTranslator
GraphTranslator:Aligning Graph Model to Large Language Model for Open-ended Tasks
HKUDS/OpenGraph
[EMNLP'2024] "OpenGraph: Towards Open Graph Foundation Models"
HKUDS/GraphEdit
"GraphEdit: Large Language Models for Graph Structure Learning"
iMoonLab/LLM4Hypergraph
The source code of ICLR 2025 "Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?"