Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Rex Ying

Rex Ying

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×1AI×1Crypto×1NLP×1

Frequent co-authors

Yangtian Zhang1×
Zhe Wang1×
Arthur Gretton1×
David van Dijk1×
Michalis K. Titsias1×
Jiaxin Shi1×

Research Timeline

2026
SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking

The paper proposes SRTJ, a Self-Evolving Rule-Driven Training-Free Jailbreak framework that systematically discovers and refines attack strategies using rule composition and feedback to achieve robust and generalizable jailbreaking against modern LLMs.

Variational Learning for Insertion-based Generation

The paper introduces the Insertion Process (IP), a novel stochastic generative model that learns variable-length, non-monotonic sequence generation by explicitly modeling the insertion order of tokens.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIRecentJun 1, 2026

Variational Learning for Insertion-based Generation

Yangtian Zhang, Zhe Wang, Arthur Gretton, Rex Ying +3 more

The paper introduces the Insertion Process (IP), a novel stochastic generative model that learns variable-length, non-monotonic sequence generation by explicitly modeling the insertion order of tokens…

View →
cs.CRcs.CLRecentMay 1, 2026

SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking

Jindong Li, Ying Liu, Yali Fu, Jinjing Zhu +3 more

The paper proposes SRTJ, a Self-Evolving Rule-Driven Training-Free Jailbreak framework that systematically discovers and refines attack strategies using rule composition and feedback to achieve robust…

View →