Linfeng Du
4 papers · 2025–2026 · 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
Top co-authors
Research topics
Keywords
video generation
(1)
contextual bandit
(1)
content creation
(1)
generative ai
(1)
mechanistic interpretability
(1)
retrieval-augmented generation
(1)
linear probing
(1)
harmful content detection
(1)
generation quality
(1)
user profile
(1)
internal representation
(1)
model personalization
(1)
guard model
(1)
preference head
(1)
extended reality
(1)
immersive video
(1)
differential preference steering
(1)
preference contribution score
(1)
profile construction
(1)
Papers
LLM Safety From Within: Detecting Harmful Content with Internal Representations
ACL 2026
Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
ACL 2026
Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
ACL 2026
Generative AI for Immersive Video: Recent Advances and Future Opportunities
IJCAI 2025