ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Sho Takase

Sho Takase

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 5:10 AM AMS

4

papers

55

total citations

papers (4)

Spike No More: Stabilizing the Pre-training of Large Language Models

All Word Embeddings from One Embedding

NEURIPS 2020arXiv

Scaling Laws for Upcycling Mixture-of-Experts Language Models

Efficient Construction of Model Family through Progressive Training Using Model Expansion