{
  "id": 3166028,
  "title": "What's the Catch? Evaluating Temporal Consistency in Vision-Language Models",
  "url": "https://urgent.news/2026/08/24/whats-the-catch-evaluating-temporal-consistency-in-vision-language",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-24T16:40:49.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.23474v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Vision-language models (VLMs) achieve strong performance on video and image-sequence benchmarks, yet it remains unclear whether they capture temporal structure. To study this question, we formulate temporal grounding as an anomaly detection problem, providing a simple and controlled evaluation that directly tests sensitivity to temporal consistency. We introduce TimeCatch, where temporal…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}