Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning
Pengcheng Pan, Xinfang Zhang
Multimodal large language models (MLLMs) can miss fine details in a full image that they recognize in a closer view. Recovering this evidence requires deciding where to look and ho…
cs.CV2026
Head-Aware Visual Cropping: Enhancing Fine-Grained VQA with Attention-Guided Subimage
Junfei Xie, Peng Pan, Xulong Zhang
Multimodal Large Language Models (MLLMs) show strong performance in Visual Question Answering (VQA) but remain limited in fine-grained reasoning due to low-resolution inputs and no…