SOURCE-LINKED INTELLIGENCE

VisLens: Single-Pass Interpretable Visual Search for Multimodal LLMs

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Multimodal large language models (MLLMs) struggle with fine-grained Visual Search, the task of locating small or rare objects in high-resolution images. Existing remedies fall into two families: (1) Training-free methods based on attention or confidence scores are accurate but slow, since they require multiple MLLM queries per example. (2) Reinforcement Learning (RL) trained tool-use models are faster at inference but opaque, since their tool calls remain uncontrollable and hard to interpret. To overcome this, we propose \emph{VisLens} (Visual Focus via Logit Lens), a Visual Search method buil

Read original source ↗ Open in workspace

recordType

paper

region

Global