SOURCE-LINKED INTELLIGENCE

Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Mixed-format medical visual question answering (VQA) requires stable option selection and machine-readable free-text output. The two formats fail differently: multiple-choice predictions can change with option symbols or positions, while clinically plausible open answers can fail automated evaluation when serialization is malformed. We address both challenges with an answer-text memory, a permutation-stabilized vision--language expert, and a sparse candidate- expanding router. The cyclic schedule follows prior work; our contribution is to make expert top-2 a routable candidate alongside memory

Read original source ↗ Open in workspace

recordType

paper

region

Global