Skip to content
conftrace_

mixture of expert

787 papers

MOE

Papers

Table-based Fact Verification with Self-labeled Keypoint Alignment COLING 2022 Taming Sparsely Activated Transformer with Stochastic Experts ICLR 2022 TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training NeurIPS 2022 Unified Scaling Laws for Routed Language Models ICML 2022 Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs NeurIPS 2022 Using Deep Mixture-of-Experts to Detect Word Meaning Shift for TempoWiC EMNLP 2022 Who Says Elephants Can’t Run: Bringing Large Scale MoE Models into Cloud Scale Production EMNLP 2022 Adaptive Text to Speech for Spontaneous Style Interspeech 2021 AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding ACL 2021 A Mixture-of-Experts Model for Antonym-Synonym Discrimination ACL 2021 Answering Product-Questions by Utilizing Questions from Other Contextually Similar Products NAACL 2021 Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference EMNLP 2021 Contextual policy transfer in reinforcement learning domains via deep mixtures-of-experts UAI 2021 Cross-Domain Label-Adaptive Stance Detection EMNLP 2021 Cross-Topic Rumor Detection using Topic-Mixtures EACL 2021 DeepME: Deep Mixture Experts for Large-scale Image Classification IJCAI 2021 DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning NeurIPS 2021 Facebook AI’s WMT21 News Translation Task Submission EMNLP 2021 Few-Shot and Continual Learning With Attentive Independent Mechanisms ICCV 2021 GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context Input NAACL 2021 Generalizable Person Re-Identification With Relevance-Aware Mixture of Experts CVPR 2021 GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding ICLR 2021 Hash Layers For Large Sparse Models NeurIPS 2021 Improving Robustness Against Common Corruptions With Frequency Biased Models ICCV 2021 Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks CVPR 2021