Zhenda Xie
Source-listed: Researcher · DeepSeek AI
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- SimMIM: A Simple Framework for Masked Image ModelingSaved credit: First author · 2022Explore people connected to this work →
- Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation LearningSaved credit: First author · 2021Explore people connected to this work →
- Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and GenerationSaved credit: Contributor · 2024Explore people connected to this work →
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningSaved credit: Contributor · 2025Explore people connected to this work →
- DeepSeek-V3 Technical ReportSaved credit: Contributor · 2024Explore people connected to this work →