{
  "docId": "019dd923-5e88-73ef-bd5d-01cf0d8a8fbc",
  "docSlug": "cc8183ec02431b7a",
  "documentTitle": "2022 Air Street Capital The State of AI Report 2022",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 30,
  "pageCount": 114,
  "prevPage": 29,
  "nextPage": 31,
  "slideType": "industry_trends",
  "function": "summarize",
  "density": "dense",
  "nDataPoints": 0,
  "notes": "Includes a list of academic paper titles as a visual reference for the trend.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "screenshot"
  ],
  "metadataConfidence": 0.95,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc/30",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc#slide-30",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Today, they are now the undisputable SOTA for text-to-image generation, and are diffusing (pun intended) into text-to-video, text generation, audio, molecular design and more.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c4-7719-a216-e08f32f141c8",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.5,
        "w": 0.2,
        "x": 0.78,
        "y": 0.38
      },
      "kind": "image",
      "text": "List of academic papers on diffusion models",
      "attrs": null,
      "subkind": "infographic",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "97bc0af7-3142-4131-861c-d9449260d77c",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.06,
        "w": 0.3,
        "x": 0.03,
        "y": 0.93
      },
      "kind": "image",
      "text": "Logos of OpenAI, Stanford, Google, UBC, UvA, EPFL",
      "attrs": null,
      "subkind": "logo-grid",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "a9ffbfba-472d-44a7-b90c-3ca3bf2c7e73",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.55,
        "w": 0.75,
        "x": 0.03,
        "y": 0.38
      },
      "kind": "list",
      "text": "Diffusion models (DMs) learn to reverse successive noise additions to images by modeling the inverse distribution (generating denoised images from noisy ones) at each step as a Gaussian whose mean and covariance are parametrized as a neural network. DMs generate new images from random noise.\nSequential denoising makes them slow, but new techniques (like denoising in a lower-dimensional space) allow them to be faster at inference time and to generate higher-quality samples (classifier-free guidance – trading off diversity for fidelity).\nSOTA text-to-image models like DALL-E 2, Imagen and Stable Diffusion are based on DMs. They're also used in controllable text generation (generating text with a pre-defined structure or semantic context), model-based reinforcement learning, video generation and even molecular generation.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "c84d9202-d497-4567-b8cd-4f3af228f315",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.75,
        "x": 0.03,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "When we covered diffusion models in the 2021 Report (slide 36), they were overtaking GANs in image generation on a few benchmarks. Today, they are now the indisputable SOTA for text-to-image generation, and are diffusing (pun intended) into text-to-video, text generation, audio, molecular design and more.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "32efee70-a784-40b5-b1e5-0af7892fbe34",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.94,
        "x": 0.03,
        "y": 0.14
      },
      "kind": "title",
      "text": "Diffusion models take over text-to-image generation and expand into other modalities",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "b700cc0c-9e90-454c-900f-186107c62900",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-1055-74e0-a955-ed0561eb9c60",
      "evidence": "Title 'Diffusion models take over text-to-image generation' states verdict.",
      "confidence": 80
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 80,
      "from": 5,
      "beatId": "019dd95a-0682-776c-8e35-2557e3799e96",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions, exec summary, Research and Industry sections inventory the state of AI.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 93,
      "from": 11,
      "beatId": "019dd95a-0682-776c-8e35-35abf646aa8b",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Research, Industry, Politics sections accumulate signals.",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 33,
      "from": 30,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3d-a4c263216829",
      "evidence": "Diffusion takeover, DALL-E 2/Imagen/Parti race, Stability/Midjourney emergence, text-to-video kickoff.",
      "position": 4,
      "objective": "Document the diffusion / text-to-image explosion across labs",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 82,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}