Taku Ito

Bio

Takuya Ito, Ph.D., is a Research Scientist in the Mathematics and Optimization Group under Algorithms & Applications. His research encompasses machine learning, compositionality, and quantum error correction, with a focus on their theoretical foundations.

Personal webpage: ito-takuya.github.com

Google scholar: https://scholar.google.com/citations?user=Ym08_RMAAAAJ&hl=en

Publications

Transformer Circuits Can Realize Clustering Algorithms
- - Kenneth Clarkson
  - Lior Horesh
  - et al.
- 2026
- ICML 2026
Conference paper
Task Representational Dynamics for Compositional Generalization During Context-Dependent Cognitive Tasks
- - Lakshman Chakravarthula
  - Michael Cole
  - et al.
- 2026
- ICLR 2026
Workshop paper
Specifying exact circuit algorithms in universal transformers
- - Taku Ito
  - Ruchir Puri
  - et al.
- 2025
- NeurIPS 2025
Workshop paper
Learning interpretable positional encodings in transformers depends on initialization
- - Taku Ito
  - Luca Cocchi
  - et al.
- 2025
- ICML 2025
Workshop paper
Geometry of naturalistic object representations in recurrent neural network models of working memory
- - Xiaoxuan Lei
  - Taku Ito
  - et al.
- 2024
- NeurIPS 2024
Conference paper
On the generalization capacity of neural networks during generic multimodal reasoning
- - Taku Ito
  - Soham Dan
  - et al.
- 2024
- ICLR 2024
Conference paper

Blog posts

Understanding AI through the algorithms they compute
Technical note
Takuya Ito
18 Aug 2025
- AI

Top collaborators

PR

Parikshit Ram

Parikshit Ram

Research Staff Member

MC

Murray Campbell

Murray Campbell

Distinguished Research Scientist, Mathematics of Computation

JK

James Kozloski

James Kozloski

Principal Research Scientist

TK

Tim Klinger

Tim Klinger

Senior Research Scientist, Math and Algorithms