New Study Traces How Visual Distraction Disrupts Vision-Language Model Reasoning
A new arXiv paper examines how vision-language models struggle to ignore irrelevant visual information, tracing the effect of visual distraction through text tokens during reasoning.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-13 05:00 · arXiv cs.CV
Back to the Question: Tracing Visual Distraction Through Text Tokens