{
  "type": "excalidraw",
  "version": 2,
  "source": "https://excalidraw.com",
  "elements": [
    {
      "id": "title",
      "type": "text",
      "x": 55,
      "y": 45,
      "width": 620,
      "height": 38,
      "angle": 0,
      "strokeColor": "#172033",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 1,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a0",
      "roundness": null,
      "seed": 101,
      "version": 1,
      "versionNonce": 1001,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "fontSize": 30,
      "fontFamily": 1,
      "text": "通用 Vision–Language–Action 论文框图",
      "rawText": "通用 Vision–Language–Action 论文框图",
      "textAlign": "left",
      "verticalAlign": "top",
      "containerId": null,
      "originalText": "通用 Vision–Language–Action 论文框图",
      "autoResize": true,
      "lineHeight": 1.25
    },
    {
      "id": "input-box",
      "type": "rectangle",
      "x": 55,
      "y": 155,
      "width": 190,
      "height": 190,
      "angle": 0,
      "strokeColor": "#334155",
      "backgroundColor": "#e0f2fe",
      "fillStyle": "solid",
      "strokeWidth": 2,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a1",
      "roundness": {"type": 3},
      "seed": 102,
      "version": 1,
      "versionNonce": 1002,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false
    },
    {
      "id": "input-text",
      "type": "text",
      "x": 80,
      "y": 190,
      "width": 140,
      "height": 105,
      "angle": 0,
      "strokeColor": "#172033",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 1,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a2",
      "roundness": null,
      "seed": 103,
      "version": 1,
      "versionNonce": 1003,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "fontSize": 22,
      "fontFamily": 1,
      "text": "多模态输入\n\n视觉观测\n语言指令",
      "rawText": "多模态输入\n\n视觉观测\n语言指令",
      "textAlign": "center",
      "verticalAlign": "middle",
      "containerId": null,
      "originalText": "多模态输入\n\n视觉观测\n语言指令",
      "autoResize": true,
      "lineHeight": 1.25
    },
    {
      "id": "encoder-box",
      "type": "rectangle",
      "x": 305,
      "y": 185,
      "width": 180,
      "height": 130,
      "angle": 0,
      "strokeColor": "#334155",
      "backgroundColor": "#ede9fe",
      "fillStyle": "solid",
      "strokeWidth": 2,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a3",
      "roundness": {"type": 3},
      "seed": 104,
      "version": 1,
      "versionNonce": 1004,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false
    },
    {
      "id": "encoder-text",
      "type": "text",
      "x": 325,
      "y": 215,
      "width": 140,
      "height": 70,
      "angle": 0,
      "strokeColor": "#172033",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 1,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a4",
      "roundness": null,
      "seed": 105,
      "version": 1,
      "versionNonce": 1005,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "fontSize": 20,
      "fontFamily": 1,
      "text": "视觉编码器\nViT / Video\n时空 Token",
      "rawText": "视觉编码器\nViT / Video\n时空 Token",
      "textAlign": "center",
      "verticalAlign": "middle",
      "containerId": null,
      "originalText": "视觉编码器\nViT / Video\n时空 Token",
      "autoResize": true,
      "lineHeight": 1.25
    },
    {
      "id": "fusion-box",
      "type": "rectangle",
      "x": 545,
      "y": 165,
      "width": 200,
      "height": 170,
      "angle": 0,
      "strokeColor": "#334155",
      "backgroundColor": "#fef3c7",
      "fillStyle": "solid",
      "strokeWidth": 2,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a5",
      "roundness": {"type": 3},
      "seed": 106,
      "version": 1,
      "versionNonce": 1006,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false
    },
    {
      "id": "fusion-text",
      "type": "text",
      "x": 565,
      "y": 200,
      "width": 160,
      "height": 100,
      "angle": 0,
      "strokeColor": "#172033",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 1,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a6",
      "roundness": null,
      "seed": 107,
      "version": 1,
      "versionNonce": 1007,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "fontSize": 20,
      "fontFamily": 1,
      "text": "多模态融合\n\nCross-Attention\nLanguage Grounding",
      "rawText": "多模态融合\n\nCross-Attention\nLanguage Grounding",
      "textAlign": "center",
      "verticalAlign": "middle",
      "containerId": null,
      "originalText": "多模态融合\n\nCross-Attention\nLanguage Grounding",
      "autoResize": true,
      "lineHeight": 1.25
    },
    {
      "id": "decoder-box",
      "type": "rectangle",
      "x": 805,
      "y": 185,
      "width": 170,
      "height": 130,
      "angle": 0,
      "strokeColor": "#334155",
      "backgroundColor": "#dcfce7",
      "fillStyle": "solid",
      "strokeWidth": 2,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a7",
      "roundness": {"type": 3},
      "seed": 108,
      "version": 1,
      "versionNonce": 1008,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false
    },
    {
      "id": "decoder-text",
      "type": "text",
      "x": 825,
      "y": 215,
      "width": 130,
      "height": 70,
      "angle": 0,
      "strokeColor": "#172033",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 1,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a8",
      "roundness": null,
      "seed": 109,
      "version": 1,
      "versionNonce": 1009,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "fontSize": 20,
      "fontFamily": 1,
      "text": "动作解码器\nDiffusion / AR\nAction Chunk",
      "rawText": "动作解码器\nDiffusion / AR\nAction Chunk",
      "textAlign": "center",
      "verticalAlign": "middle",
      "containerId": null,
      "originalText": "动作解码器\nDiffusion / AR\nAction Chunk",
      "autoResize": true,
      "lineHeight": 1.25
    },
    {
      "id": "robot-box",
      "type": "rectangle",
      "x": 1035,
      "y": 155,
      "width": 120,
