Publications

PML4SC Publications

4 papers listed

2 accepted papers

2026 latest publication year

2026

conference Accepted

Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes

Yan Zhang , Xuefeng Liu , Sipeng Chen , Sascha Ranftl , Chong Liu , Shibo Li

ICML 2026 Proceedings of the 43rd International Conference on Machine Learning 2026

A regime-adaptive Bayesian optimization framework that models heterogeneous response patterns with Dirichlet process mixtures of Gaussian processes.

arXiv

PDF

BibTeX

@article{zhang2026rambo,
  title={Regime-Adaptive {Bayesian} Optimization via {Dirichlet} Process Mixtures of {Gaussian} Processes},
  author={Zhang, Yan and Liu, Xuefeng and Chen, Sipeng and Ranftl, Sascha and Liu, Chong and Li, Shibo},
  journal={arXiv preprint arXiv:2601.20043},
  year={2026}
}

conference Accepted

COMPOL: A Unified Neural Operator Framework for Scalable Multi-Physics Simulations

Junqi Qu , Tao Wang , Yushun Dong , Hewei Tang , Shibo Li

IJCNN 2026 International Joint Conference on Neural Networks 2026

A unified neural operator framework for scalable multi-physics simulations, currently available as an arXiv preprint and accepted by IJCNN 2026.

arXiv

PDF

BibTeX

@article{qu2025compol,
  title={{COMPOL}: A Unified Neural Operator Framework for Scalable Multi-Physics Simulations},
  author={Qu, Junqi and Wang, Tao and Dong, Yushun and Tang, Hewei and Li, Shibo},
  journal={arXiv preprint arXiv:2501.17296},
  year={2025}
}

2025

preprint

Beyond Heuristics: Globally Optimal Configuration of Implicit Neural Representations

Sipeng Chen , Yan Zhang , Shibo Li

arXiv 2025 arXiv preprint 2025

OptiINR formulates implicit neural representation configuration as a principled global optimization problem and uses Bayesian optimization to jointly search activation families and initialization parameters for stronger, more stable performance.

arXiv

PDF

BibTeX

@article{chen2025optiinr,
  title={Beyond Heuristics: Globally Optimal Configuration of Implicit Neural Representations},
  author={Chen, Sipeng and Zhang, Yan and Li, Shibo},
  journal={arXiv preprint arXiv:2509.23139},
  year={2025}
}

conference Published

ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks

Zhan Cheng , Bolin Shen , Tianming Sha , Yuan Gao , Shibo Li , Yushun Dong

KDD 2025 Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2025

ATOM is a real-time defense framework for graph neural network model extraction attacks that combines sequential modeling, reinforcement learning, and structural graph features to detect evolving attack behavior more effectively.

DOI

PDF

BibTeX

@inproceedings{cheng2025atom,
  title={{ATOM}: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks},
  author={Cheng, Zhan and Shen, Bolin and Sha, Tianming and Gao, Yuan and Li, Shibo and Dong, Yushun},
  booktitle={Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  publisher={Association for Computing Machinery},
  pages={322--333},
  year={2025},
}