Sho Takase
Affiliations
- ○ SB Intuitions — Former Research Scientist (Jul 2024 – Jul 2025; now at CyberAgent)Formerly: LINE Corp (Senior Researcher); Tokyo Institute of Technology; Tohoku University (PhD)
Related Outputs
| 2026-03-17 | Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning | paper |
| 2025-02-05 | Scaling Laws for Upcycling Mixture-of-Experts Language Models | paper |
| 2024-06-24 | Large Vocabulary Size Improves Large Language Models | paper |
| 2023-12-28 | Spike No More: Stabilizing the Pre-training of Large Language Models | paper |