      "height": 190,
      "angle": 0,
      "strokeColor": "#334155",
      "backgroundColor": "#fee2e2",
      "fillStyle": "solid",
      "strokeWidth": 2,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "a9",
      "roundness": {"type": 3},
      "seed": 110,
      "version": 1,
      "versionNonce": 1010,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false
    },
    {
      "id": "robot-text",
      "type": "text",
      "x": 1050,
      "y": 205,
      "width": 90,
      "height": 90,
      "angle": 0,
      "strokeColor": "#172033",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 1,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "aA",
      "roundness": null,
      "seed": 111,
      "version": 1,
      "versionNonce": 1011,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "fontSize": 20,
      "fontFamily": 1,
      "text": "机器人\n\n环境交互",
      "rawText": "机器人\n\n环境交互",
      "textAlign": "center",
      "verticalAlign": "middle",
      "containerId": null,
      "originalText": "机器人\n\n环境交互",
      "autoResize": true,
      "lineHeight": 1.25
    },
    {
      "id": "arrow-1",
      "type": "arrow",
      "x": 245,
      "y": 250,
      "width": 60,
      "height": 0,
      "angle": 0,
      "strokeColor": "#334155",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 3,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "aB",
      "roundness": {"type": 2},
      "seed": 112,
      "version": 1,
      "versionNonce": 1012,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "points": [[0, 0], [60, 0]],
      "lastCommittedPoint": null,
      "startBinding": null,
      "endBinding": null,
      "startArrowhead": null,
      "endArrowhead": "arrow",
      "elbowed": false
    },
    {
      "id": "arrow-2",
      "type": "arrow",
      "x": 485,
      "y": 250,
      "width": 60,
      "height": 0,
      "angle": 0,
      "strokeColor": "#334155",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 3,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "aC",
      "roundness": {"type": 2},
      "seed": 113,
      "version": 1,
      "versionNonce": 1013,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "points": [[0, 0], [60, 0]],
      "lastCommittedPoint": null,
      "startBinding": null,
      "endBinding": null,
      "startArrowhead": null,
      "endArrowhead": "arrow",
      "elbowed": false
    },
    {
      "id": "arrow-3",
      "type": "arrow",
      "x": 745,
      "y": 250,
      "width": 60,
      "height": 0,
      "angle": 0,
      "strokeColor": "#334155",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 3,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "aD",
      "roundness": {"type": 2},
      "seed": 114,
      "version": 1,
      "versionNonce": 1014,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "points": [[0, 0], [60, 0]],
      "lastCommittedPoint": null,
      "startBinding": null,
      "endBinding": null,
      "startArrowhead": null,
      "endArrowhead": "arrow",
      "elbowed": false
    },
    {
      "id": "arrow-4",
      "type": "arrow",
      "x": 975,
      "y": 250,
      "width": 60,
      "height": 0,
      "angle": 0,
      "strokeColor": "#334155",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 3,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "aE",
      "roundness": {"type": 2},
      "seed": 115,
      "version": 1,
      "versionNonce": 1015,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "points": [[0, 0], [60, 0]],
      "lastCommittedPoint": null,
      "startBinding": null,
      "endBinding": null,
      "startArrowhead": null,
      "endArrowhead": "arrow",
      "elbowed": false
    },
    {
      "id": "training-box",
      "type": "rectangle",
      "x": 235,
      "y": 435,
      "width": 730,
      "height": 125,
      "angle": 0,
      "strokeColor": "#64748b",
      "backgroundColor": "#f8fafc",
      "fillStyle": "solid",
      "strokeWidth": 2,
      "strokeStyle": "dashed",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "aF",
      "roundness": {"type": 3},
      "seed": 116,
      "version": 1,
      "versionNonce": 1016,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false
    },
    {
      "id": "training-text",
      "type": "text",
      "x": 290,
      "y": 465,
      "width": 620,
      "height": 65,
      "angle": 0,
      "strokeColor": "#172033",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 1,
      "strokeStyle": "solid",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "aG",
      "roundness": null,
      "seed": 117,
      "version": 1,
      "versionNonce": 1017,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "fontSize": 21,
      "fontFamily": 1,
      "text": "训练监督\n机器人轨迹数据  ·  视觉语言对齐损失  ·  动作预测损失",
      "rawText": "训练监督\n机器人轨迹数据  ·  视觉语言对齐损失  ·  动作预测损失",
      "textAlign": "center",
      "verticalAlign": "middle",
      "containerId": null,
      "originalText": "训练监督\n机器人轨迹数据  ·  视觉语言对齐损失  ·  动作预测损失",
      "autoResize": true,
      "lineHeight": 1.25
    },
    {
      "id": "supervision-arrow",
      "type": "arrow",
      "x": 645,
      "y": 435,
      "width": 0,
      "height": 100,
      "angle": 3.141592653589793,
      "strokeColor": "#64748b",
      "backgroundColor": "transparent",
      "fillStyle": "solid",
      "strokeWidth": 2,
      "strokeStyle": "dashed",
      "roughness": 1,
      "opacity": 100,
      "groupIds": [],
      "frameId": null,
      "index": "aH",
      "roundness": {"type": 2},
      "seed": 118,
      "version": 1,
      "versionNonce": 1018,
      "isDeleted": false,
      "boundElements": null,
      "updated": 1788336000000,
      "link": null,
      "locked": false,
      "points": [[0, 0], [0, 100]],
      "lastCommittedPoint": null,
      "startBinding": null,
      "endBinding": null,
      "startArrowhead": null,
      "endArrowhead": "arrow",
      "elbowed": false
    }
  ],
  "appState": {
    "gridSize": 20,
    "gridStep": 5,
    "gridModeEnabled": false,
    "viewBackgroundColor": "#fffdf8"
  },
  "files": {}
}