AI RESEARCH
LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
arXiv CS.CV
•
ArXi:2509.10026v4 Announce Type: replace As large vision language models (VLMs) advance, their capabilities in multilingual visual question answering (mVQA) have significantly improved. Chain-of-thought (CoT) reasoning has been proven to enhance interpretability and complex reasoning. However, most existing approaches rely primarily on textual CoT and provide limited for multilingual multimodal reasoning, cons