Jiajun Zhu 「N.B」 My Chinese name is "祝家俊".
It’s also fine to call me Jurray.

I am currently an undergraduate student in Mathematics at Zhejiang University, with a minor in Entrepreneurship. I have been working on explainable machine learning and long-context language model. Beyond that, I am keen to contribute to the following concepts: trustworthiness (e.g., explainability, robustness, safety) and multi-task learners (e.g., large language models, multimodal models). I'm open to collaboration as long as I have the bandwidth.

Email  /  CV  /  Google Scholar  /  Github

「News」
「Research」
IBS
Interpretable and Robust State Space Models with Stochastic Selection
Jiajun Zhu, Yuehao Wang, Peihao Wang, Ruisi Cai, Siqi Miao, Liliang Ren, Pan Li,
Zhangyang Wang
ICML 2025. Under Review.
Paper Code
TAPE
Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding
Jiajun Zhu, Peihao Wang, Ruisi Cai, Jason D. Lee, Pan Li, Zhangyang Wang
Preprint.
Paper Code
benchmark
Towards Unveiling Sensitive and Decisive Patterns in Explainable AI with a Case Study in Geometric Deep Learning
Jiajun Zhu, Siqi Miao, Rex Ying, Pan Li
Nature Machine Intelligence.
Paper Code
「Extra」

I aspire to be a compassionate yet influential individual. In addition to my academic interest in AI, I am fascinated by other cutting-edge technologies such as brain-computer interfaces and blockchain, the inherent traits of successful entrepreneurs, and practical and effective ways to promote social good. My role models include Charlie Munger, Stephen Curry, Jian Li (李健), and many of my kind and intelligent peers.

Website template: Jon Barron's and Yunzhi Zhang's
Last updated: Jan. 2025