Tokio Kajitsuka

According to our database, Tokio Kajitsuka authored at least 3 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective.

Tokio Kajitsuka, Ukyo Honda, Sho Takase

CoRR, April, 2026

2025

On the Optimal Memorization Capacity of Transformers.

Tokio Kajitsuka, Issei Sato

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?

Tokio Kajitsuka, Issei Sato

Proceedings of the Twelfth International Conference on Learning Representations, 2024