ResearchTrend.AI
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time

Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time

Yifan Lan
Yuanpu Cao
Weitong Zhang
Lu Lin
Jinghui Chen
    AAML
ArXiv (abs)PDFHTMLHuggingFace (4 upvotes)Github (1★)

Papers citing "Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time"

0 / 0 papers shown

No papers found