LLMpeople
Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Chunyuan Li

Chunyuan Li is a multimodal AI researcher whose public homepage highlights work on large-scale language and vision training, including LLaVA, GroundingDINO, GLIP, GLIGEN, Florence, and Oscar.

Researcher in multimodal intelligence and large-scale vision-language training1 organizations1 reports

Profile status: updated

updated 2 public sources
multimodal intelligencevision-language modelscomputer visiondeep generative models

Current frame

Researcher in multimodal intelligence and large-scale vision-language training

Extended note

According to his public homepage, Chunyuan Li focuses on multimodal intelligence with an emphasis on large-scale language and vision training. His homepage highlights contributions including LLaVA and earlier work such as GroundingDINO, GLIP, GLIGEN, Florence, and Oscar. The same page says he has held research roles at xAI, ByteDance, and Microsoft Research, Redmond, and that he earned a PhD in machine learning from Duke University under Lawrence Carin, where his doctoral work explored deep generative models. OpenReview also links his homepage and Google Scholar profile and lists Duke University PhD study from 2014 to 2018.

Education

Duke University PhD · Machine learning 2014 → 2018

Public links

website Homepage google_scholar Google Scholar openreview OpenReview

Organizations

core ByteDance Seed

Reports

Vision-Language Models Seed1.5-VL Technical Report

Official and primary sources

Chunyuan Li Official source · homepage Chunyuan Li Official source · openreview · OpenReview