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

Atlas / People / Detail

Chaorui Deng

Chaorui Deng is publicly credited as an author on ByteDance Seed multimodal research publications, including the Seed1.5-VL technical report and the BAGEL paper on unified multimodal pretraining.

Researcher on multimodal and vision-language systems, credited on ByteDance Seed publications including Seed1.5-VL and BAGEL.1 organizations1 reports

Profile status: updated

updated 3 public sources
vision-language modelsmultimodal learningvideo captioning

Current frame

Researcher on multimodal and vision-language systems, credited on ByteDance Seed publications including Seed1.5-VL and BAGEL.

Extended note

Chaorui Deng is a researcher publicly credited on ByteDance Seed publications in multimodal and vision-language modeling. Public sources confirm authorship on the Seed1.5-VL Technical Report and on ByteDance Seed's BAGEL publication, which focuses on unified multimodal understanding and generation. DBLP also indexes earlier work under the same name, including a CVPR 2021 paper on dense video captioning. No strong public homepage, scholar profile, or education record was found, so personal links and chronology are left conservative.

Organizations

core ByteDance Seed

Reports

Vision-Language Models Seed1.5-VL Technical Report

Official and primary sources

Sketch, Ground, and Refine: Top-Down Dense Video Captioning Official source · dblp · DBLP Emerging Properties in Unified Multimodal Pretraining - Publications - ByteDance Seed Team Official source · team_page · ByteDance Seed

Supporting sources

Seed1.5-VL Technical Report Supporting source · report · arXiv