| Quantifying attention flow in transformers S Abnar, W Zuidema 58th Annual Meeting of the Association for Computational Linguistics, 2020 | 985 | 2020 |
| Long range arena: A benchmark for efficient transformers Y Tay, M Dehghani, S Abnar, Y Shen, D Bahri, P Pham, J Rao, L Yang, ... arXiv preprint arXiv:2011.04006, 2020 | 731 | 2020 |
| Scale efficiently: Insights from pre-training and fine-tuning transformers Y Tay, M Dehghani, J Rao, W Fedus, S Abnar, HW Chung, S Narang, ... arXiv preprint arXiv:2109.10686, 2021 | 147 | 2021 |
| Gaudi: A neural architect for immersive 3d scene generation MA Bautista, P Guo, S Abnar, W Talbott, A Toshev, Z Chen, L Dinh, S Zhai, ... Advances in Neural Information Processing Systems 35, 25102-25116, 2022 | 133 | 2022 |
| Exploring the limits of large scale pre-training S Abnar, M Dehghani, B Neyshabur, H Sedghi arXiv preprint arXiv:2110.02095, 2021 | 133 | 2021 |
| Scaling laws vs model architectures: How does inductive bias influence scaling? Y Tay, M Dehghani, S Abnar, HW Chung, W Fedus, J Rao, S Narang, ... arXiv preprint arXiv:2207.10551, 2022 | 90 | 2022 |
| Blackbox meets blackbox: Representational Similarity and Stability Analysis of Neural Language Models and Brains S Abnar, L Beinborn, R Choenni, W Zuidema 2nd BlackBoxNLP workshop, 2019 | 86 | 2019 |
| Experiential, distributional and dependency-based word embeddings have complementary roles in decoding brain activity S Abnar, R Ahmed, M Mijnheer, W Zuidema Cognitive Modeling and Computational Linguistics (CMCL) 2018, 2018 | 72 | 2018 |
| Transferring inductive biases through knowledge distillation S Abnar, M Dehghani, W Zuidema arXiv preprint arXiv:2006.00555, 2020 | 69 | 2020 |
| An evolutionary algorithm for forming mixed groups of learners in web based collaborative learning environments S Abnar, F Orooji, F Taghiyareh 2012 IEEE international conference on technology enhanced education (ICTEE), 1-6, 2012 | 65 | 2012 |
| Diffusion probabilistic fields P Zhuang, S Abnar, J Gu, A Schwing, JM Susskind, MA Bautista The Eleventh International Conference on Learning Representations, 2023 | 26 | 2023 |
| Robust Evaluation of Language-Brain Encoding Experiments L Beinborn, S Abnar, R Choenni CICLing, 2019 | 24 | 2019 |
| Gradual domain adaptation in the wild: When intermediate distributions are absent S Abnar, R Berg, G Ghiasi, M Dehghani, N Kalchbrenner, H Sedghi arXiv preprint arXiv:2106.06080, 2021 | 22 | 2021 |
| Expanded n-grams for semantic text alignment S Abnar, M Dehghani, H Zamani, A Shakery Cappellato et al.[35], 2014 | 20 | 2014 |
| A comparison of architectures and pretraining methods for contextualized multilingual word embeddings N van der Heijden, S Abnar, E Shutova Proceedings of the AAAI conference on artificial intelligence 34 (05), 9090-9097, 2020 | 19 | 2020 |
| Authorship identification using dynamic selection of features from probabilistic feature set H Zamani, HN Esfahani, P Babaie, S Abnar, M Dehghani, A Shakery Information Access Evaluation. Multilinguality, Multimodality, and …, 2014 | 19 | 2014 |
| The healing power of poison: Helpful non-relevant documents in feedback M Dehghani, S Abnar, J Kamps Proceedings of the 25th ACM International on Conference on Information and …, 2016 | 5 | 2016 |
| Meta Text Aligner: Text Alignment Based on Predicted Plagiarism Relation S Abnar, M Dehghani, A Shakery Conference of the CLEF Association, CLEF’15 Toulouse, France, September 8–11 …, 2015 | 5 | 2015 |
| Parameters vs flops: Scaling laws for optimal sparsity for mixture-of-experts language models S Abnar, H Shah, D Busbridge, AME Ali, J Susskind, V Thilak arXiv preprint arXiv:2501.12370, 2025 | 3 | 2025 |
| Adaptivity and modularity for efficient generalization over task complexity S Abnar, O Saremi, L Dinh, S Wilson, MA Bautista, C Huang, V Thilak, ... arXiv preprint arXiv:2310.08866, 2023 | 3 | 2023 |
Mostafa DehghaniResearch Scientist, Google DeepMindOverená e-mailová adresa na: google.com