Author

Jingyu (Jack) Zhang

Johns Hopkins University

h-index 11 Homepage View on Semantic Scholar

We have 2 of 22 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Minimally Invasive Steering of Language Models

Minimally Invasive Steering Vector Optimization (MISVO), which penalizes interventions using the local KL geometry of the induced token distribution, achieves the highest mean reward in six of seven model--task settings, with diversity and coherence scores close to those of Best-of-N.

Taha Entesari, Jingyu (Jack) Zhang, Daniel Khashabi et al. · 0 citations

Conference Open access Jul 2026

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models

JailMeter is proposed, an evidence-based evaluation framework designed to more faithfully measure jailbreak effectiveness and distill into a small language model, JailMeter\textsubscript{SLM}, which maintains comparable reliability with significantly reduced computational costs.

Qingjia Huang, Jingyu (Jack) Zhang, Jianguo Wu et al. · Annual Meeting of the Associ... · 2 citations · ⚡1