Jian Kim
2 papers
· 2025–2025
· 2 conferences
· across top CS/AI conferences
Achievements
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
ACL (1)
EMNLP (1)
Top co-authors
Keywords
adversarial attack
(1)
vision language model
(1)
jailbreak attack
(1)
llm safety
(1)
large language model
(1)
embodied decision making
(1)
physical safety
(1)
command refusal
(1)
plan safety test
(1)
language model security
(1)
plan safety
(1)
unsafe command detection
(1)
computer-use agent
(1)
safety bypass
(1)