Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering
Researchers have developed a new decoding method called Wasserstein Equilibrium Decoding to improve the reliability of medical visual question answering (VQA) systems, particularly for smaller models. This approach uses a semantically aware Wasserstein stopping criterion to achieve consensus among similar answers, avoiding issues with lexical ordering. The method has shown consistent improvements on medical VQA datasets like VQA-RAD and PathVQA, enhancing accuracy and inference efficiency for models such as Qwen3-VL-2B and Gemma-3-4B. AI
IMPACT Enhances the accuracy and efficiency of medical VQA systems, enabling more reliable clinical deployment of smaller AI models.