Tsinghua PhD Gu Yuxian Joins DeepSeek as Author on V4 Paper, Bringing 5,000+ Citations in Model Compression

DEEPSEEK-1.13%
According to Beating's monitoring, Gu Yuxian, a Tsinghua computer science PhD and 2025 recipient of the postgraduate fellowship, has officially joined DeepSeek and appears on the author list of DeepSeek V4. His research focuses on efficiency optimization in large language model pre-training, compression, and inference, with approximately 5,000 citations on Google Scholar. His notable works include MiniLLM, a knowledge distillation method adopted by Google, Alibaba, and Nvidia, and Jet-Nemotron, a mixed-architecture model that achieved 53.6x throughput improvement on H100 GPUs while handling 256K ultra-long contexts.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments