Profile photo

Junru Zhang (张君如）

PhD Student @ ZJU & Visiting @ NTU

  • LLMs for Time Series
  • Time Series Analysis
  • Generative Models
  • Transfer Learning

Google Scholar GitHub LinkedIn

About Me

I am currently a final-year Ph.D. student in the College of Computer Science and Technology at Zhejiang University, where I began a combined master's and Ph.D. program in the fall of 2021. I am fortunate to be advised by Prof. Duanqing Xu and Prof. Yabo Dong. Since December 2024, I have also been a visiting student at the College of Computing and Data Science at Nanyang Technological University, under the supervision of Prof. Han Yu. Additionally, I am currently a research intern at Ant Group in Hangzhou, where I work on multimodal user behavior understanding and generation.

My primary research interests lie in sensor-based time-series data mining, including EEG, ECG, and human activity recognition, with a particular emphasis on developing LLMs for time-series analysis, generative modeling, and transfer learning. Currently, I focus on sequential user behavior modeling, leveraging LLMs to understand user behavior and learn general-purpose representations for downstream decision-making in industrial applications.

Preprints (* co-first)

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning
Junru Zhang*, Lang Feng*, Xu Guo, Yuhan Wu, Yabo Dong, Duanqing Xu
Paper Code

Selected Publications (* co-first; † corresponding)

Federated Domain Generalization for Time-Series Classification via Dynamics-to-Domain Generation
Haoran Shi*, Junru Zhang*†, Xiaoli Tang, Yifei Zhang, Hao Zhu, Yabo Dong, Lizhen Cui, Han Yu
KDD 2026, Oral, CCF A
Paper
AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection
Junru Zhang, Lang Feng, Haoran Shi, Xu Guo, Han Yu, Yabo Dong, Duanqing Xu
ICML 2026, CCF A
Paper Code
FedDiG: Frequency-Guided Diffusion Diversity for Generalizable Federated Time Series Classification
Haoran Shi*, Junru Zhang*†, Cheng Peng, Xiaoli Tang, Longtao Huang, Han Yu
WWW 2026, Oral, CCF A
Paper
Diffusion-Guided Diversity for Single Domain Generalization in Time Series Classification
Junru Zhang, Lang Feng, Xu Guo, Han Yu, Yabo Dong, Duanqing Xu
KDD 2025, Oral, CCF A
Paper Code
DI2SDiff++: Activity Style Decomposition and Diffusion-Based Fusion for Cross-Person Generalization in Activity Recognition
Junru Zhang, Cheng Peng, Zhidan Liu, Lang Feng, Yabo Dong, Duanqing Xu
IEEE Transactions on Mobile Computing 2025, CCF A
Paper
Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition
Junru Zhang, Lang Feng, Zhidan Liu, Yuhan Wu, Yang He, Yabo Dong, Duanqing Xu
KDD 2024, Oral, CCF A
Paper Code
Temporal Convolutional Explorer Helps Understand 1D-CNN's Learning Behavior in Time Series Classification from Frequency Domain
Junru Zhang, Lang Feng, Yang He, Yuhan Wu, Yang He, Yabo Dong
CIKM 2023, Oral, CCF B
Paper Code
Adacket: ADAptive Convolutional KErnel Transform for Multivariate Time Series Classification
Junru Zhang, Lang Feng, Haowen Zhang, Yuhan Wu, Yabo Dong
ECML-PKDD 2023, Oral, CCF B
Paper Code
A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting
Yu Lei, Zixuan Wang, Yiqing Feng, Junru Zhang, Yahui Li, Liu Chu, Tongyao Wang, Dongyang Li
ACL 2026, Oral, CCF A
Paper

For a complete list of publications, please refer to my Google Scholar profile.

Academic Services

Program Committee (PC) Member

Reviewer