Sho Takase
Scholar

Sho Takase

Google Scholar ID: 2dvzFDYAAAAJ
CyberAgent
Natural Language ProcessingMachine LearningNeural Networks
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
984
 
H-index
17
 
i10-index
21
 
Publications
20
 
Co-authors
3
list available
Contact
CVOpen ↗GitHubOpen ↗
Publications
6 items
Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
2026
Cited
0
Natural Fingerprints of Large Language Models
2025
Cited
0
Efficient Construction of Model Family through Progressive Training Using Model Expansion
2025
Cited
0
Scaling Laws for Upcycling Mixture-of-Experts Language Models
2025
Cited
0
Large Vocabulary Size Improves Large Language Models
arXiv.org · 2024
Cited
3
Spike No More: Stabilizing the Pre-training of Large Language Models
arXiv.org · 2023
Cited
15
Resume (English only)
Co-authors
3 total
Jun Suzuki
Jun Suzuki
Tohoku University
Shun Kiyono
Shun Kiyono
SB Intuitions
Kentaro Inui
Kentaro Inui
MBZUAI, Tohoku University, RIKEN