Maddies at GroundLM 2026 Shared Tasks: Answer-Preserving Visual Re-grounding for Multi-View Driving VQA
Abstract
AbstractGoldenViewVQA asks a multimodal model to answer a driving-scene question and identify the synchronized camera view that supports its answer. Our first system, QAVEL, used option blind routing, local image inspection, pairwise view selection, and a final verifier. Tests with GPT-5.6 Luna and Terra showed a recurring problem: extra stages often replaced correct direct predictions, and higher reasoning effort did not repair the cascade. We therefore built Joint Answer-preserving Visual Re-grounding (JAVR) around a GPT-5.6 Sol joint prediction. JAVR freezes the answer, aligns the queried actor or condition across all six views, revisits disputed cameras with target-specific crops, and changes only the view when a restricted comparator certifies an exact, direct, and complete evidence source. On the 55-item development set, JAVR produced a descriptive one item increase over its Sol anchor, from 46 to 47 jointly correct predictions, without changing any answer. Our official 59-item test submission reached 79.66% joint accuracy, 81.36% view accuracy, and 94.92% answer accuracy