{
  "Image Generation": [
    [
      "Text to Image",
      "Image to Text",
      "Image-to-Image",
      "Image-to-Video",
      "Unconditional Image Generation",
      "Video Classification",
      "Text-to-Video",
      "Zero-Shot Image Classification",
      "Mask Generation",
      "Zero-Shot Object Detection",
      "Text-to-3D",
      "Image-to-3D",
      "Image Feature Extraction",
      "Keypoint Detection",
      "Video-to-Video"
    ]
  ],
  "Natural Language Processing": [
    [
      "Text Classification",
      "Token Classification",
      "Table Question Answering",
      "Question Answering",
      "Zero-Shot Classification",
      "Translation",
      "Summarization",
      "Feature Extraction",
      "Text Generation",
      "Fill-Mask",
      "Sentence Similarity",
      "Text Ranking"
    ]
  ],
  "Audio": [
    [
      "Text-to-Speech",
      "Text-to-Audio",
      "Automatic Speech Recognition",
      "Audio-to-Audio",
      "Audio Classification",
      "Voice Activity Detection"
    ]
  ],
  "Tabular": [
    ["Tabular Classification", "Tabular Regression", "Time Series Forecasting"]
  ],
  "Reinforcement Learning": [["Reinforcement Learning", "Robotics"]],
  "Other": [["Graph Machine Learning"]]
}