Zhuochen Yang — accepted AI-conference papers

2026

CoSPED: Consistent Soft Prompt Targeted Data Extraction and Defense

Zhuochen Yang, Kar Wai Fok, Vrizlynn L. L. Thing

AAAI 2026technical

Large language models have gained widespread attention recently, but their potential security vulnerabilities, especially privacy leakage, are also becoming apparent. To test and evaluate for data extraction risks in LLMs, we propose CoSPED, short for Consistent Soft Prompt Targeted Data Extraction

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

TinyVPR: Distilling Correct and Confusing Knowledge for Lightweight Visual Place Recognition

Zhuochen Yang, Runheng Zuo, Xu Yang, Runjiang Dou, Zhe Wang, Liyuan Liu +1

ICRA 2026poster

Visual Place Recognition (VPR) is a key technology in autonomous driving, robotics, and augmented reality, requiring efficient and robust localization in large-scale environments. However, most existing methods rely on heavy deep models that are computationally expensive and difficult to deploy on e…

Cited by 0 Scholar ↗