VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

Open Webpage

Tianyu Zhang, Suyuchen Wang, Lu Li, Ge Zhang, Perouz Taslakian, Sai Rajeswar, Jie Fu, Bang Liu, Yoshua Bengio

Published: 01 Jan 2025, Last Modified: 21 May 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0