LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bi, Jinhe, Wang, Yujun, Chen, Haokun, Xiao, Xun, Hecker, Artur, Tresp, Volker, Ma, Yunpu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!