◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Soichiro Kumano

The University of Tokyo

3 papers hereh-index 332 citations12 works total

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

author position
  • first author3

Across the 3 of 3 papers where every author was matched, so the position is known.

fields
  • cs.LG3
affiliations
  • The University of Tokyo
HomepageORCID 0000-0002-3461-3943

identity via Semantic Scholar / OpenAlex

collaborators

3 papers

cs.LG2026

Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners

Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

Adversarial training is one of the most effective defenses against adversarial attacks, but it incurs a high computational cost. In this study, we present the first theoretical ana…

cs.LG2025

Adversarial Training from Mean Field Perspective

Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

Although adversarial training is known to be effective against adversarial examples, training dynamics are not well understood. In this study, we present the first theoretical anal…

cs.LG2025

Wide Two-Layer Networks can Learn from Adversarial Perturbations

Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

Adversarial examples have raised several open questions, such as why they can deceive classifiers and transfer between different models. A prevailing hypothesis to explain these ph…

◍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.