| P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts | Oct 14, 2021 | Mixture-of-ExpertsNatural Language Queries | —Unverified | 0 |
| Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Model | Oct 13, 2021 | Mixture-of-ExpertsQuestion Generation | —Unverified | 0 |
| HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models | Oct 8, 2021 | Abstractive Text SummarizationDecoder | CodeCode Available | 1 |
| Taming Sparsely Activated Transformer with Stochastic Experts | Oct 8, 2021 | Machine TranslationMixture-of-Experts | CodeCode Available | 1 |
| Sparse MoEs meet Efficient Ensembles | Oct 7, 2021 | Few-Shot LearningMixture-of-Experts | CodeCode Available | 1 |
| Continual Learning Using Task Conditional Neural Networks | Sep 29, 2021 | Continual LearningMixture-of-Experts | —Unverified | 0 |
| Full-Precision Free Binary Graph Neural Networks | Sep 29, 2021 | Graph Neural NetworkMixture-of-Experts | —Unverified | 0 |
| MECATS: Mixture-of-Experts for Probabilistic Forecasts of Aggregated Time Series | Sep 29, 2021 | Mixture-of-ExpertsTime Series | —Unverified | 0 |
| HydraSum - Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models | Sep 29, 2021 | Abstractive Text SummarizationDecoder | —Unverified | 0 |
| Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference | Sep 24, 2021 | Mixture-of-ExpertsSentence | —Unverified | 0 |
