Takase, Sho

4 publications

ICLR 2026 Pre-Training LLM Without Learning Rate Decay Enhances Supervised Fine-Tuning Kazuki Yano, Shun Kiyono, Sosuke Kobayashi, Sho Takase, Jun Suzuki

ICML 2025 Scaling Laws for Upcycling Mixture-of-Experts Language Models Seng Pei Liew, Takuya Kato, Sho Takase

NeurIPS 2020 All Word Embeddings from One Embedding Sho Takase, Sosuke Kobayashi

AAAI 2019 Character N-Gram Embeddings to Improve RNN Language Models Sho Takase, Jun Suzuki, Masaaki Nagata