SOURCE-LINKED INTELLIGENCE

Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved from external sources. However, MLLMs may overlook relevant evidence in both modalities, attending weakly to the textual sentences or visual regions needed for the correct answer. Recent efforts address this by highlighting retrieved text and marking visual regions before generation, but apply a fixed, one-shot policy that cannot adapt to three sources of variation: whether highlighting is necessary, how much evidence different examples require,

Read original source ↗ Open in workspace

recordType

paper

region

Global