LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Multilingual Text-Centric VQA
Open Access
- 12 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 8262-8273
Abstract
No abstract availableFunding Information
- Japan Science and Technology Agency (JST) and the Agency for Science, Technology and Research (A*STAR) (R24I6IR133)
This publication has 9 references indexed in Scilit:
- Contrastive Region Guidance: Improving Grounding in Vision-Language Models Without Training2024
- ViperGPT: Visual Inference via Python Execution for Reasoning2023
- Image as a Foreign Language: BEIT Pretraining for Vision and Vision-Language Tasks2023
- UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling2022
- Flamingo: A Visual Language Model for Few-Shot Learning2022
- Beyond OCR + VQA2021
- DocVQA: A Dataset for VQA on Document Images2021
- OCR-VQA: Visual Question Answering by Reading Text in Images2019
- Towards VQA Models That Can Read2019