{
  "id": 19301749,
  "title": "WanderBench: Can World Models Explore Dynamic Worlds from Video?",
  "url": "https://urgent.news/2026/11/09/wanderbench-can-world-models-explore-dynamic-worlds-from-video",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-09T15:23:53.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2611.12557v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Video world models conditioned on an input video make it possible to explore real, recorded dynamic scenes, enabling re-shooting of footage, free-viewpoint replay, and real-to-sim environments for embodied agents. Such uses require the generated rollout to stay faithful to the recorded world, yet existing benchmarks start from a single image or a text prompt, and video-conditioned generation is…",
  "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."
}