{
  "docId": "019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "docSlug": "8757f1b44ef7f176",
  "documentTitle": "2024 Air Street Capital The State of AI Report 2024",
  "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": 57,
  "pageCount": 213,
  "prevPage": 56,
  "nextPage": 58,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "dense",
  "nDataPoints": 8,
  "notes": "The slide explains a technical process for brain-to-image reconstruction using a specific neural architecture.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "process_diagram",
    "comparison_table"
  ],
  "metadataConfidence": 0.95,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0856e1444fb9/57",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9#slide-57",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "MindEye2, is a generative model that maps fMRI activity to a rich CLIP space from which images of what the individual sees are reconstructed using a fine-tuned Stable Diffusion XL.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d12-d286148135f0",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.5,
        "x": 0.46,
        "y": 0.43
      },
      "kind": "diagram",
      "text": "MindEye2 architecture diagram showing fMRI input to image reconstruction",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "bdf0d1f2-324d-4644-84d0-2489cfee007e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.35,
        "x": 0.16,
        "y": 0.435
      },
      "kind": "image",
      "text": "Comparison grid of reconstructed images across different models",
      "attrs": null,
      "subkind": "infographic",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "02f49653-c35d-432e-97ec-e9a2d54c5e1f",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.96,
        "x": 0.02,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "MindEye2, is a generative model that maps fMRI activity to a rich CLIP space from which images of what the individual sees are reconstructed using a fine-tuned Stable Diffusion XL. The model is trained on the Natural Scenes Dataset, an fMRI dataset built from 8 subjects whose brain responses were captured for 30-40 hours as they looked at hundreds of rich naturalistic stimuli from the COCO dataset scanning sessions for 3 seconds each.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "073178db-c727-4460-8100-4e77c01f7089",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.18,
        "w": 0.25,
        "x": 0.47,
        "y": 0.68
      },
      "kind": "table",
      "text": "Subject training data table",
      "attrs": null,
      "subkind": "data",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "d3760671-9d27-4b57-a336-9a5c610ffbd7",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.6,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "Foundation models for the mind: reconstructing what you see",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "6d150bf7-a363-4a45-b7b2-00024a73089e",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "NxN matrix",
      "slug": "matrix-nxn",
      "agent": null,
      "layer": "slide",
      "matchId": "561db6ca-dbd0-42ba-9e3c-9c588125a159",
      "evidence": "Comparison grid of reconstructed images across different models",
      "confidence": 0.7
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 153,
      "from": 9,
      "beatId": "019dd95a-0682-776c-8e35-5f2398b8d1d0",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Exec summary + Research + Industry sections inventory the year",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 85,
      "from": 12,
      "beatId": "019dd95a-0682-776c-8e35-6d9d8ee06d0a",
      "arcName": "Voyage and Return",
      "arcSlug": "voyage-return",
      "beatName": "The Unknown",
      "beatSlug": "voyage-return-the-unknown",
      "evidence": "Research section explores frontier model uncharted territory",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Complication",
      "parentBeatSlug": "complication"
    }
  ],
  "loops": [
    {
      "to": 58,
      "from": 45,
      "name": "Zoom In",
      "slug": "06-zoom-in",
      "bestFor": "Technical deep-dives, case studies, detailed analysis",
      "matchId": "019dd95a-07fe-70ce-8d3e-3bc439910222",
      "evidence": "Nobels, AlphaFold3, AlphaProteo, ESM3, gene editors, materials, brain fMRI, speech-from-cortex case studies",
      "position": 7,
      "objective": "Zoom into AI for science domain by domain",
      "structure": "The Big Picture -> Key Area of Focus -> Specific Detail -> Implication",
      "confidence": 80,
      "description": "Start broad, then progressively focus on specific details that prove your point"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}