Author

Xin Li

h-index 0 View on Semantic Scholar

We have 2 of 3 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.

Preprint Aug 2026

MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities

MMJailBench is introduced, a factorized benchmark that systematically varies and combines these factors under controlled configurations, enabling fine-grained comparison and factor-level attribution and a modular multimodal jailbreak evaluation suite with full and lightweight configurations, multiple judge options, and multidimensional metrics, enabling reproducible, scalable, and cost-efficient multimodal jailbreak auditing.

Tianshi Wang, Jing-Song Wang, Ya-Fei Huang et al. · 0 citations

Preprint Jul 2026

ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency

ActFovea is introduced, a plug-and-play safeguarding framework that detects and mitigates runtime failures of vision-language-action policies without retraining or modifying the underlying VLA policy.

Wen-Da Yu, Tianshi Wang, Fengling Li et al. · 0 citations