| SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing | Dec 10, 2022 | Mixture-of-Experts | —Unverified | 0 |
| Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning | Jul 1, 2024 | Continual LearningMixture-of-Experts | —Unverified | 0 |
| Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners | Jan 16, 2022 | Mixture-of-ExpertsMulti-Task Learning | —Unverified | 0 |
| Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners | Apr 16, 2022 | Mixture-of-ExpertsMulti-Task Learning | —Unverified | 0 |
| Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT | May 24, 2022 | Mixture-of-Experts | —Unverified | 0 |
| Sparse Mixture of Experts as Unified Competitive Learning | Mar 29, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Sparse Mixture-of-Experts for Non-Uniform Noise Reduction in MRI Images | Jan 24, 2025 | DenoisingDiagnostic | —Unverified | 0 |
| Cross-token Modeling with Conditional Computation | Sep 5, 2021 | Computational EfficiencyImage Classification | —Unverified | 0 |
| Sparse Upcycling: Inference Inefficient Finetuning | Nov 13, 2024 | Mixture-of-Experts | —Unverified | 0 |
| Sparse Video Representation Using Steered Mixture-of-Experts With Global Motion Compensation | Sep 13, 2022 | Mixture-of-ExpertsMotion Compensation | —Unverified | 0 |
