{
  "id": "2402.15391",
  "title": "Genie: Generative Interactive Environments",
  "authors": "Jake Bruce, Michael Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, Yusuf Aytar, Sarah Bechtle, Feryal Behbahani, Stephanie Chan, Nicolas Heess, Lucy Gonzalez, Simon Osindero, Sherjil Ozair, Scott Reed, Jingwei Zhang, Konrad Zolna, Jeff Clune, Nando de Freitas, Satinder Singh, Tim Rocktäschel",
  "first_public": "2024-02-23",
  "first_public_source": "https://arxiv.org/abs/2402.15391",
  "venue": "arXiv",
  "arxiv": "2402.15391",
  "paper_url": "https://arxiv.org/abs/2402.15391",
  "lens": [
    "interactive-worlds"
  ],
  "related_terms": [
    "Genie",
    "generative interactive environments",
    "latent actions",
    "foundation world model"
  ],
  "summary": "Learns controllable visual environments from videos without ground-truth action labels, using a learned latent action space.",
  "contribution": "Combines video tokenization, a dynamics model, and latent-action learning so users can interact with worlds initialized from images.",
  "limitations": "Controls use learned latent actions inferred from video.",
  "model_output": "Action-conditioned future video frames.",
  "action_interface": "Discrete latent actions inferred during training rather than recorded physical input events.",
  "state_memory": "A spatiotemporal dynamics model conditions predictions on previous visual tokens and actions.",
  "relationship": "Cited in NeuralOS's related work. Genie learns its action space from video; NeuralOS takes mouse and keyboard events as inputs.",
  "relationship_source": "https://arxiv.org/html/2507.08800v2",
  "author_names": [
    "Jake Bruce",
    "Michael Dennis",
    "Ashley Edwards",
    "Jack Parker-Holder",
    "Yuge Shi",
    "Edward Hughes",
    "Matthew Lai",
    "Aditi Mavalankar",
    "Richie Steigerwald",
    "Chris Apps",
    "Yusuf Aytar",
    "Sarah Bechtle",
    "Feryal Behbahani",
    "Stephanie Chan",
    "Nicolas Heess",
    "Lucy Gonzalez",
    "Simon Osindero",
    "Sherjil Ozair",
    "Scott Reed",
    "Jingwei Zhang",
    "Konrad Zolna",
    "Jeff Clune",
    "Nando de Freitas",
    "Satinder Singh",
    "Tim Rocktäschel"
  ],
  "record_url": "https://neural-os.com/reading-list/papers/2402.15391/",
  "legacy_record_url": "https://neural-os.com/reading-list/papers/#paper-2402-15391",
  "citation_date": "2024-02-23",
  "json_url": "https://neural-os.com/reading-list/papers/2402.15391/record.json",
  "markdown_url": "https://neural-os.com/reading-list/papers/2402.15391/index.md",
  "bibtex_url": "https://neural-os.com/reading-list/papers/2402.15391/citation.bib",
  "csl_url": "https://neural-os.com/reading-list/papers/2402.15391/citation.csl.json"
}