Zhijie Wang

PhD student, Shanghai Jiaotong University

Joined

May 2023

Names

Zhijie Wang (Preferred)

Emails

****@qq.com (Confirmed)

****@sjtu.edu.cn (Confirmed)

****@tencent.com

Personal Links

Homepage

Google Scholar

Career & Education History

PhD student

Shanghai Jiaotong University (sjtu.edu.cn)

2024 – 2029

Intern

Tencent AI Lab (tencent.com)

2024 – 2025

Undergrad student

Shanghai Jiaotong University (sjtu.edu.cn)

2020 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Shuai Li

2024 – 2029

PhD Advisor

Qing Li

2024 – 2029

Coauthor

Xiaoyuan Liu

2024 – 2025

Coauthor

Zhiwei He

2024 – 2025

Coauthor

Zhaopeng Tu

2024 – 2025

Coauthor

Ruofeng Yang

2023 – 2024

Expertise

Transformer theory

2024 – Present

Diffusion Model

2023 – 2024

Publications

In-Context Stochastic Gradient Descent with Hybrid Mamba-2 and Linear Self-Attention Model
Zhijie Wang, Shuai Li
- Submitted to ICLR 2026
- Readers: Everyone
On the Effect of Positional Encoding for In-context Learning in Transformers
Zhijie Wang, Bo Jiang, Qing Li, Shuai Li
- Submitted to ICLR 2026
- Readers: Everyone
RaSA: Rank-Sharing Low-Rank Adaptation
Zhiwei He, Zhaopeng Tu, Xing Wang, Xingyu Chen, Zhijie Wang, Jiahao Xu, Tian Liang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang
- ICLR 2025 Poster
- Readers: Everyone
Leveraging Drift to Improve Sample Complexity of Variance Exploding Diffusion Models
Ruofeng Yang, Zhijie Wang, Bo Jiang, Shuai Li
- NeurIPS 2024 poster
- Readers: Everyone
In-context Learning on Function Classes Unveiled for Transformers
Zhijie Wang, Bo Jiang, Shuai Li
- ICML 2024 Poster
- Readers: Everyone
Transformers Perform In-Context Learning through Neural Networks
Zhijie Wang, Bo Jiang, Shuai Li
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
The Convergence of Variance Exploding Diffusion Models under the Manifold Hypothesis
Ruofeng Yang, Zhijie Wang, Bo Jiang, Shuai Li
- Submitted to ICLR 2024
- Readers: Everyone

Zhijie Wang

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

In-Context Stochastic Gradient Descent with Hybrid Mamba-2 and Linear Self-Attention Model

On the Effect of Positional Encoding for In-context Learning in Transformers

RaSA: Rank-Sharing Low-Rank Adaptation

Leveraging Drift to Improve Sample Complexity of Variance Exploding Diffusion Models

In-context Learning on Function Classes Unveiled for Transformers

Transformers Perform In-Context Learning through Neural Networks

The Convergence of Variance Exploding Diffusion Models under the Manifold Hypothesis

Co-Authors