LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Multilingual Text-Centric VQA.

Jing Huang, Zhiya Tan, Shutao Gong, Fanwei Zeng, Joey Tianyi Zhou, Changtao Miao, Huazhe Tan, Weibin Yao, Jianshu Li

Browse the full WWW paper archive.