Wanlong Yu
3 papers · 2025–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(5)
🌍
Conference Polyglot
(2)
Conferences
ACL (2)
AAAI (1)
Top co-authors
Keywords
reinforcement learning
(1)
domain adaptation
(1)
text understanding
(1)
ai safety
(1)
harmful content
(1)
graph random walk
(1)
adversarial defense
(1)
jailbreak attack
(1)
risk assessment
(1)
domain shift
(1)
representation steering
(1)
teacher-student model
(1)
llm safety
(1)
adversarial game
(1)
harmfulness defense
(1)
content filtering
(1)
continual test-time adaptation
(1)
large language model safety
(1)
Papers
WALKSAFE: Risk-aware Graph Random Walk with Bi-GRPO for LLM Safety
AAAI 2026
CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher
ACL 2026
AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models
ACL 2025