haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
PythonApache-2.0
Stargazers
- beastars
- chenxy99The University of Minnesota Twin Cities
- DLSeed
- DongdingLinPolyU
- ezjhpark23
- fly51flyPRIS
- fxia22Google, Inc.
- haotian-liuUW-Madison
- HusseinLezzaik@OpenMined
- imaxwel
- in4sec-orgAI Flow Pte. Ltd.
- JulianJuanerCUHK, SmartMore
- khaled-hammadi
- lesniewski
- lgw2000
- LiliumSancta
- MIL-VLGHangzhou Dianzi University
- ngthanhtinN.G.U
- OE-HeartZhejiang University
- QinghongLinNational University of Singapore
- RangiLyuShanghai AI Laboratory
- SandalotsVolcanak
- ShaoTengLiuCUHK
- sjYoondeltarSeoul
- sokazakiTokyo, Japan
- SY-Xuan
- taesiriPlanet Mars
- TheSouthFrogCUHK
- xujinglinUniversity of Science and Technology Beijing
- youcaiSUN
- youngkyunJang
- ytaek-ohKAIST
- yuchongy1University of Melbourne
- yukang2017CUHK
- yuleiniuColumbia University
- zfchenUniqueThe University of Hong Kong