From Routing Signals to Selective Review: Visual regrounding in MoE VLMs
MoE routing signals detect missing visual targets in Qwen and Gemma VLMs and trigger selective review.
The paper uses Mixture-of-Experts routing probabilities to detect target-absence grounding failures in vision-language models before generation. Linear detectors on Qwen3-VL-30B-A3B-Instruct and Gemma-4-26B-A4B-it reach ROC-AUCs of 0.9988 and 0.9956 on GQA-Inpaint, retaining 0.8095 and 0.7781 on OBER. A routing-gated review prompt raises end-to-end accuracy by up to 22.25% for Qwen and 13.42% for Gemma without modifying weights.
55