Z. Sun

Z. Sun

Assistant Professor @ SUFE

Research Profile

Efficient Machine Learning Lab @ SUFE

We develop novel and efficient learning algorithms for modern artificial intelligence and theoretical machine learning problems.

Artificial General Intelligence LLMs, world models, diffusion models, reinforcement learning, and scalable learning systems.
Theoretical Machine Learning Monte Carlo methods, variational inference, and probabilistic machine learning.

Zhuo Sun is a tenure-track Assistant Professor in the School of Statistics and Data Science at Shanghai University of Finance and Economics.

  • Visiting Researcher at Imperial College London
  • Area Chair/Program Committee: ICML/ICLR/NeurIPS/AISTATS/UAI
  • Ph.D. in Machine Learning and Computational Statistics from University College London, supervised by Prof. François-Xavier Briol and Prof. Jinghao-Xue; master's degree in statistical science from the University of Oxford, supervised by Prof. George Deligiannidis.
Interested in these research directions? Please feel free to get in touch. zhuosunreid@outlook.com

Research Topics and Goals

Research topics and goals diagram

Preprints & Working Papers

* equal contribution; † corresponding author

arxiv
2026+
Cheng, X.*; Yuan, W.*; Mu, Z.; Zhang, Y.; Yang, Y.; Wang, H.; Sun, Z.†; Liu, C.† (2026). Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization arxiv. arXiv
arxiv
2026+
Zhao, Y.*; Cheng, X.*; Liu, H.*; He, B.; Zhang, Xin.; Zhu, H.; Chen, W.; Zeng, L.; Sun, Z.† (2026). Saliency-Aware Regularized Quantization Calibration for Large Language Models arxiv. arXiv
arxiv
2026+
Cheng, X*; Wang, H.*; Yuan, W.; Wang, Z.; Chen, Z.; Zeng, L.; Sun, Z.† (2026). Fisher Decorator: Refining Flow Policy via A Local Transport Map arxiv. arXiv
arxiv
2026+
Yang, Y.; Cheng, X.; He, Y.; Li, K.; Yuan W.; Sun, Z.† (2026). Outlier-Robust Diffusion Posterior Sampling for Bayesian Inverse Problems arxiv. arXiv
ICML'W
2026+
Guo, S.; Cheng, X.; Liu, X.; Niu, Z.; Chen, Z.; Liu, X.; Sun, Z.† (2026). Random-Projection Tree Stein Variational Gradient Descent In ICML 2026 Workshop on Structured Probabilistic Inference & Generative Modeling. arXiv
ICML'W
2026+
Kiyohara, N.*; Zhu, BH.*; Hassanin, R.*; Sun, Z.†; Chen, WL.; Bhatt, S.†; Li, YZ.† (2026). Interdomain Attention: Beyond Token-Level Key-Value Memory In ICML 2026 Workshop on Foundations of Deep Generative Models: Understanding Memorization, Generalization, and Reasoning. arXiv

Publications 📖

* equal contribution; † corresponding author

ICML
2026
Cheng, X.*; Yuan, W.*; Li, B.; Xu, Y.; Yang, Y.; Liang, H.; Peng, B.; Loftin, R.; Sun, Z.; Hu, Y. (2026). How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models? In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026). arXiv
ICLR
2026
Li, K.; Yang, Y.; Chen, X.; He, Y.; Sun, Z.† (2026). Multilevel Control Functional. In International Conference on Learning Representations (ICLR 2026). With Score 8,8,8 (Rank 2nd over 19000 submissions)
ICLR
2026
Cheng, X.; Yuan, W.; Yang, Y.; Zhang, Y.; Cheng, S.; He, Y.; Sun, Z.† (2026). Information Shapes Koopman Representation. In International Conference on Learning Representations (ICLR 2026). Selected for Oral Presentation (top 1.18%)
ICLR
2026
Cheng, X.; Yang, Y.; Jiang, W.; Yuan, C.; Sun, Z.; Hu, Y. (2026). From Embedding to Control: Representations for Stochastic Multi-Object Systems. In International Conference on Learning Representations (ICLR 2026).
UAI
2023
Sun, Z.; Oates, C. J; Briol, F-X. (2023). Meta-learning Control Variates: Variance Reduction with Limited Data. In Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023). Selected for Oral Presentation (top 3%)
ICML SPIGM
2023
Li, K.*; Sun, Z.*† (2023). Multilevel Control Functional (Short Version). In ICML 2023 SPIGM.
ICML
2023
Sun, Z.; Barp, A.; Briol, F.-X. (2023). Vector-valued Control Variates. In Proceedings of the 40th International Conference on Machine Learning (ICML 2023). ASA SBSS Best Student Paper (2022)
AISTATS
2021
Sun, Z.; Wu, J.; Li, X.; Yang, W.; Xue, J-H. (2021). Amortized Bayesian Prototype Meta-learning: A new probabilistic meta-learning approach to few-shot image classification. In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics(AISTATS 2023).
Neurocomputing
2021
Li, X.*; Sun, Z.*; Xue, J-H. ; Ma, Z. (2021). A Concise Review of Recent Few-shot Meta-learning Methods. Neurocomputing.
IEEE TIP
2020
Li, X.*; Wu, J.*; Sun, Z.*; Ma, Z. ; Cao, J.; Xue, J-H. (2020). Bi-Similarity Network for Fine-grained Few-shot Image Classification. IEEE Transactions on Image Processing.