| Fooling neural network interpretations via adversarial model manipulation J Heo, S Joo, T Moon Advances in neural information processing systems 32, 2019 | 243 | 2019 |
| Toward a unified framework for interpreting machine-learning models in neuroimaging L Kohoutová, J Heo, S Cha, S Lee, T Moon, TD Wager, CW Woo Nature protocols 15 (4), 1399-1435, 2020 | 145 | 2020 |
| Estimating PM2. 5 concentration of the conterminous United States via interpretable convolutional neural networks Y Park, B Kwon, J Heo, X Hu, Y Liu, T Moon Environmental Pollution 256, 113395, 2020 | 122 | 2020 |
| Robust explanation constraints for neural networks M Wicker, J Heo, L Costabello, A Weller arXiv preprint arXiv:2212.08507, 2022 | 19 | 2022 |
| Towards more robust interpretation via local gradient alignment S Joo, S Jeong, J Heo, A Weller, T Moon Proceedings of the AAAI Conference on Artificial Intelligence 37 (7), 8168-8176, 2023 | 8 | 2023 |
| Do Concept Bottleneck Models Obey Locality? N Raman, ME Zarlenga, J Heo, M Jamnik XAI in Action: Past, Present, and Future Applications, 2023 | 8 | 2023 |
| Do LLMs" know" internally when they follow instructions? J Heo, C Heinze-Deml, O Elachqar, S Ren, U Nallasamy, A Miller, ... arXiv preprint arXiv:2410.14516, 2024 | 1 | 2024 |
| Use perturbations when learning from explanations J Heo, V Piratla, M Wicker, A Weller Advances in Neural Information Processing Systems 36, 26872-26897, 2023 | 1 | 2023 |
| Estimation of concept explanations should be uncertainty aware V Piratla, J Heo, KM Collins, S Singh, A Weller arXiv preprint arXiv:2312.08063, 2023 | 1 | 2023 |
| Physics-Based Decoding Improves Magnetic Resonance Fingerprinting J Heo, P Song, W Liu, A Weller International Conference on Medical Image Computing and Computer-Assisted …, 2023 | 1 | 2023 |
| Leveraging Task Structures for Improved Identifiability in Neural Network Representations W Chen, J Horwood, J Heo, JM Hernández-Lobato arXiv preprint arXiv:2306.14861, 2023 | 1 | 2023 |
| Do LLMs estimate uncertainty well in instruction-following? J Heo, M Xiong, C Heinze-Deml, J Narain arXiv preprint arXiv:2410.14582, 2024 | | 2024 |
| On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective SA Siddiqui, Y Chen, J Heo, M Xia, A Weller arXiv preprint arXiv:2410.04541, 2024 | | 2024 |
| GeValDi: Generative Validation of Discriminative Models V Palaniappan, M Ashman, KM Collins, J Heo, A Weller, U Bhatt ICLR 2023 Workshop on Pitfalls of limited data and computation for …, 2023 | | 2023 |
| Robust Learning from Explanations. J Heo, V Piratla, M Wicker, A Weller CoRR, 2023 | | 2023 |
| Do LLMs internally``know''when they follow instructions? J Heo, C Heinze-Deml, O Elachqar, SY Ren, KHR Chan, U Nallasamy, ... 🍃 MINT: Foundation Model Interventions, 0 | | |
| LLMs on interactive feature collections with implicit look-ahead strategies J Heo, V Piratla, K Lee, H Joh, A Weller The First Workshop on System-2 Reasoning at Scale, NeurIPS'24, 0 | | |
| Does GPT-4 have good intuition about functions? SA Siddiqui, J Heo, Y Chen, A Weller | | |
| Hypothesis-and Structure-based prompting for medical and business diagnosis J Heo, K Lee, H Joh, U Bhatt, A Weller | | |
| Physics-based Decoding Improves Magnetic Resonance Fingerprinting (Supplementary Material) J Heo, P Song, W Liu, A Weller | | |
