BWhat changed
Introduced fine-grained expert segmentation and shared experts for sparse language models, reporting improved expert specialization and efficiency.
Scientific scope
Introduced fine-grained expert segmentation and shared experts for sparse language models, reporting improved expert specialization and efficiency. Scope limitation: The paper studies specified DeepSeekMoE models and comparisons; it is distinct from later DeepSeek-V2/R1 and not the invention of MoE.
Evidence
The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. The paper studies specified DeepSeekMoE models and comparisons; it is distinct from later DeepSeek-V2/R1 and not the invention of MoE.
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.
- Dai and colleagues: DeepSeekMoE expert specialization — original paper
- Dai and colleagues: DeepSeekMoE expert specialization — official company 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