500AI
Back to researchers

Chunyuan Li

Visual instruction tuning (LLaVA)

Co-authored Visual Instruction Tuning: a widely-cited recipe for LLaVA-style multimodal assistants.

Highlights

LLaVAMultimodalVision-languageOpen-source
Focus: Visual instruction tuning (LLaVA)
Why it matters: Co-authored Visual Instruction Tuning: a widely-cited recipe for LLaVA-style multimodal assistants.
Start here
Visual Instruction Tuningpaper →LLaVA (GitHub)project →

Research Areas

LLaVAMultimodalVision-languageOpen-source
Chunyuan Li - AI Researcher Profile | 500AI