Architecture researcherOpen-source implementer
Haotian Liu
Built LLaVA, the open visual-instruction-tuning recipe that made multimodal chat models easy to reproduce.
Works in the archive (1) · lead author on 1
- LeadLLaVA: Visual Instruction Tuning · 2023
“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.