◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Takuya Ito

5 papers hereh-index 318 citations10 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author3
  • middle author2

Across the 5 of 5 papers where every author was matched, so the position is known.

fields
  • cs.LG3
  • cs.AI2
same name
  • Takuya Ito — 3 papers, h 17
  • Takuya Ito — 1 paper
  • Takuya Ito — 1 paper
  • Takuya Ito — 1 paper, h 3

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20242026
collaborators
Showing cs.LGShow all

3 papers · 1 filter

cs.LG2026

Universal Transformers for Circuit Computations: Perfect Length Generalization in Tiny Transformers

Takuya Ito, Ruchir Puri, Murray Campbell +1

Learning generalizable algorithmic computations remains a challenge for neural networks, as reflected in persistent failures on compositional and length generalization benchmarks.…

cs.LG2025

Transformer Circuits Can Realize Clustering Algorithms

Kenneth L. Clarkson, Lior Horesh, Takuya Ito +2

Although transformers are most commonly optimized as statistical sequence models, it is unclear to what extent they can implement and learn exact algorithmic computations. Here, we…

cs.LG2024

Learning interpretable positional encodings in transformers depends on initialization

Takuya Ito, Luca Cocchi, Tim Klinger +3

In transformers, the positional encoding (PE) provides essential information that distinguishes the position and order amongst tokens in a sequence. Most prior investigations of PE…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.