Publications | Chase Walker

2025

Explaining the Reasoning of Large Language Models Using Attribution Graphs

Chase Walker and Rickard Ewetz

arXiv preprint arXiv:2512.15663, 2025
Metric-Driven Attributions for Vision Transformers

Chase Walker, Sumit Kumar Jha, and Rickard Ewetz

In The Thirteenth International Conference on Learning Representations, 2025
Verifiable Natural Language to Linear Temporal Logic Translation: A Benchmark Dataset and Evaluation Suite

William H English, Chase Walker, Dominic Simon, and 2 more authors

arXiv preprint arXiv:2507.00877, 2025
Explaining ViTs Using Information Flow

Chase Walker, Md Rubel Ahmed, Sumit Kumar Jha, and 1 more author

In International Conference on Artificial Intelligence and Statistics, 2025
GinSign: Grounding Natural Language Into System Signatures for Temporal Logic Translation

William English, Chase Walker, Dominic Simon, and 1 more author

arXiv preprint arXiv:2512.16770, 2025
Detecting and Removing Adversarial Patches using Frequency Signatures

Dominic Simon, Chase Walker, Sumit Jha, and 1 more author

In 2025 International Joint Conference on Neural Networks (IJCNN), 2025

Attribution quality metrics with magnitude alignment

Chase Walker, Dominic Simon, Kenny Chen, and 1 more author

In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, 2024
Integrated decision gradients: Compute your attributions where the model makes its decision

Chase Walker, Sumit Jha, Kenny Chen, and 1 more author

In Proceedings of the AAAI Conference on Artificial Intelligence, 2024
Out-of-Distribution Detection for Contrastive Models Using Angular Distance Measures

M Shifat Hossain, Sumit Kumar Jha, Chase Walker, and 1 more author

In 2024 International Conference on Machine Learning and Applications (ICMLA), 2024

Adversarial pixel and patch detection using attribution analysis

Chase Walker, Dominic Simon, Sumit Kumar Jha, and 1 more author

In MILCOM 2023-2023 IEEE Military Communications Conference (MILCOM), 2023