Vaibhav Unhelkar

Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations

2022 · arXiv (Cornell University)

Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A better understanding of the needs of XAI users, as well as human-centered evaluations of explainable models are both a …

I-CEE: Tailoring Explanations of Image Classification Models to User Expertise

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

Effectively explaining decisions of black-box machine learning models is critical to responsible deployment of AI systems that rely on them. Recognizing their importance, the field of explainable AI (XAI) provides several techniques to generate these …

Hierarchical Imitation Learning of Team Behavior from Heterogeneous Demonstrations

2025 · arXiv (Cornell University)

Successful collaboration requires team members to stay aligned, especially in complex sequential tasks. Team members must dynamically coordinate which subtasks to perform and in what order. However, real-world constraints like partial observability and limited communication …