{
  "id": 10602348,
  "title": "Video, Ergo Genero: Unifying Video Tasks via Spatiotemporal Analogy",
  "url": "https://urgent.news/2026/09/27/video-ergo-genero-unifying-video-tasks-via-spatiotemporal-analogy",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-27T21:26:58.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.33935v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Adapting video models to new tasks typically requires dedicated data curation and fine-tuning. While visual analogy provides a training-free alternative by specifying tasks in-context, it remains restricted to the image domain. To explore whether analogy-based methods can unify diverse video tasks and generalize to out-of-distribution scenarios, we introduce ViGeo, a framework that extends visual…",
  "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."
}