SEMINAR

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

Jiwon Kim

2025.04.04

DPO

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

VENUE2025 ICLR

PAPER LINKOpen Access

PDFPDF 다운로드

이전 글Are Large Language Models Good Statisticans?

다음 글Robust Test-Time Adaptation in Dynamic Scenarios