| Captum: A unified and generic model interpretability library for PyTorch. arXiv 2020 N Kokhlikyan, V Miglani, M Martin, E Wang, B Alsallakh, J Reynolds, ... arXiv preprint arXiv:2009.07896, 0 | 1308 | |
| Mind the Pad--CNNs Can Develop Blind Spots B Alsallakh, N Kokhlikyan, V Miglani, J Yuan, O Reblitz-Richardson arXiv preprint arXiv:2010.02178, 2020 | 117 | 2020 |
| Xair: A framework of explainable ai in augmented reality X Xu, A Yu, TR Jonker, K Todi, F Lu, X Qian, JM Evangelista Belo, T Wang, ... Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems …, 2023 | 85 | 2023 |
| Pytorch captum N Kokhlikyan, V Miglani, M Martin, E Wang, J Reynolds, A Melnikov, ... GitHub repository, 2019 | 57 | 2019 |
| Captum: A unified and generic model interpretability library for PyTorch. arXiv N Kokhlikyan, V Miglani, M Martin, E Wang, B Alsallakh, J Reynolds, ... arXiv preprint arXiv:2009.07896 2, 5, 2020 | 55 | 2020 |
| Using captum to explain generative language models V Miglani, A Yang, A Markosyan, D Garcia-Olano, N Kokhlikyan Proceedings of the 3rd workshop for natural language processing open source …, 2023 | 54 | 2023 |
| Instantiating resources of an IT-service JE Arwe, G Breiter, M Chodorowski, F Dross, N Kokhlikyan, HA Le, ... US Patent 9,203,774, 2015 | 30 | 2015 |
| Investigating saturation effects in integrated gradients V Miglani, N Kokhlikyan, B Alsallakh, M Martin, O Reblitz-Richardson arXiv preprint arXiv:2010.12697, 2020 | 29 | 2020 |
| Method cards for prescriptive machine-learning transparency D Adkins, B Alsallakh, A Cheema, N Kokhlikyan, E McReynolds, P Mishra, ... Proceedings of the 1st International Conference on AI Engineering: Software …, 2022 | 25 | 2022 |
| How much do language models memorize? JX Morris, C Sitawarin, C Guo, N Kokhlikyan, GE Suh, AM Rush, ... arXiv preprint arXiv:2505.24832, 2025 | 22 | 2025 |
| Coauthors, 2020: Captum: A unified and generic model interpretability library for PyTorch N Kokhlikyan arXiv preprint arXiv:2009.07896, 2009 | 21 | 2009 |
| Investigating sanity checks for saliency maps with image and text classification N Kokhlikyan, V Miglani, B Alsallakh, M Martin, O Reblitz-Richardson arXiv preprint arXiv:2106.07475, 2021 | 19 | 2021 |
| Debugging the internals of convolutional networks B Alsallakh, N Kokhlikyan, V Miglani, S Muttepawar, E Wang, S Zhang, ... eXplainable AI approaches for debugging and diagnosis., 2021 | 16 | 2021 |
| Filtering electronic messages C Sathi, A Tarasov, D Mykhaylov, N Kokhlikyan, R Ivchenko US Patent 10,447,635, 2019 | 16 | 2019 |
| Prescriptive and descriptive approaches to machine-learning transparency D Adkins, B Alsallakh, A Cheema, N Kokhlikyan, E McReynolds, P Mishra, ... CHI conference on human factors in computing systems extended abstracts, 1-9, 2022 | 15 | 2022 |
| Instantiating resources of an IT-service JE Arwe, G Breiter, M Chodorowski, F Dross, N Kokhlikyan, HA Le, ... US Patent 9,432,247, 2016 | 14 | 2016 |
| Building recommender systems with PyTorch D Mudigere, M Naumov, J Spisak, G Chauhan, N Kokhlikyan, A Singh, ... Proceedings of the 26th ACM SIGKDD International Conference on Knowledge …, 2020 | 9 | 2020 |
| Fine-grained interpretation and causation analysis in deep NLP models H Sajjad, N Kokhlikyan, F Dalvi, N Durrani arXiv preprint arXiv:2105.08039, 2021 | 7 | 2021 |
| Error discovery by clustering influence embeddings F Wang, J Adebayo, S Tan, D Garcia-Olano, N Kokhlikyan Advances in Neural Information Processing Systems 36, 41765-41777, 2023 | 6 | 2023 |
| Mind the pool: Convolutional neural networks can overfit input size B Alsallakh, D Yan, N Kokhlikyan, V Miglani, O Reblitz-Richardson, ... The Eleventh International Conference on Learning Representations, 2022 | 6 | 2022 |
Bilal AlsallakhVoxel AIVerified email at voxelai.com
