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

@inproceedings{huang-2026-lavcot, author = {Jing Huang and Zhiya Tan and Shutao Gong and Fanwei Zeng and Joey Tianyi Zhou and Changtao Miao and Huazhe Tan and Weibin Yao and Jianshu Li}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Multilingual Text-Centric VQA}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {8262--8273}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792793}, doi = {https://doi.org/10.1145/3774904.3792793} }