Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Janjua, Muhammad Kamran, Silva, Hugo, Niu, Di, Rashidi, Bahador
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.12896