https://duongtruongbinh.github.io/https://duongtruongbinh.github.io/cv/https://duongtruongbinh.github.io/projects/https://duongtruongbinh.github.io/projects/robust-vqa-counterfactual/https://duongtruongbinh.github.io/publications/https://duongtruongbinh.github.io/publications/dam-qa/https://duongtruongbinh.github.io/publications/viinfographicvqa/https://duongtruongbinh.github.io/publications/vivqa-x/https://duongtruongbinh.github.io/tags/https://duongtruongbinh.github.io/tags/contrastive-learning/https://duongtruongbinh.github.io/tags/counterfactual-learning/https://duongtruongbinh.github.io/tags/dataset-construction/https://duongtruongbinh.github.io/tags/document-intelligence/https://duongtruongbinh.github.io/tags/multi-image-reasoning/https://duongtruongbinh.github.io/tags/multimodal-learning/https://duongtruongbinh.github.io/tags/robust-ai/https://duongtruongbinh.github.io/tags/text-rich-images/https://duongtruongbinh.github.io/tags/vietnamese-ai/https://duongtruongbinh.github.io/tags/vision-language-models/https://duongtruongbinh.github.io/tags/visual-question-answering/