Sibei Yang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1
Frequent co-authors
Research Timeline
2026
EVA: Editing for Versatile Alignment against Jailbreaks
The paper proposes EVA, a novel framework that uses direct model editing to surgically correct specific neurons responsible for jailbreaking vulnerabilities in LLMs and VLMs, achieving robust safety alignment without performance degradation.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIRecentMay 14, 2026
EVA: Editing for Versatile Alignment against Jailbreaks
Yi Wang, Hongye Qiu, Yue Xu, Sibei Yang +3 more
The paper proposes EVA, a novel framework that uses direct model editing to surgically correct specific neurons responsible for jailbreaking vulnerabilities in LLMs and VLMs, achieving robust safety a…
View →