AWhat changed
Simplified sparse mixture-of-experts routing for transformers with one expert selected per token and reported faster large-scale pre-training and trillion-parameter models.
Scientific scope
Simplified sparse mixture-of-experts routing for transformers with one expert selected per token and reported faster large-scale pre-training and trillion-parameter models. Scope limitation: This is the 2021 first preprint, later published in JMLR 2022; it does not invent MoE or imply that a trillion parameters are active per token.
Evidence
The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. This is the 2021 first preprint, later published in JMLR 2022; it does not invent MoE or imply that a trillion parameters are active per token.
Contributors
- The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured.
- Fedus and colleagues: Switch Transformer sparse expert routing — original paper
- Fedus and colleagues: Switch Transformer sparse expert routing — company research source
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction