Get started
Author

Changshun Wu

A survey of safety and trustworthiness of large language models through the lens of verification and validation
2024 · Xiaowei Huang, Wenjie Ruan, et al. · Artificial Intelligence Review · 166
Safeguarding large language models: a survey
2025 · Yi Dong, Ronghui Mu, et al. · Artificial Intelligence Review · 118
PDF
What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety-Critical Systems
2023 · Saddek Bensalem, Chih-Hong Cheng, et al. · Lecture notes in computer science · 14
PDF
Customizable Reference Runtime Monitoring of Neural Networks Using Resolution Boxes
2023 · Changshun Wu, Yliès Falcone, et al. · Lecture notes in computer science · 13
PDF
Continuous Engineering for Trustworthy Learning-Enabled Autonomous Systems
2023 · Saddek Bensalem, Panagiotis Katsaros, et al. · Lecture notes in computer science · 9
PDF
DeepAbstraction: 2-Level Prioritization for Unlabeled Test Inputs in Deep Neural Networks
2022 · Hamzah Al-Qadasi, Changshun Wu, et al. · IEEE International Conference on Artificial Intelligence Testing (AITest) · 9
Box-Based Monitor Approach for Out-of-Distribution Detection in YOLO: An Exploratory Study
2024 · Weicheng He, Changshun Wu, et al. · Lecture notes in computer science · 8
Bridging formal methods and machine learning with model checking and global optimisation
2023 · Saddek Bensalem, Xiaowei Huang, et al. · Journal of Logical and Algebraic Methods in Programming · 7
BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection
2024 · Changshun Wu, Weicheng He, et al. · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · 5
PDF
Predicting macro-mechanical properties of loess from basic physical properties using various machine learning methods
2025 · Yongfeng Zhu, Wei Xiong, et al. · Environmental Earth Sciences · 4
Prioritizing Corners in OoD Detectors via Symbolic String Manipulation
2022 · Chih-Hong Cheng, Changshun Wu, et al. · Lecture notes in computer science · 4
PDF
Digital twin for the formal analysis of a depth of anesthesia controller
2025 · Mohamed AbdElSalam, Saddek Bensalem, et al. · SIMULATION · 3
A Digital Twin prototype for traffic sign recognition of a learning-enabled autonomous vehicle
2024 · AbdElSalam, Mohamed, Ali, Loai, et al. · arXiv (Cornell University) · 2
PDF
Formal Verification of ST Programs using CSP
2021 · Qibin Zhou, Fangda Cai, et al. · Journal of Physics Conference Series · 2
PDF
Correction to “Synchronizing sequences on a class of unbounded systems using synchronized Petri nets”
2019 · Changshun Wu, Isabel Demongodin, et al. · Discrete Event Dynamic Systems · 2
Numerical investigation on effects of particle size distribution on loess mechanics using DEM
2025 · Yongfeng Zhu, Yani Wei, et al. · Environmental Earth Sciences · 1
Mitigating Hallucinations in YOLO-based Object Detection Models: A Revisit to Out-of-Distribution Detection
2025 · Weicheng He, Changshun Wu, et al. · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · 1
Computation of synchronizing sequences for a class of 1-place-unbounded synchronized Petri nets
2018 · Changshun Wu, Isabel Demongodin, et al. · International Conference on Control, Decision and Information Technologies (CoDIT) · 1
Conversion of 1-Place-Unbounded Synchronized Petri Nets into Weighted Automata
2017 · Changshun Wu, Isabel Demongodin, et al. · IFAC-PapersOnLine · 1
AgentMonopoly: Behavioral Patterns and Persona Control in LLM Agents
2026 · Wu, Changshun, Li, Mengyu, et al. · arXiv (Cornell University)
PDF
SPK: Eliciting Structured Prior Knowledge for Interpretable Out-of-Distribution Detection in Real-Time Object Detection
2026 · Wu, Changshun, He, Weicheng, et al. · arXiv (Cornell University)
PDF
SCOPE: Sequential Conformal Probing for Reliable OOD Rejection in LLM Services
2026 · Li, Zhuoyun, Wang, Boxuan, et al. · arXiv (Cornell University)
PDF
Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment
2026 · Bensalem, S., Dong, Y., et al. · arXiv (Cornell University)
PDF
Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
2026 · He, Qisong, Hu, Jinwei, et al. · arXiv (Cornell University)
PDF
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
2026 · He, Qisong, Huang, Xinmiao, et al. · arXiv (Cornell University)
PDF
Works count: 42
Citation count: 370
H-index: 7
I10-index: 4
Year
Topic
Type