conftrace
_
Papers
Trends
Conferences
Explore
More
Authors
Topics
Keywords
Papers
Trends
Conferences
Explore
Authors
Topics
Keywords
Achievements
← Authors
Copy link
Xiaohao Luo
1 papers · 2026–2026 · 1 conference
· across top CS/AI conferences
Conferences
ACL (1)
Top co-authors
Ying Wei (1)
Rui Zhao (1)
Keywords
jailbreak attack
(1)
activation steering
(1)
large language model
(1)
feed forward network
(1)
harmful query detection
(1)
Papers
Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring
ACL 2026