Although cross-modal hashing enables efficient large-scale retrieval by encoding multimodal data into compact binary representations, its fixed code length and binary nature impose a fundamental capacity constraint that hinders continual adaptation to growing data streams and emerging semantic concepts. Existing contin...
Wen-Hao Liu, Tian-Shi Wang, Feng-Ling Li et al.· IEEE Transactions on Pattern...· 0 citations
Multi-modal hashing converts high-dimensional features into compact binary codes while preserving semantic similarity, thereby achieving high performance with lower storage and computational costs. However, existing methods generally overly depend on discrete supervisory information, ignoring the ambiguity of labels an...
Chao-Qun Zheng, Rui-Fan Zuo, Feng-Ling Li et al.· ACM Transactions on Multimed...· 0 citations
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...
Tian-Shi Wang, Jing-Song Wang, Ya-Fei Huang et al.· 0 citations
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
UniTexture is introduced, a cross-task universal adversarial texture attack that uses a single textured 3D object to induce targeted deviations in VLA action predictions across multiple tasks and reveals shared cross-task vulnerabilities in multitask VLAs that can be systematically exploited through a single adversaria...
Yu Dai, Mingzhe Dai, Tianshi Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
