SOURCE-LINKED INTELLIGENCE

Region-Level Policy Optimization for Fine-grained MLLM Perception

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Fine-grained visual perception in MLLMs is commonly improved by raising the resolution, but the added visual tokens inflate vision-encoding and language-model prefilling costs. We show that the two operations underlying fine-grained perception, localizing the region of interest (RoI) and recognizing its content, have different resolution requirements. In a controlled diagnostic, localization tolerates roughly 3 to 4 times stronger token compression than recognition, which motivates localizing from a coarse view and concentrating resolution on the selected evidence. Decoding coordinates with th

Read original source ↗ Open in workspace

recordType

paper

region

Global