According to Beating Monitor, Gu Yuxian, a Ph.D. graduate from Tsinghua University’s Department of Computer Science and recipient of the 2025 Special Prize for Graduate Scholarships, has officially joined DeepSeek; his name now appears on the author list of the DeepSeek V4 paper. Gu Yuxian’s research primarily focuses on efficiency optimization for large models during pre-training, model compression, and inference stages, with a total Google Scholar citation count nearing 5,000. His previous notable works include the large model knowledge distillation method MiniLLM (adopted by platforms such as Google, Alibaba, and NVIDIA) and the hybrid architecture model Jet-Nemotron. Jet-Nemotron achieves a 53.6x increase in generation throughput compared to traditional full-attention models when processing 256K long contexts on H100 GPUs, while outperforming larger parameter-sized mixture-of-experts models across multiple benchmark tests.
Tsinghua Scholarship winner Gu Yuxian joins DeepSeek, leading model distillation and a 50x speed boost.
MarsBitShare
Summary
Gu Yuxian, a Ph.D. graduate of Tsinghua University and 2025 scholarship recipient, has joined DeepSeek, where he contributes to model distillation and efficiency optimization. His work includes gas optimization techniques for large model pre-training and inference. Gu’s MiniLLM distillation method is utilized by Google and NVIDIA. He also led the development of Jet-Nemotron, a hybrid model that improved processing speed by 53.6x for long contexts. His research has potential applications in zero-knowledge proof (ZKP) systems requiring efficient computation.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.