Narine Kokhlikyan

Captum: A unified and generic model interpretability library for PyTorch

Narine Kokhlikyan, Vivek Miglani, Miguel Vargas Martín et al. · arXiv (Cornell University) · 2020 · 625 citations · Full text

Artificial Intelligence, Engineering, Machine Learning +21

XAIR: A Framework of Explainable AI in Augmented Reality

Xuhai Xu, Anna Yu, Tanya R. Jonker et al. · 2023 · 62 citations · Full text

Mind the Pad -- CNNs can Develop Blind Spots

Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani et al. · arXiv (Cornell University) · 2020 · 31 citations · Full text

Convolutional Neural Network, Engineering, Machine Learning +20

Method cards for prescriptive machine-learning transparency

David Adkins, Bilal Alsallakh, Adeel Cheema et al. · 2022 · 16 citations

Artificial Intelligence, Engineering, Machine Learning +16

Using Captum to Explain Generative Language Models

Vivek Miglani, Aobo Yang, Aram Markosyan et al. · 2023 · 14 citations · Full text