I am a Ph.D. student in the Department of Electrical and Computer Engineering at the University of California, Riverside, where I am fortunate to be advised by Prof. Yinglun Zhu. Prior to that, I received my bachelor’s degree in Software Engineering from Shandong University. Download my Curriculum Vitae.
My research focuses on efficient and adaptive machine learning, with a particular interest in foundation models. I’m especially interested in delving into the following research areas:
- Active Learning (AL)
- Test-Time Training (TTT)
- Large Language Models (LLMs)
- Multimodal Models
🔥 News
📝 Publications [Google Scholar]
(* Corresponding authors; # Equal contribution)
-
Towards Multimodal Generative Active Learning: Efficient Learning via Uncertainty Dynamics
Jiancheng Zhang, Zeli Liu, Bowen Zuo, Cong Liu, Yinglun Zhu*
In submission -
Balancing Quality and Coverage in Diffusion Language Models with Adaptive Risk Portfolios
Bowen Zuo, Yue Yu, Jiancheng Zhang, Zeli Liu, Lei Zhao, Bohao Qu, Cong Liu, David J. Crandall, Yinglun Zhu*
In submission -
Active Testing of Large Language Models via Approximate Neyman Allocation
Zeli Liu, Jiancheng Zhang, Cong Liu, Yinglun Zhu*
In submission [arXiv] -
Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
Jiancheng Zhang, Meiqing Li, Qi Zhang, Yinglun Zhu*
ICML 2026 International Conference on Machine Learning [Paper] -
Mixtraining: A Better Trade-Off Between Compute and Performance
Zexin Li#, Jiancheng Zhang#, Yufei Li, Yinglun Zhu*, Cong Liu
TMLR 2026 Transactions on Machine Learning Research [Paper] -
Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data
Jiancheng Zhang, Yinglun Zhu*
TMLR 2026 Transactions on Machine Learning Research [Paper] -
Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models
Yinglun Zhu*, Jiancheng Zhang, Fuzhi Tang
ICLR 2026 International Conference on Learning Representations [Paper] -
Reconstructing Noisy Gene Regulation Dynamics Using Extrinsic-Noise-Driven Neural Stochastic Differential Equations
Jiancheng Zhang, Xiangting Li#, Xiaolu Guo#, Zhaoyi You, Lucas Böttcher, Alex Mogilner, Alexander Hoffmann, Tom Chou*, Mingtao Xia*
PLOS CB 2025 PLOS Computational Biology [Paper] -
Knowledge Distillation In Medical Data Mining: A Survey
Hefeng Meng, Zhiqiang Lin, Fan Yang, Jiancheng Zhang, Wei He, Yonghui Xu*, Lizhen Cui*
ICCSE 2021 In 5th International Conference on Crowd Science and Engineering [Paper] -
A Survey on Knowledge Enhanced EHR Data Mining
Jiancheng Zhang, Xiao Yang, Hefeng Meng, Zhiqiang Lin, Yonghui Xu*, Lizhen Cui*
ICCSE 2021 In 5th International Conference on Crowd Science and Engineering [Paper]
🧑🏫 Services
Conference Reviewer
- International Conference on Learning Representations (ICLR), 2027
- Neural Information Processing Systems (NeurIPS), 2026
- Conference on Language Modeling (COLM), 2026
- International Conference on Learning Representations (ICLR), 2026
- International Conference on Machine Learning (ICML), 2025
- International Conference on Learning Representations (ICLR), 2025
- Conference on Language Modeling (COLM), 2025
Journal Reviewer
- Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026
🎖️ Awards
- Top Reviewer, NeurIPS 2026
- UCR Dean’s Distinguished Fellowship, 2024
- 2022 SDU School of Software Scholarship, 2022
- 2022 SDU School of Software Specialty Scholarship, 2022
- 2021 SDU School of Software Scholarship, 2021
- First Prize of Shandong, National Mathematical Modeling Contest, 2021
📚 Teaching
Teaching Assistant (TA) at UCR:
- EE114: Probability, Random Variables, and Random Processes in Electrical Engineering, Fall’2025
- EE114: Probability, Random Variables, and Random Processes in Electrical Engineering, Winter’2025
🎓 Education
- 2024.09 - Now, PhD Student, University of California, Riverside
- 2020.09 - 2024.06, Undergraduate, Shandong University
💼 Experience
Intern Experience
- New York University
Research Intern
Work with: Dr. Mingtao Xia