First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ha, Jiwoo, Baek, Jongwoo, So, Jinhyun
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.00455