Yanzhou Pan
4 papers · 2025–2025 · 3 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 · Bronze
🗺️
Taxonomy Completionist
(12)
Top co-authors
Research topics
Keywords
large language model
(3)
training data
(2)
responsible ai
(1)
data valuation
(1)
llm copyright
(1)
online-offline optimization
(1)
associative learning
(1)
data privacy
(1)
influence function
(1)
retrieval-augmented generation
(1)
internal state analysis
(1)
neural network classifier
(1)
context processing
(1)
copyright leakage
(1)
inappropriate content
(1)
linearized future influence kernel
(1)
risk management
(1)
copyrighted data leakage
(1)
model safety
(1)
Papers
ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation
NAACL 2025
ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
EMNLP 2025
Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks
ICML 2025
Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context
EMNLP 2025