SOURCE-LINKED INTELLIGENCE
Seeing is not Enough: Vision-Language Models Perceive Evidence but Fail to Act
Vision-language models (VLMs) perform strongly on visual question answering benchmarks, yet often make decisions that contradict visual evidence they have already identified correctly. We distinguish perceptual failure, where relevant evidence is not recognized, from process failure, where recognized evidence fails to constrain the final decision. We introduce VPAC-Bench, a benchmark spanning nine real-image process families, with each image annotated by its current activity stage and nearby stage transition. We also propose State-Relevance-Target (SRT), a family of structured process-prior in
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-18T21:13:03.000Z
First collected: 2026-09-23T12:01:45.602Z. This is not the publication date.