Building Next-Gen Multimodal Foundation Models for General-Purpose Assistants

LLaVA is an open-source project, collaborating with research community to advance the state-of-the-art in AI. LLaVA represents the first end-to-end trained large multimodal model (LMM) that achieves impressive chat capabilities mimicking spirits of the multimodal GPT-4. The LLaVA family continues growing to support more modalities, capabilities, applications and beyond.

People

Open research collaboration across universities in the research community and multiple Microsoft team, pushing the SoTA in new capabilities scale and applications etc.

Portrait of Hao Cheng

Hao Cheng

Principal Researcher

Portrait of Michel Galley

Michel Galley

Senior Principal Researcher

Portrait of Jianfeng Gao

Jianfeng Gao

Distinguished Scientist & Vice President

Portrait of Yong Jae Lee

Yong Jae Lee

Associate Professor

University of Wisconsin-Madison

Portrait of Lars Liden

Lars Liden

Principal Research Software Engineer Manager

Portrait of Haotian Liu

Haotian Liu

Ph.D. student

University of Wisconsin-Madison

Portrait of Xiaodong Liu

Xiaodong Liu

Senior Principal Researcher

Portrait of Yadong Lu

Yadong Lu

Researcher

Microsoft Azure AI

Portrait of Matt Mazzola

Matt Mazzola

Senior Research Software Engineer

Portrait of Tristan Naumann

Tristan Naumann

Principal Researcher

Portrait of Hoifung Poon

Hoifung Poon

General Manager, Health Futures

Portrait of Yelong Shen

Yelong Shen

Principal Researcher

Microsoft Azure AI

Portrait of Swadheen Shukla

Swadheen Shukla

Principal Program Manager

Portrait of Irina Spiridonova

Irina Spiridonova

Senior Software Engineer

Portrait of Andrea Tupini

Andrea Tupini

Research Software Engineer

Portrait of Naoto Usuyama

Naoto Usuyama

Principal Researcher

Portrait of Cliff Wong

Cliff Wong

Principal Data Scientist

Portrait of Jianwei Yang

Jianwei Yang

Principal Researcher

Portrait of Sheng Zhang

Sheng Zhang

Principal Researcher