{
  "id": "2405.12399",
  "title": "Diffusion for World Modeling: Visual Details Matter in Atari",
  "authors": "Eloi Alonso, Adam Jelley, Vincent Micheli, Anssi Kanervisto, Amos Storkey, Tim Pearce, François Fleuret",
  "first_public": "2024-05-20",
  "first_public_source": "https://arxiv.org/abs/2405.12399",
  "venue": "NeurIPS 2024",
  "arxiv": "2405.12399",
  "paper_url": "https://arxiv.org/abs/2405.12399",
  "lens": [
    "interactive-worlds",
    "evaluation"
  ],
  "related_terms": [
    "DIAMOND",
    "diffusion world model",
    "neural game engine",
    "model-based reinforcement learning"
  ],
  "summary": "Introduces DIAMOND, an agent trained in a diffusion world model, and studies how preserving visual detail affects control.",
  "contribution": "Connects diffusion-based observation prediction with Atari policy learning and demonstrates an interactive Counter-Strike simulator.",
  "limitations": "Evaluated on games; NeuralOS adapts and evaluates it for desktop screen prediction.",
  "model_output": "Predicted visual observations; auxiliary reward and termination predictions support reinforcement learning.",
  "action_interface": "Actions of the modeled game environment.",
  "state_memory": "Visual dynamics condition on a finite history of observations and actions.",
  "relationship": "NeuralOS adapts DIAMOND to OS screen prediction as a baseline in Appendix A of its 2026 revision.",
  "relationship_source": "https://arxiv.org/html/2507.08800v2#A1",
  "author_names": [
    "Eloi Alonso",
    "Adam Jelley",
    "Vincent Micheli",
    "Anssi Kanervisto",
    "Amos Storkey",
    "Tim Pearce",
    "François Fleuret"
  ],
  "record_url": "https://neural-os.com/reading-list/papers/2405.12399/",
  "legacy_record_url": "https://neural-os.com/reading-list/papers/#paper-2405-12399",
  "citation_date": "2024-05-20",
  "json_url": "https://neural-os.com/reading-list/papers/2405.12399/record.json",
  "markdown_url": "https://neural-os.com/reading-list/papers/2405.12399/index.md",
  "bibtex_url": "https://neural-os.com/reading-list/papers/2405.12399/citation.bib",
  "csl_url": "https://neural-os.com/reading-list/papers/2405.12399/citation.csl.json",
  "method_comparisons": [
    {
      "title": "A game world model evaluated on desktop interactions",
      "text": "DIAMOND learns visual game dynamics with a diffusion model. NeuralOS adapts DIAMOND to OS screen prediction as a baseline in Appendix A of its 2026 revision. NeuralOS adds a recurrent state representation and spatial cursor conditioning for desktop interaction.",
      "source_ids": [
        "2405.12399",
        "2507.08800"
      ],
      "source_urls": [
        "https://arxiv.org/abs/2405.12399",
        "https://arxiv.org/html/2507.08800v2#A1"
      ],
      "source_labels": [
        "DIAMOND paper",
        "NeuralOS Appendix A"
      ],
      "topic_id": "interactive-worlds",
      "topic_label": "Interactive learned environments",
      "topic_url": "https://neural-os.com/reading-list/guides/games-to-computers/"
    }
  ]
}