Zhiyu Wu
Source-listed: Research & Engineering team member · DeepSeek-AI (DeepSeek)
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal UnderstandingSaved credit: First author · 2024Explore people connected to this work →
- Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and GenerationSaved credit: Contributor · 2025Explore people connected to this work →
- JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and GenerationSaved credit: Contributor · 2025Explore people connected to this work →
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model ScalingSaved credit: Contributor · 2025Explore people connected to this work →
- DeepSeek-V3 Technical ReportSaved credit: Contributor · 2024Explore people connected to this work →