Chunyuan Li

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

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

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

A useful anchor for the open-model ecosystem because his path runs from EleutherAI’s training efforts into a more explicit alignment and interpretability agenda at Conjecture.

An important bridge figure between open-weight language-model communities and the modern alignment debate, especially when you want to understand how frontier capability, openness, and control arguments collide in practice.

One of the more useful people to study for the Gemini era because his work spans both the text-core of multimodal frontier models and the optimization tricks that make those systems cheaper and more stable to train.