N. Naik

Look Where It Counts: A Free, Label-Free Visual Evidence Signal for Fine-Grained Vision-Language Reasoning

Multimodal large language models (MLLMs) fail at fine-grained visual questions less because they cannot reason than because they never see the evidence: high-resolution images are downsampled before encoding, so the model answers from linguistic priors. The standard remedies are expensive: annotated answers (SFT), hand...