Zhao Zhilin

Associate Professor

Email: zhaozhlin@mail.sysu.edu.cn

Address: A613

Links: https://lawliet-zzl.github.io/

About Me

Zhilin Zhao, Associate Professor, Jointly Appointed Professor at Shenzhen Loop Area Institute, and recipient of a National-Level Young Talent Program

Research Interests

Our research primarily focuses on machine learning, with particular emphasis on model behavior and generalization in unknown environments. Guided by the philosophy that simplicity is the ultimate sophistication, we value the integration of theory and practice and strive to bridge the gap between algorithmic principles and real-world applications. Our current research interests include, but are not limited to:

  • Foundations of Machine Learning: out-of-distribution generalization, robust optimization, uncertainty modeling, time-series analysis, and related topics
  • Generative Models: image generation, controllable generation, image editing, generative contrastive learning, and related topics
  • Large Language Models: retrieval-augmented generation, hallucination detection and correction, cross-lingual and cross-task transfer
  • Embodied Intelligence and Multi-Agent Systems: sim-to-real transfer and policy adaptation, language-driven embodied manipulation, multi-agent collaboration and decision-making
  • Open Exploration: if you have your own research interests, you are also welcome to share them with us so that we can learn and explore together

 

👉 Click here to learn more about our research group.

 

📌 Our laboratory provides extensive computational resources for group members. If you are interested in my research and would like to learn and explore with us, Ph.D. students, master's students, and outstanding undergraduate students are warmly welcome to join our laboratory.

 

📢 We currently have openings for professional master's students, academic master's students, Ph.D. students, and jointly supervised Ph.D. students with Shenzhen Hetao College for admission in 2027. Please feel free to contact me if you are interested.  

🙏 Due to the large volume of emails I receive, your message may occasionally be overlooked. If you do not receive a response after some time, please feel free to send me a reminder. I sincerely apologize for any inconvenience this may cause.

 

Research Projects

  • National High-Level Young Talent Program Project (2024–2027), Principal Investigator
  • General Program of the National Natural Science Foundation of China (2025–2028), Principal Investigator
  • Key-Area Research and Development Program of Guangdong Province (2026–2029), Project Lead
  • Young Scientist Program of Sun Yat-sen University (2025–2028), Principal Investigator

Awards and Honors

  • 2018, Outstanding Master's Graduate of Guangdong Province
  • 2016, Outstanding Undergraduate Graduate of Sun Yat-sen University

Education

  • Aug. 2018–Aug. 2022, Ph.D., Faculty of Engineering and Information Technology, University of Technology Sydney
  • Sep. 2016–Jun. 2018, Master's Degree, School of Data and Computer Science, Sun Yat-sen University
  • Sep. 2012–Jun. 2016, Bachelor's Degree, School of Mobile Information Engineering, Sun Yat-sen University

Professional Experience

  • Dec. 2024–Present, Associate Professor, School of Computer Science and Engineering, Sun Yat-sen University
  • May 2023–Nov. 2024, Postdoctoral Research Fellow, Faculty of Science and Engineering, Macquarie University
  • Aug. 2022–May 2023, Postdoctoral Research Fellow, Faculty of Engineering and Information Technology, University of Technology Sydney

Courses Taught

Students are welcome to report any errors or omissions in the course materials and to provide suggestions for improving the course content and presentation via WeCom or email. Your support and feedback are greatly appreciated.

Selected Publications

[TPAMI] Zhilin Zhao, Longbing Cao, Yixuan Zhang, Kun-Yu Lin, Wei-Shi Zheng. Distilling the Unknown to Unveil Certainty. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 47, no. 10, pp. 9232–9249, 2025. 

[TPAMI] Zhilin Zhao, Longbing Cao, Kun-Yu Lin. Supervision Adaptation Balancing In-Distribution Generalization and Out-of-Distribution Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 45, no. 12, pp. 15743–15758, 2023.

[TPAMI] Zhilin Zhao, Longbing Cao, Kun-Yu Lin. Revealing the Distributional Vulnerability of Discriminators by Implicit Generators. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 45, no. 7, pp. 8888–8901, 2022.

[AIJ] Zhilin Zhao, Longbing Cao, Philip S. Yu. Out-of-distribution Detection by Regaining Lost Clues. Artificial Intelligence Journal (AIJ), vol. 339, 104275, 2024.

[TMLR] Zhilin Zhao, Longbing Cao. Dual Representation Learning for Out-of-Distribution Detection. Transactions on Machine Learning Research (TMLR), pp. 1–21, 2023.

[MLJ] Zhilin Zhao, Longbing Cao. Weighting Non-IID Batches for Out-of-distribution Detection. Machine Learning Journal (MLJ), vol. 113, no. 10, pp. 7371–7391, 2024.

[TNNLS] Zhilin Zhao, Longbing Cao, Kun-Yu Lin. Out-of-Distribution Detection by Cross-Class Vicinity Distribution of In-Distribution Data. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 35, no. 10, pp. 13777–13788, 2024.

[TNNLS] Zhilin Zhao, Longbing Cao, Chang-Dong Wang. Gray Learning from Non-iid Data with Out-of-distribution Samples. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 36, no. 1, pp. 1396–1409, 2025.

[NeurIPS] Zhilin Zhao, Longbing Cao, Xuhui Fan, Wei-Shi Zheng. Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data. Advances in Neural Information Processing Systems (NeurIPS), pp. 1–28, 2024.

[NeurIPS] Zhilin Zhao, Longbing Cao. R-divergence for Estimating Model-oriented Distribution Discrepancy. Advances in Neural Information Processing Systems (NeurIPS), pp. 1–19, 2023.

[AAAI] Zhilin Zhao, Longbing Cao, Yuanyu Wan. Mixture of Online and Offline Experts for Non-stationary Time Series. Association for the Advancement of Artificial Intelligence (AAAI), pp. 1–8, 2025.

[IJCAI] Zhilin Zhao, Longbing Cao, Philip S. Yu. Out-of-distribution Detection by Regaining Lost Clues. International Joint Conference on Artificial Intelligence (IJCAI), 2025.

[IJCAI] Zhilin Zhao, Longbing Cao, Philip S. Yu. Deep Non-IID Learning. International Joint Conference on Artificial Intelligence (IJCAI), 2024 (Tutorial).

[CVPR] Shuxuan Li (M.S. student), Zhilin Zhao*, Quyu Kong, Wei-Shi Zheng. Bridging Domain Expertise and Generalization for Performance Estimation, IEEE/CVF Conference on Computer Vision & Pattern Recognition (CVPR), 2026.

[EMNLP] Lang Zhou (Ph.D. student), Shuxuan Li, Zhuohao Li, Shi Liu, Wei-Shi Zheng, Zhilin Zhao*. UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference, Empirical Methods in Natural Language Processing (EMNLP), Main Conference, 2026.