Changshun Wu

According to our database, Changshun Wu authored at least 28 papers between 2018 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Revisiting Out-of-Distribution Detection in Real-Time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigm.

Changshun Wu, Weicheng He, Chih-Hong Cheng, Xiaowei Huang, Saddek Bensalem

IEEE Trans. Pattern Anal. Mach. Intell., May, 2026

Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment.

Saddek Bensalem, Yi Dong, M. Franzle, Xiaowei Huang, J. Kroger, Dejan Nickovic, A. Nouri, R. Roy, Changshun Wu

CoRR, May, 2026

Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation.

Qisong He, Xinmiao Huang, Jinwei Hu, Zhuoyun Li, Yi Dong, Changshun Wu, Xiaowei Huang

CoRR, May, 2026

PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors.

Xinmiao Huang, Jinwei Hu, Rajarshi Roy, Changshun Wu, Yi Dong, Xiaowei Huang

CoRR, May, 2026

What Matters to an LLM? Behavioral and Computational Evidences from Summarization.

Yongxin Zhou, Changshun Wu, Philippe Mulhem, Didier Schwab, Maxime Peyrard

Proceedings of the Findings of the Association for Computational Linguistics: EACL 2026, 2026

2025

Safeguarding large language models: a survey.

Yi Dong, Ronghui Mu, Yanghao Zhang, Siqi Sun, Tianle Zhang, Changshun Wu, Gaojie Jin, Yi Qi, Jinwei Hu, Jie Meng, Saddek Bensalem, Xiaowei Huang

Artif. Intell. Rev., December, 2025

LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layers.

Changshun Wu, Tianyi Duan, Saddek Bensalem, Chih-Hong Cheng

CoRR, June, 2025

Digital twin for the formal analysis of a depth of anesthesia controller.

Mohamed Abdelsalam, Saddek Bensalem, Antoine Delacourt, Weicheng He, Panagiotis Katsaros, Nikolaos Kekatos, Ricardo Ruiz Nolasco, Doron Peled, Matthieu Ponchant, Ismail Ryad, Anastasios Temperekidis, Changshun Wu

Simul., 2025

Runtime Monitoring and Enforcement of Conditional Fairness in Generative AIs.

Chih-Hong Cheng, Changshun Wu, Xingyu Zhao, Saddek Bensalem, Harald Ruess

Proceedings of the Runtime Verification - 25th International Conference, 2025

Mitigating Hallucinations in YOLO-based Object Detection Models: A Revisit to Out-of-Distribution Detection.

Weicheng He, Changshun Wu, Chih-Hong Cheng, Xiaowei Huang, Saddek Bensalem

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2025

Def-VAE: Identifying Adversarial Inputs with Robust Latent Representations.

Chengye Li, Changshun Wu, Rongjie Yan

Proceedings of the 16th International Conference on Internetware, 2025

Out-of-Distribution Detectors: Not Yet Primed for Practical Deployment.

Changshun Wu, Wendi Ding, Xiaowei Huang, Saddek Bensalem

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Randomized Smoothing Meets Vision-Language Models.

Emmanouil Seferis, Changshun Wu, Stefanos Kollias, Saddek Bensalem, Chih-Hong Cheng

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

A survey of safety and trustworthiness of large language models through the lens of verification and validation.

Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu, André Freitas, Mustafa A. Mustafa

Artif. Intell. Rev., July, 2024

Bridging formal methods and machine learning with model checking and global optimisation.

Saddek Bensalem, Xiaowei Huang, Wenjie Ruan, Qiyi Tang, Changshun Wu, Xingyu Zhao

J. Log. Algebraic Methods Program., February, 2024

Formal Specification, Assessment, and Enforcement of Fairness for Generative AIs.

Chih-Hong Cheng, Changshun Wu, Harald Ruess, Xingyu Zhao, Saddek Bensalem

CoRR, 2024

Box-Based Monitor Approach for Out-of-Distribution Detection in YOLO: An Exploratory Study.

Weicheng He, Changshun Wu, Saddek Bensalem

Proceedings of the Runtime Verification - 24th International Conference, 2024

BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection.

Changshun Wu, Weicheng He, Chih-Hong Cheng, Xiaowei Huang, Saddek Bensalem

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024

Stress Matrix-Based Formation Control of Multi-Agent Systems with Discrete-Time Communication.

Okechi Onuoha, Brendan Chijioke Ubochi, Suleiman Kurawa, Zezhi Tang, Changshun Wu, Yi Dong

Proceedings of the 12th International Conference on Systems and Control, 2024

2023

Towards Rigorous Design of OoD Detectors.

Chih-Hong Cheng, Changshun Wu, Harald Ruess, Saddek Bensalem

CoRR, 2023

Continuous Engineering for Trustworthy Learning-Enabled Autonomous Systems.

Saddek Bensalem, Panagiotis Katsaros, Dejan Nickovic, Brian Hsuan-Cheng Liao, Ricardo Ruiz Nolasco, Mohamed Abd El Salam Ahmed, Tewodros A. Beyene, Filip Cano, Antoine Delacourt, Hasan Esen, Alexandru Forrai, Weicheng He, Xiaowei Huang, Nikolaos Kekatos, Bettina Könighofer, Michael Paulitsch, Doron Peled, Matthieu Ponchant, Lev Sorokin, Son Tong, Changshun Wu

Proceedings of the Bridging the Gap Between AI and Reality, 2023

What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety-Critical Systems.

Saddek Bensalem, Chih-Hong Cheng, Wei Huang, Xiaowei Huang, Changshun Wu, Xingyu Zhao

Proceedings of the Bridging the Gap Between AI and Reality, 2023

Customizable Reference Runtime Monitoring of Neural Networks Using Resolution Boxes.

Changshun Wu, Yliès Falcone, Saddek Bensalem

Proceedings of the Runtime Verification - 23rd International Conference, 2023

A digital twin prototype for traffic sign recognition of a learning-enabled autonomous vehicle.

Mohamed Abdelsalam, Loai Ali, Saddek Bensalem, Weicheng He, Panagiotis Katsaros, Nikolaos Kekatos, Doron Peled, Anastasios Temperekidis, Changshun Wu

Proceedings of the Companion Proceedings of the 16th IFIP WG 8.1 Working Conference on the Practice of Enterprise Modeling and the 13th Enterprise Design and Engineering Working Conference: BES, DTE, FACETE, Tools & Demos, Forum, EDEN Doctoral Consortium co-located with PoEM 2023, Vienna, Austria, November 28, 2023

2022

Prioritizing Corners in OoD Detectors via Symbolic String Manipulation.

Chih-Hong Cheng, Changshun Wu, Emmanouil Seferis, Saddek Bensalem

Proceedings of the Automated Technology for Verification and Analysis, 2022

DeepAbstraction: 2-Level Prioritization for Unlabeled Test Inputs in Deep Neural Networks.

Hamzah Al-Qadasi, Changshun Wu, Yliès Falcone, Saddek Bensalem

Proceedings of the IEEE International Conference On Artificial Intelligence Testing, 2022

2019

Correction to "Synchronizing sequences on a class of unbounded systems using synchronized Petri nets".

Changshun Wu, Isabel Demongodin, Alessandro Giua

Discret. Event Dyn. Syst., 2019

2018

Computation of synchronizing sequences for a class of 1-place-unbounded synchronized Petri nets.

Changshun Wu, Isabel Demongodin, Alessandro Giua

Proceedings of the 5th International Conference on Control, 2018