4 papers
Beyond Decision Boundaries: Relational Geometry Attacks on Contrastive Embedding Manifolds
Fei Zhao, Peiyuan Zhang, Xi Li +2
Contrastive learning and Siamese embedding models have become the foundation of modern verification systems, where decisions are governed not by discrete classification boundaries,…
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
Xi Li, Shu Zhao, Xiaohan Zou +6
Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this arc…
MarkMatch: Same-Hand Stuffing Detection
Fei Zhao, Runlin Zhang, Chengcui Zhang +1
We present MarkMatch, a retrieval system for detecting whether two paper ballot marks were filled by the same hand. Unlike the previous SOTA method BubbleSig, which used binary cla…
Mitigating Image Captioning Hallucinations in Vision-Language Models
Fei Zhao, Chengcui Zhang, Runlin Zhang +2
Hallucinations in vision-language models (VLMs) hinder reliability and real-world applicability, usually stemming from distribution shifts between pretraining data and test samples…