Masato Uchida
4 papers · 2020–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
Top co-authors
Research topics
Keywords
consistency
(2)
attention head
(1)
jailbreak attack
(1)
predictive model
(1)
internal representation
(1)
pairwise classification
(1)
activation pattern
(1)
classification risk
(1)
large language model
(1)
complementary label
(1)
ordinary label
(1)
one-versus-all classification
(1)
weak feature
(1)
estimation model
(1)
finite-sample conditions
(1)
continuous weak features
(1)
feature estimation models
(1)
iterative learning methods
(1)
label prediction models
(1)
generalization error
(1)
Papers
A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features
ICML 2025
Jailbreak Defense in LLM via Attention Head Analysis and Selective Intervention
ACML 2025
Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing Data
ICML 2025
Bridging Ordinary-Label Learning and Complementary-Label Learning
ACML 2020