AI models show human-like attention in safety-critical scenes

A new study published on arXiv compares the visual attention of large vision-language models (VLMs) with human gaze patterns in safety-critical environments. Researchers collected eye-tracking data from participants viewing risky scenes and then prompted models like GPT-4o, Gemini Pro, Gemini Flash, and Claude to predict human attention. The findings indicate that VLMs can identify areas of interest that broadly align with human visual focus, suggesting their potential as scalable tools for approximating human attentional patterns without explicit eye-tracking training. AI

IMPACT Suggests VLMs can approximate human attentional patterns, potentially aiding in safety analysis and design.

RANK_REASON The cluster contains an academic paper detailing a comparative study of AI model attention versus human gaze. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• Claude
• Gemini Flash
• Gemini Pro
• GPT-4o
• OpenAI Vision Application Programming Interface
• Pupil Invisible

• paper
• safety
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →