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. Concurrently, I serve as a research intern at the Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Yong Liu, and as an AI Technical Consultant for a Tsinghua-affiliated AI startup. In this consulting role, our team is collaborating with the Beijing Dongcheng District Education Commission to develop “AI + Basic Education” (primary and secondary education) products.
I work on the 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.
I occasionally publish my notes and informal research on my blog. I am always open to collaborating with researchers worldwide, so please feel free to contact me. Currently, I am seeking industry internship opportunities focused on LLM pre-training and AI theory research, as well as PhD positions for Fall 2028.
Research Interests
- Mechanistic interpretability of LLMs
- Deep learning theory & optimization
News
| Apr 18, 2026 | Excited to announce that I have officially joined the ScalingOpt project! I will be co-maintaining this amazing systematic platform and working on the frontiers of optimizer design for large language models. |
|---|
Latest Posts
| Apr 14, 2026 | 在 LLM 语境下,梯度里的噪声会如何影响 training dynamics? |
|---|---|
| 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 |