Git Stars Git Stars

#multi-modal-learning Repositories

Discover 19 active open source GitHub repositories tagged with #multi-modal-learning, accumulating 41,270 total stars (averaging 2,172 stars per project). Leading this topic is mlfoundations/open_clip with 14,278 stars.

19
Total Repositories
41,270
Total Stars
2,172
Avg Stars/Repo
1
mlfoundations/open_clip

An open source implementation of CLIP.

mlfoundations
โญ 14,278 Python ๐Ÿ‘ค mlfoundations Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2021-07-28
2
OFA-Sys/Chinese-CLIP

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

OFA-Sys
โญ 6,056 Jupyter Notebook ๐Ÿ‘ค OFA-Sys Organization ๐Ÿ• Updated 2026-03-31 ๐Ÿ“… Created 2022-07-08
3
open-gigaai/giga-brain-0

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

open-gigaai
โญ 2,673 Python ๐Ÿ‘ค open-gigaai Organization ๐Ÿ• Updated 2026-09-09 ๐Ÿ“… Created 2025-09-26
4
MineDojo/MineDojo

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

MineDojo
โญ 2,108 Java ๐Ÿ‘ค MineDojo Organization ๐Ÿ• Updated 2024-03-18 ๐Ÿ“… Created 2022-06-18
5
NVlabs/RADIO

Official repository for "AM-RADIO: Reduce All Domains Into One"

NVlabs
โญ 2,008 Python ๐Ÿ‘ค NVlabs Organization ๐Ÿ• Updated 2026-10-06 ๐Ÿ“… Created 2023-12-08
6
apple-aiml-research/ml-mobileclip

This repository contains the official implementation of the research papers, "MobileCLIP" CVPR 2024 and "MobileCLIP2" TMLR August 2025

apple-aiml-research
โญ 1,687 Python ๐Ÿ‘ค apple-aiml-research Organization ๐Ÿ• Updated 2026-09-11 ๐Ÿ“… Created 2024-03-01
7
lyuchenyang/Macaw-LLM

Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration

lyuchenyang
โญ 1,594 Python ๐Ÿ‘ค lyuchenyang User ๐Ÿ• Updated 2025-01-01 ๐Ÿ“… Created 2023-05-23
8
ZeyueT/AudioX

[ICLR 2026] Repository of AudioX

ZeyueT
โญ 1,559 Python ๐Ÿ‘ค ZeyueT User ๐Ÿ• Updated 2026-03-10 ๐Ÿ“… Created 2025-03-13
9
NVlabs/prismer

The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".

NVlabs
โญ 1,308 Python ๐Ÿ‘ค NVlabs Organization ๐Ÿ• Updated 2024-01-17 ๐Ÿ“… Created 2023-03-02
10
Phantom-video/HuMo

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Phantom-video
โญ 1,292 Python ๐Ÿ‘ค Phantom-video User ๐Ÿ• Updated 2026-01-25 ๐Ÿ“… Created 2025-09-09
11
microsoft/VideoX

VideoX: a collection of video cross-modal models

microsoft
โญ 1,052 Python ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2024-06-03 ๐Ÿ“… Created 2019-11-21
12
alfworld/alfworld

ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

alfworld
โญ 921 Python ๐Ÿ‘ค alfworld User ๐Ÿ• Updated 2026-02-08 ๐Ÿ“… Created 2020-10-13
13
IDEA-Research/X-Pose

[ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"

IDEA-Research
โญ 772 Python ๐Ÿ‘ค IDEA-Research Organization ๐Ÿ• Updated 2024-08-16 ๐Ÿ“… Created 2023-10-11
14
lucidrains/x-clip

A concise but complete implementation of CLIP with various experimental improvements from recent papers

lucidrains
โญ 726 Python ๐Ÿ‘ค lucidrains User ๐Ÿ• Updated 2026-11-03 ๐Ÿ“… Created 2021-12-01
15
microsoft/BiomedParse

BiomedParse: A Foundation Model for Joint Segmentation, Detection, and Recognition of Biomedical Objects Across Nine Modalities

microsoft
โญ 717 Python ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2026-09-09 ๐Ÿ“… Created 2024-05-18
16
taokz/BiomedGPT

BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks

taokz
โญ 707 Python ๐Ÿ‘ค taokz User ๐Ÿ• Updated 2025-07-08 ๐Ÿ“… Created 2023-05-11
17
InternRobotics/EmbodiedScan

[CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

InternRobotics
โญ 668 Python ๐Ÿ‘ค InternRobotics Organization ๐Ÿ• Updated 2025-06-13 ๐Ÿ“… Created 2023-12-11
18
JohnsonJiang1996/Awesome-VLA4AD

Visionโ€“Languageโ€“Action models for Autonomous Driving (VLA4AD) resources, serving as the companion repository to the survey paper โ€œA Survey on Visionโ€“Languageโ€“Action Models for Autonomous Drivingโ€.

JohnsonJiang1996
โญ 632 ๐Ÿ‘ค JohnsonJiang1996 User ๐Ÿ• Updated 2025-11-20 ๐Ÿ“… Created 2025-06-30
19
zjukg/KG-MM-Survey

Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

zjukg
โญ 510 ๐Ÿ‘ค zjukg Organization ๐Ÿ• Updated 2026-03-02 ๐Ÿ“… Created 2024-01-29

Frequently Asked Questions

1

What is the most popular #multi-modal-learning repository on GitHub?

The top ranked open source #multi-modal-learning project on GitHub is mlfoundations/open_clip with 14,278 stars. An open source implementation of CLIP.

2

Which programming languages are most used in #multi-modal-learning repositories?

Among the top ranked #multi-modal-learning projects on GitHub, the most common programming languages are Python, Jupyter Notebook, Java.

3

How is the #multi-modal-learning repository ranking calculated?

We track 19 active open source repositories tagged with #multi-modal-learning (500+ stars), totaling 41,270 stars with an average of 2,172 stars per repository. Rankings update daily from the GitHub API.