VQASynth

datacomp

DataComp: In search of the next generation of multimodal datasets

GitHubGitHub스타 796github.com오픈소스최근 반응 3년 전

Ovis

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

GitHubGitHub스타 1,538github.com오픈소스최근 반응 2년 전

Largest open-source multimodal AI dataset

HNHacker News8점e-mm1.github.io최근 반응 작년

MultimodalUniverse

Large-Scale Multimodal Dataset of Astronomical Data

GitHubGitHub스타 515github.com오픈소스최근 반응 3년 전

vidi

The official repo for "Vidi: Large Multimodal Models for Video Understanding and Editing"

GitHubGitHub스타 663github.com오픈소스최근 반응 작년