Ryosuke Takahashi
5 papers · 2022–2026 · 4 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
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(10)
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
language model
(2)
representation learning
(2)
temporal reasoning
(1)
masked language model
(1)
document-level translation
(1)
token classification
(1)
hidden state
(1)
side effect
(1)
sentence-level translation
(1)
idiom detection
(1)
large language model
(1)
knowledge triple
(1)
translation reranking
(1)
minimum bayesian risk
(1)
rank-one update
(1)
uncontextualized embedding
(1)
japanese calendar
(1)
calendar arithmetic
(1)
knowledge editing
(1)
Papers
Suppressing Final Layer Hidden State Jumps in Transformer Pretraining
EACL 2026
Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki
IJCNLP 2025
Understanding the Side Effects of Rank-One Knowledge Editing
EMNLP 2025
Document-level Translation with LLM Reranking: Team-J at WMT 2024 General Translation Task
EMNLP 2024
Leveraging Three Types of Embeddings from Masked Language Models in Idiom Token Classification
NAACL 2022