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

Atlas / People / Detail

Shan Lu

Research scientist at ByteDance Seed focused on multimodal representation learning, self-supervised learning, and diffusion models; coauthor of Janus and JanusFlow.

Researcher1 organizations2 reports

Profile status: updated

updated 1 public sources

Public links

website Personal homepage

Organizations

core DeepSeek

Reports

Vision-Language Models Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation Vision-Language Models JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

Official and primary sources

https://lushan1996.github.io/ Official source · homepage