| Sparse is Enough in Scaling Transformers S Jaszczur, A Chowdhery, A Mohiuddin, L Kaiser, W Gajewski, ... Advances in Neural Information Processing Systems 34, 9895-9907, 2021 | 94 | 2021 |
| MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts M Pióro, K Ciebiera, K Król, J Ludziejewski, S Jaszczur arXiv preprint arXiv:2401.04081, 2024 | 57 | 2024 |
| Scaling Laws for Fine-Grained Mixture of Experts J Krajewski, J Ludziejewski, K Adamczewski, M Pióro, M Krutul, ... arXiv preprint arXiv:2402.07871, 2024 | 35* | 2024 |
| Neural heuristics for SAT solving S Jaszczur, M Łuszczyk, H Michalewski arXiv preprint arXiv:2005.13406, 2020 | 14 | 2020 |
| Use of domain knowledge and feature engineering in helping AI to play Hearthstone P Przybyszewski, S Dziewiątkowski, S Jaszczur, M Śmiech, M Szczuka 2017 Federated Conference on Computer Science and Information Systems …, 2017 | 6 | 2017 |
| Structured packing in llm training improves long context utilization K Staniszewski, S Tworkowski, S Jaszczur, Y Zhao, H Michalewski, ... arXiv preprint arXiv:2312.17296, 2023 | 5 | 2023 |
| Mixture of Tokens: Continuous MoE through Cross-Example Aggregation S Antoniak, M Krutul, M Pióro, J Krajewski, J Ludziejewski, K Ciebiera, ... Advances in Neural Information Processing Systems 37, 103873-103896, 2025 | 4* | 2025 |
| Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient J Ludziejewski, M Pióro, J Krajewski, M Stefaniak, M Krutul, J Małaśnicki, ... arXiv preprint arXiv:2502.05172, 2025 | | 2025 |
| Sparse attention neural networks A Chowdhery, A Mohiuddin, H Michalewski, JM Kanerva, LM Kaiser, ... US Patent App. 17/666,400, 2022 | | 2022 |
| Different Rates for Different Weights: Decoupled Relative Learning Rate Schedules J Ludziejewski, J Małaśnicki, M Pióro, M Krutul, K Ciebiera, M Stefaniak, ... | | |
Marek CyganUniversity of Warsaw在 mimuw.edu.pl 的电子邮件经过验证