| Link prediction in heterogeneous data via generalized coupled tensor factorization B Ermiş, E Acar, AT Cemgil Data Mining and Knowledge Discovery 29, 203-236, 2015 | 164 | 2015 |
| Linear Bandits with Stochastic Delayed Feedback C Vernade, A Carpentier, T Lattimore, G Zappella, B Ermis, M Brueckner ICML, 2020 | 76 | 2020 |
| Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning T Zadouri, A Üstün, A Ahmadian, B Ermiş, A Locatelli, S Hooker arXiv preprint arXiv:2309.05444, 2023 | 59 | 2023 |
| Memory efficient continual learning with transformers B Ermis, G Zappella, M Wistuba, A Rawal, C Archambeau Advances in Neural Information Processing Systems 35, 10629-10642, 2022 | 44 | 2022 |
| Link prediction via generalized coupled tensor factorisation B Ermiş, E Acar, AT Cemgil arXiv preprint arXiv:1208.6231, 2012 | 39 | 2012 |
| On the challenges of using black-box apis for toxicity evaluation in research L Pozzobon, B Ermis, P Lewis, S Hooker arXiv preprint arXiv:2304.12397, 2023 | 34 | 2023 |
| Optimal weight learning for coupled tensor factorization with mixed divergences U Şimşekli, B Ermiş, AT Cemgil, E Acar 21st European Signal Processing Conference (EUSIPCO 2013), 1-5, 2013 | 27 | 2013 |
| A Bayesian tensor factorization model via variational inference for link prediction B Ermis, AT Cemgil arXiv preprint arXiv:1409.8276, 2014 | 24 | 2014 |
| Learning to Rank in the Position Based Model with Bandit Feedback B Ermis, P Ernst, Y Stein, G Zappella CIKM, 2405-2412, 2020 | 21 | 2020 |
| Exact MCMC with Differentially Private Moves Y Sinan, B Ermis Statistics and Computing 28 (123), 1-17, 2019 | 21* | 2019 |
| PASHA: Efficient HPO and NAS with progressive resource allocation O Bohdal, L Balles, M Wistuba, B Ermis, C Archambeau, G Zappella arXiv preprint arXiv:2207.06940, 2022 | 19 | 2022 |
| Elo uncovered: Robustness and best practices in language model evaluation M Boubdir, E Kim, B Ermis, S Hooker, M Fadaee arXiv preprint arXiv:2311.17295, 2023 | 18 | 2023 |
| Learning mixed divergences in coupled matrix and tensor factorization models U Şimşekli, AT Cemgil, B Ermiş 2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015 | 17 | 2015 |
| Goodtriever: Adaptive toxicity mitigation with retrieval-augmented models L Pozzobon, B Ermis, P Lewis, S Hooker arXiv preprint arXiv:2310.07589, 2023 | 15 | 2023 |
| Investigating Continual Pretraining in Large Language Models: Insights and Implications Ç Yıldız, NK Ravichandran, P Punia, M Bethge, B Ermis arXiv preprint arXiv:2402.17400, 2024 | 13 | 2024 |
| Continual learning with transformers for image classification B Ermis, G Zappella, M Wistuba, A Rawal, C Archambeau Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 13 | 2022 |
| Data Sharing via Differentially Private Coupled Matrix Factorization B Ermiş, AT Cemgil ACM Transactions on Knowledge Discovery from Data (TKDD) 14 (3), 1-27, 2020 | 11 | 2020 |
| Exact MCMC with differentially private moves Revisiting the penalty algorithm in a data privacy framework S Yildirim, B Ermis Statistics and Computing 29 (5), 947-963, 2019 | 11 | 2019 |
| Contextual bandits under delayed feedback C Vernade, A Carpentier, G Zappella, B Ermis, M Brueckner arXiv preprint arXiv:1807.02089 361, 2018 | 11 | 2018 |
| Iterative Splits of Quadratic Bounds for Scalable Binary Tensor Factorization. B Ermis, G Bouchard UAI, 192-199, 2014 | 10 | 2014 |
Ali Taylan CemgilResearch Scientist, DeepMind UK在 google.com 的电子邮件经过验证
