Research Output

Publications

Fundamental Questions, Diverse Methodologies, and Practical Impact. † Co-first authors.

Learning Theory and Optimization

  1. Yufei Gu, Xie Zeke. Mano: Restriking Manifold Optimization for LLM Training. arXiv:2601.23000, 2026. <preprint>

  2. Tang Qian-Yuan†, Yufei Gu†, Cai Yunfeng, Sun Mingming, Li Ping, Xie Zeke, et al. Investigating the Overlooked Hessian Structure: From CNNs to LLMs. In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025). <poster>

  3. Yufei Gu, Xiaoqing Zheng, Tomaso Aste. Unraveling the Enigma of Double Descent: an in-depth Analysis Through the Lens of Learned Feature Space. In Proceedings of the 12th International Conference on Learning Representations (ICLR 2024). <poster>

  4. Zhao Ji, Yufei Gu, Shao Shitong, Zhou Xun, Xiang Liang, Xie Zeke. Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better. In Proceedings of the 14th International Conference on Learning Representations (ICLR 2026). <poster>

  5. Shao Shitong, Yufei Gu, Xie Zeke. FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters. In Proceedings of The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026). <poster>

Spiking Neural Networks & Bio-inspired Algorithms

  1. Changze Lv†, Zhengkang Guo†, Yufei Gu†, Zhibo Xu, Yixin Wu, Feiran Zhang, Tianyuan Shi, Zhenghua Wang, Ruicheng Yin, Yu Shang, et al. Towards biologically plausible computing: A comprehensive comparison. arXiv:2406.16062, 2024. <preprint>

  2. Changze Lv, Tianlong Li, Wenhao Liu, Yufei Gu, Jianhan Xu, Cenyuan Zhang, Muling Wu, Xiaoqing Zheng, Xuanjing Huang. SpikeCLIP: A contrastive language–image pretrained spiking neural network. Neural Networks 188:107475, 2025. <article>