Hiromu Takahashi
3 papers · 2022–2026 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(14)
Top co-authors
Research topics
Artificial Intelligence
(2)
Machine Learning
(2)
Natural Language Processing
(2)
Core AI
(2)
Learning Types · Machine Learning
(2)
Resources & Methods
(2)
Data Science & Analytics
(1)
Deep Learning
(1)
Application Areas
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Methods
(1)
Optimization & Theory
(1)
Keywords
large language model
(2)
multilingual nlp
(1)
temporal analysis
(1)
language model
(1)
privacy auditing
(1)
semantic shift
(1)
continual pre-training
(1)
pre-trained language model
(1)
performance degradation
(1)
word embedding
(1)
membership inference attack
(1)
japanese language model
(1)
industry-specific corpus
(1)
language model privacy
(1)
memorization quantification
(1)
time series analysis
(1)
non-english language model
(1)
Papers
Fast-MIA: Efficient and Scalable Membership Inference for LLMs
ACL 2026
Quantifying Memorization in Continual Pre-training with Japanese General or Industry-Specific Corpora
ACL 2025
Semantic Shift Stability: Efficient Way to Detect Performance Degradation of Word Embeddings and Pre-trained Language Models
AACL 2022