Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Yejin, Hwang, Dongjun, Cha, Sungmin, Choe, Junsuk
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!