| On the Adaptation to Concept Drift for CTR Prediction | Apr 1, 2022 | Click-Through Rate PredictionIncremental Learning | —Unverified | 0 |
| Efficient Reflectance Capture with a Deep Gated Mixture-of-Experts | Mar 29, 2022 | DecoderMixture-of-Experts | —Unverified | 0 |
| Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution | Mar 27, 2022 | Image Super-ResolutionMixture-of-Experts | CodeCode Available | 1 |
| Build a Robust QA System with Transformer-based Mixture of Experts | Mar 20, 2022 | Data AugmentationMixture-of-Experts | CodeCode Available | 0 |
| Efficient Language Modeling with Sparse all-MLP | Mar 14, 2022 | AllCommon Sense Reasoning | —Unverified | 0 |
| SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization | Mar 13, 2022 | Abstractive Text SummarizationDocument Summarization | CodeCode Available | 1 |
| SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding | Mar 7, 2022 | Language ModellingMasked Language Modeling | —Unverified | 0 |
| Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models | Mar 2, 2022 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| Functional mixture-of-experts for classification | Feb 28, 2022 | ClassificationMixture-of-Experts | —Unverified | 0 |
| Mixture-of-Experts with Expert Choice Routing | Feb 18, 2022 | Mixture-of-Experts | —Unverified | 0 |
