| Compacter: Efficient low-rank hypercomplex adapter layers R Karimi Mahabadi, J Henderson, S Ruder Advances in neural information processing systems 34, 1022-1035, 2021 | 662 | 2021 |
| Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks RK Mahabadi, S Ruder, M Dehghani, J Henderson arXiv preprint arXiv:2106.04489, 2021 | 403 | 2021 |
| End-to-end bias mitigation by modelling biases in corpora RK Mahabadi, Y Belinkov, J Henderson Proceedings of the 58th annual meeting of the association for computational …, 2020 | 215 | 2020 |
| Learning-based compressive MRI B Gözcü, RK Mahabadi, YH Li, E Ilıcak, T Cukur, J Scarlett, V Cevher IEEE transactions on medical imaging 37 (6), 1394-1406, 2018 | 165 | 2018 |
| Perfect: Prompt-free and efficient few-shot learning with language models RK Mahabadi, L Zettlemoyer, J Henderson, M Saeidi, L Mathias, ... arXiv preprint arXiv:2204.01172, 2022 | 86 | 2022 |
| Variational information bottleneck for effective low-resource fine-tuning RK Mahabadi, Y Belinkov, J Henderson arXiv preprint arXiv:2106.05469, 2021 | 78 | 2021 |
| Llama-nemotron: Efficient reasoning models A Bercovich, I Levy, I Golan, M Dabbah, R El-Yaniv, O Puny, I Galil, ... arXiv preprint arXiv:2505.00949, 2025 | 58 | 2025 |
| ParsiNLU: A Suite of Language Understanding Challenges for Persian D Khashabi, A Cohan, S Shakeri, P Hosseini, P Pezeshkpour, M Alikhani, ... Transactions of the Association for Computational Linguistics 9, 1147-1162, 2021 | 58 | 2021 |
| Tess: Text-to-text self-conditioned simplex diffusion RK Mahabadi, H Ivison, J Tae, J Henderson, I Beltagy, ME Peters, ... arXiv preprint arXiv:2305.08379, 2023 | 51 | 2023 |
| Nemotron-h: A family of accurate and efficient hybrid mamba-transformer models A Blakeman, A Basant, A Khattar, A Renduchintala, A Bercovich, A Ficek, ... arXiv preprint arXiv:2504.03624, 2025 | 31 | 2025 |
| Segment based 3D object shape priors R Karimi Mahabadi, C Hane, M Pollefeys Proceedings of the IEEE conference on computer vision and pattern …, 2015 | 24 | 2015 |
| A non-Euclidean gradient descent framework for non-convex matrix factorization YP Hsieh, YC Kao, RK Mahabadi, A Yurtsever, A Kyrillidis, V Cevher IEEE Transactions on Signal Processing 66 (22), 5917-5926, 2018 | 19 | 2018 |
| Simple but effective techniques to reduce biases RK Mahabadi, J Henderson arXiv preprint arXiv:1909.06321 9, 2019 | 18 | 2019 |
| Nvidia nemotron nano 2: An accurate and efficient hybrid mamba-transformer reasoning model A Basant, A Khairnar, A Paithankar, A Khattar, A Renduchintala, A Malte, ... arXiv preprint arXiv:2508.14444, 2025 | 16 | 2025 |
| Scalable sparse covariance estimation via self-concordance A Kyrillidis, RK Mahabadi, QT Dinh, V Cevher Proceedings of the AAAI Conference on Artificial Intelligence 28 (1), 2014 | 16 | 2014 |
| Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks R Karimi Mahabadi, S Ruder, M Dehghani, J Henderson arXiv e-prints, arXiv: 2106.04489, 2021 | 8 | 2021 |
| Parsinlu: a suite of language understanding challenges for persian D Khashabi, A Cohan, S Shakeri, P Hosseini, P Pezeshkpour, M Alikhani, ... arXiv preprint arXiv:2012.06154, 2020 | 7 | 2020 |
| A learning-based framework for quantized compressed sensing RK Mahabadi, J Lin, V Cevher IEEE Signal Processing Letters 26 (6), 883-887, 2019 | 7 | 2019 |
| Nemotron-cc-math: A 133 billion-token-scale high quality math pretraining dataset RK Mahabadi, S Satheesh, S Prabhumoye, M Patwary, M Shoeybi, ... arXiv preprint arXiv:2508.15096, 2025 | 5 | 2025 |
| Real-time dct learning-based reconstruction of neural signals RK Mahabadi, C Aprile, V Cevher 2018 26th European Signal Processing Conference (EUSIPCO), 1925-1929, 2018 | 5 | 2018 |
James HendersonSenior Researcher, Idiap Research InstituteVerified email at idiap.ch
