Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

Bibliografski detalji

Izdano u:	arXiv.org (Nov 28, 2023), p. n/a
Glavni autor:	Leng, Sicong
Daljnji autori:	Zhang, Hang, Chen, Guanzheng, Li, Xin, Lu, Shijian, Miao, Chunyan, Bing, Lidong
Izdano:	Cornell University Library, arXiv.org
Teme:	Hallucinations Vision Training
Online pristup:	Citation/Abstract Full text outside of ProQuest
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!