SEMINAR

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Jiwon Kim

2025.06.09

LVLM

DPO

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

VENUE2025 CVPR

PAPER LINKCVF Open Access

PDFPDF 다운로드

이전 글MPMQA: Multimodal Question Answering on Product Manuals

다음 글Adjustment and Alignment for Unbiased Open Set Domain Adaptation