Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
机构 * UC Berkeley(加州大学伯克利分校) ; POSTECH
Comments Accepted to NeurIPS 2025; Project Page: https://reverse-vlm.github.io
作者
Computer Vision
机构 * UC Berkeley(加州大学伯克利分校) ; POSTECH
Comments Accepted to NeurIPS 2025; Project Page: https://reverse-vlm.github.io