| Improved knowledge distillation via teacher assistant: Bridging the gap between student and teacher SI Mirzadeh, M Farajtabar, A Li, H Ghasemzadeh AAAI 2020, 2020 | 1370* | 2020 |
| Dyrep: Learning representations over dynamic graphs R Trivedi, M Farajtabar, P Biswal, H Zha ICLR 2019, 2019 | 773* | 2019 |
| Orthogonal Gradient Descent for Continual Learning M Farajtabar, N Azizan, A Mott, A Li AISTATS 2020, 2020 | 404 | 2020 |
| Coevolve: A joint point process model for information diffusion and network co-evolution M Farajtabar, Y Wang, MG Rodriguez, S Li, H Zha, L Song JMLR 2016, 2015 | 319 | 2015 |
| More robust doubly robust off-policy evaluation M Farajtabar, Y Chow, M Ghavamzadeh ICML 2018, 2018 | 302 | 2018 |
| Learning granger causality for hawkes processes H Xu, M Farajtabar, H Zha ICML 2016, 2016 | 281 | 2016 |
| Self-distillation amplifies regularization in hilbert space H Mobahi, M Farajtabar, PL Bartlett NeurIPS 2020, 2020 | 274 | 2020 |
| Understanding the Role of Training Regimes in Continual Learning S Iman Mirzadeh, M Farajtabar, R Pascanu, H Ghasemzadeh NeurIPS 2020, 2020 | 241* | 2020 |
| Fake news mitigation via point process based intervention M Farajtabar, J Yang, X Ye, H Xu, R Trivedi, E Khalil, S Li, L Song, H Zha ICML 2017, 2017 | 220 | 2017 |
| Wasserstein learning of deep generative point process models S Xiao, M Farajtabar, X Ye, J Yan, L Song, H Zha NeurIPS 2017, 2017 | 213 | 2017 |
| Dirichlet-hawkes processes with applications to clustering continuous-time document streams N Du, M Farajtabar, A Ahmed, AJ Smola, L Song KDD 2015, 2015 | 212 | 2015 |
| Shaping social activity by incentivizing users M Farajtabar, N Du, MG Rodriguez, I Valera, H Zha, L Song NeurIPS 2014, 2014 | 181 | 2014 |
| Adapting auxiliary losses using gradient similarity Y Du, WM Czarnecki, SM Jayakumar, M Farajtabar, R Pascanu, ... arXiv preprint arXiv:1812.02224, 2018 | 176 | 2018 |
| Learning time series associated event sequences with recurrent point process networks S Xiao, J Yan, M Farajtabar, L Song, X Yang, H Zha IEEE transactions on neural networks and learning systems 30 (10), 3124-3136, 2019 | 169* | 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 arXiv preprint arXiv:2410.05229, 2024 | 159 | 2024 |
| Linear mode connectivity in multitask and continual learning SI Mirzadeh, M Farajtabar, D Gorur, R Pascanu, H Ghasemzadeh ICLR 2021, 2021 | 140 | 2021 |
| Back to the past: Source identification in diffusion networks from partially observed cascades M Farajtabar, MG Rodriguez, M Zamani, N Du, H Zha, L Song AISTATS 2015, 2015 | 105 | 2015 |
| Llm in a flash: Efficient large language model inference with limited memory K Alizadeh, SI Mirzadeh, D Belenko, S Khatamifard, M Cho, ... Proceedings of the 62nd Annual Meeting of the Association for Computational …, 2024 | 96 | 2024 |
| Sam-clip: Merging vision foundation models towards semantic and spatial understanding H Wang, PKA Vasu, F Faghri, R Vemulapalli, M Farajtabar, S Mehta, ... CVPR workshop 2024, 2023 | 81 | 2023 |
| Learning to Incentivize Other Learning Agents J Yang, A Li, M Farajtabar, P Sunehag, E Hughes, H Zha NeurIPS 2020, 2020 | 81 | 2020 |
Hongyuan ZhaThe Chinese University of Hong Kong, Shenzhen在 cuhk.edu.cn 的电子邮件经过验证