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

Yanzhao Wu

2 indexed papers

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

Publications per year

2
26

Top categories

AI×2Crypto×1

Frequent co-authors

Abhijith Babu1×
Ramneet Kaur1×
Nathaniel D. Bastian1×
Olivera Kotevska1×
Susmit Jha1×
Sumit Kumar Jha1×

Research Timeline

2026
GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models

The paper proposes GUARD-SLM, a token activation-based defense mechanism, to enhance the robustness of Small Language Models (SLMs) against various jailbreak attacks by analyzing and filtering malicious patterns in the model's internal representation space.

Closed-Loop Neural Activation Control in Vision-Language-Action Models

The paper proposes CTRL-STEER, a closed-loop framework that adaptively adjusts intervention strength to stabilize concept regulation and improve task success in Vision-Language-Action models without retraining the base model.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 29, 2026

Closed-Loop Neural Activation Control in Vision-Language-Action Models

Abhijith Babu, Ramneet Kaur, Nathaniel D. Bastian, Olivera Kotevska +4 more

The paper proposes CTRL-STEER, a closed-loop framework that adaptively adjusts intervention strength to stabilize concept regulation and improve task success in Vision-Language-Action models without r…

View →
cs.CRcs.AIRecentMar 28, 2026

GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models

Md Jueal Mia, Joaquin Molto, Yanzhao Wu, M. Hadi Amini

The paper proposes GUARD-SLM, a token activation-based defense mechanism, to enhance the robustness of Small Language Models (SLMs) against various jailbreak attacks by analyzing and filtering malicio…

View →