Zhen Zhang ☕️
Zhen Zhang

Senior Research Fellow

About Me

Zhen Zhang is currently a Postdoctoral Researcher at the University of Adelaide, working with Prof. Javen Qinfeng Shi. Previously, he was a postdoctoral research fellow in the Department of Computer Science at the National University of Singapore under the supervision of Prof. Lee Wee Sun. He received a PhD in Computer Science from Northwestern Polytechnical University (Xi’an, China) under the supervision of Prof. Yanning Zhang. During Nov. 2012 to Dec. 2014, he was a visiting student at Australian Centre for Visual Technologies, University of Adelaide, under the supervision of Prof. Anton van den Hengel and Prof. Javen Qinfeng Shi. He completed his bachelor degree in Computer Science in 2010 at School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China.

Interests
  • Causality
  • Machine Learning
  • Artificial Intelligence
Education
  • PhD in Computer Science

    Northwestern Polytechnical University

  • Bachelor in Computer Science

    Northwestern Polytechnical University

Recent News
Working Papers
(2025). Rethinking State Disentanglement in Causal Reinforcement Learning. Submitted to International Conference on Machine Learning (ICML) 2025.
(2025). Silver Linings: On the Types of Distribution Shifts that Enhance Identifiability in Causal Representation Learning. Submitted to International Conference on Machine Learning (ICML) 2025.
(2025). The Quest for Winning Tickets in Low-Rank Adapters. Submitted to International Conference on Machine Learning (ICML) 2025.
(2025). I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?. Submitted to International Conference on Machine Learning 2025.
(2024). Decomposing Task Vectors for Refined Model Editing. Submitted to International Conference on Computer Vision and Pattern Recognition (CVPR) 2025.
Recent Publications
(2025). Analytic DAG Constraints for Differentiable DAG Learning. International Conference on Learning Representations.
(2025). CLAP: Isolating Content from Style Through Contrastive Learning with Augmented Prompts. Computer Vision – ECCV 2024.
(2025). Generalization of anomaly detection in bridge structures using a vibration‐based Siamese convolutional neural network. Computer aided Civil Eng.
(2024). Identifiable Latent Polynomial Causal Models Through the Lens of Change. ICLR.
(2024). A Causal Inspired Early-Branching Structure for Domain Generalization. Int J Comput Vis.