School of Mathematics and Statistics, XJTU

Gaoling School of Artificial Intelligence, RUC

Hi, I am Jiaxuan Zou (邹嘉轩).

I am currently an undergraduate student at the School of Mathematics and Statistics, Xi’an Jiaotong University, and a research intern at the Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Yong Liu.

I work on mechanistic understanding and interpretability of deep learning. My approach is phenomenon-driven: start from empirical behaviors, then build first-principles mechanisms that explain why a model works (or fails) and where certain behaviors come from.

Research Interests

Mechanistic interpretability of LLMs
Deep learning theory & optimization

Latest Posts

Mar 23, 2026	并行性与表达能力的权衡：从 $AC^0$/$TC^0$ 到 Linear Attention 的理论边界
Mar 11, 2026	有限宽度下随机高斯矩阵谱范数的偏置与涨落
Mar 08, 2026	Adam 与 Muon 优化器更新矩阵的 Frobenius 范数估计
Mar 07, 2026	球面之上：带有 Hyperball 机制的优化器的 μP 缩放
Mar 05, 2026	球面之上：从球面动力学到 μP

Selected Publications

Effective Frontiers: A Unification of Neural Scaling Laws

Jiaxuan Zou, Zixuan Gong, Ye Su, and 2 more authors

Under Review, 2026

Bib PDF

@article{zou2025effective,
  title = {Effective Frontiers: A Unification of Neural Scaling Laws},
  author = {Zou, Jiaxuan and Gong, Zixuan and Su, Ye and Tang, Huayi and Liu, Yong},
  year = {2026},
  journal = {Under Review},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
}

Capabilities and Fundamental Limits of Latent Chain-of-Thought

Jiaxuan Zou, Yaozhong Xiong, and Yong Liu

Under Review, 2026

Bib PDF

@article{zou2025capabilities,
  title = {Capabilities and Fundamental Limits of Latent Chain-of-Thought},
  author = {Zou, Jiaxuan and Xiong, Yaozhong and Liu, Yong},
  year = {2026},
  journal = {Under Review},
  archiveprefix = {arXiv},
  primaryclass = {cs.AI},
}

Statistical MIA: Rethinking Membership Inference Attack for Reliable Unlearning Auditing

Jialong Sun, Zeming Wei, Jiaxuan Zou, and 5 more authors

Under Review, 2026

Bib PDF

@article{sun2025statistical,
  title = {Statistical MIA: Rethinking Membership Inference Attack for Reliable Unlearning Auditing},
  author = {Sun, Jialong and Wei, Zeming and Zou, Jiaxuan and Gong, Jiacheng and Wang, Guanheng and Dong, Chengyang and Li, Jialong and Liu, Bo},
  year = {2026},
  journal = {Under Review},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
}

FreIE: Low-Frequency Spectral Bias in Neural Networks for Time-Series Tasks

Jialong Sun, Xinpeng Ling, Jiaxuan Zou, and 2 more authors

In IEEE ICDM, 2025

Bib PDF Video

@inproceedings{sun2025freielowfrequencyspectralbias,
  title = {FreIE: Low-Frequency Spectral Bias in Neural Networks for Time-Series Tasks},
  author = {Sun, Jialong and Ling, Xinpeng and Zou, Jiaxuan and Kang, Jiawen and Zhang, Kejia},
  year = {2025},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2510.25800},
  booktitle = {IEEE ICDM}
}