| Improved knowledge distillation via teacher assistant: Bridging the gap between student and teacher SI Mirzadeh, M Farajtabar, A Li, H Ghasemzadeh AAAI Conference on Artificial Intelligence (AAAI), 2019 | 1681* | 2019 |
| Gsm-Symbolic: Understanding the limitations of mathematical reasoning in large language models I Mirzadeh, K Alizadeh, H Shahrokhi, O Tuzel, S Bengio, M Farajtabar International Conference on Learning Representations (ICLR 2025), 2024 | 680 | 2024 |
| The illusion of thinking: Understanding the strengths and limitations of reasoning models via the lens of problem complexity P Shojaee, I Mirzadeh, K Alizadeh, M Horton, S Bengio, M Farajtabar arXiv preprint arXiv:2506.06941, 2025 | 337* | 2025 |
| Understanding the role of training regimes in continual learning SI Mirzadeh, M Farajtabar, R Pascanu, H Ghasemzadeh Advances in Neural Information Processing Systems (NeurIPS), 2020 | 309 | 2020 |
| Llm in a flash: Efficient large language model inference with limited memory K Alizadeh, SI Mirzadeh, D Belenko, S Khatamifard, M Cho, ... Annual Meeting of the Association for Computational Linguistics (ACL) 1 …, 2024 | 218 | 2024 |
| Linear mode connectivity in multitask and continual learning SI Mirzadeh, M Farajtabar, D Gorur, R Pascanu, H Ghasemzadeh International Conference on Learning Representations (ICLR), 2021 | 187 | 2021 |
| Relu strikes back: Exploiting activation sparsity in large language models I Mirzadeh, K Alizadeh, S Mehta, CC Del Mundo, O Tuzel, G Samei, ... International Conference on Learning Representations (ICLR), 2023 | 139 | 2023 |
| Openelm: An efficient language model family with open training and inference framework S Mehta, MH Sekhavat, Q Cao, M Horton, Y Jin, C Sun, I Mirzadeh, ... arXiv preprint arXiv:2404.14619, 2024 | 129* | 2024 |
| Wide neural networks forget less catastrophically SI Mirzadeh, A Chaudhry, D Yin, H Hu, R Pascanu, D Gorur, M Farajtabar International Conference on Machine Learning (ICML), 15699-15717, 2022 | 98 | 2022 |
| Architecture matters in continual learning SI Mirzadeh, A Chaudhry, D Yin, T Nguyen, R Pascanu, D Gorur, ... arXiv preprint arXiv:2202.00275, 2022 | 96 | 2022 |
| Dropout as an Implicit Gating Mechanism For Continual Learning SI Mirzadeh, M Farajtabar, H Ghasemzadeh The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR …, 2020 | 64 | 2020 |
| Continual learning beyond a single model T Doan, SI Mirzadeh, M Farajtabar Conference on Lifelong Learning Agents, 961-991, 2023 | 21 | 2023 |
| Use of machine learning to predict medication adherence in individuals at risk for atherosclerotic cardiovascular disease SI Mirzadeh, A Arefeen, J Ardo, R Fallahzadeh, B Minor, JA Lee, ... Smart Health 26, 100328, 2022 | 17 | 2022 |
| TransNet: Minimally supervised deep transfer learning for dynamic adaptation of wearable systems SA Rokni, M Nourollahi, P Alinia, I Mirzadeh, M Pedram, H Ghasemzadeh ACM Transactions on Design Automation of Electronic Systems (TODAES) 26 (1 …, 2020 | 17 | 2020 |
| Scaling smart: Accelerating large language model pre-training with small model initialization M Samragh, I Mirzadeh, KA Vahid, F Faghri, M Cho, M Nabi, D Naik, ... arXiv preprint arXiv:2409.12903, 2024 | 16 | 2024 |
| Designing deep neural networks robust to sensor failure in mobile health environments A Mamun, SI Mirzadeh, H Ghasemzadeh 2022 44th Annual International Conference of the IEEE Engineering in …, 2022 | 16 | 2022 |
| ActiLabel: A Combinatorial Transfer Learning Framework for Activity Recognition P Alinia, SI Mirzadeh, H Ghasemzadeh arXiv preprint arXiv:2003.07415, 2020 | 15 | 2020 |
| TiC-LM: A web-scale benchmark for time-continual LLM pretraining J Li, M Armandpour, SI Mirzadeh, S Mehta, V Shankar, R Vemulapalli, ... Proceedings of the 63rd Annual Meeting of the Association for Computational …, 2025 | 10* | 2025 |
| Inter-beat interval estimation with tiramisu model: A novel approach with reduced error A Arefeen, A Akbari, SI Mirzadeh, R Jafari, BA Shirazi, H Ghasemzadeh ACM Transactions on Computing for Healthcare 5 (1), 1-19, 2024 | 10 | 2024 |
| Efficient continual learning ensembles in neural network subspaces T Doan, SI Mirzadeh, J Pineau, M Farajtabar arXiv preprint arXiv:2202.09826, 2022 | 10 | 2022 |
Mehrdad FarajtabarResearch Scientist at AppleVerified email at apple.com
