{
  "id": 1209,
  "url": "https://arxiv.org/abs/2606.10620v1",
  "title": "Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency",
  "summary": "Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly understood. Practical workflows such as storyboarding, step-by-step illustration, reference-guided editing, and video previsualization require models to preserve identities, objects, spatial relations, and causal order across multiple visual states. Existing evaluations largely measure single-image correctness, compositional alignment, or video qualit",
  "authors": "Xinrui Wu, Lichen Huang",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-09T09:17:55.000Z",
  "fetched_at": "2026-07-14T14:15:07.843Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1209",
  "original_url": "https://arxiv.org/abs/2606.10620v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}