Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xue, Haotian, Ge, Yunhao, Zeng, Yu, Li, Zhaoshuo, Liu, Ming-Yu, Chen, Yongxin, Fan, Jiaojiao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.25794