{
  "frequency": {
    "language": 73,
    "vision": 92,
    "imitation": 48,
    "diffusion": 58,
    "3D": 28,
    "RL": 41,
    "VLA": 33,
    "open-source": 2,
    "audio-speech": 22,
    "world-model": 15,
    "RF-radar": 17,
    "navigation": 18,
    "dataset": 40,
    "transformer": 78,
    "manipulation": 35,
    "sim2real": 18,
    "VLM": 27,
    "flow-matching": 13,
    "locomotion": 6,
    "tactile": 5,
    "mamba-ssm": 8
  },
  "cooccurrence": {
    "language": {
      "vision": 46,
      "imitation": 17,
      "RL": 18,
      "VLA": 22,
      "open-source": 2,
      "audio-speech": 7,
      "3D": 6,
      "RF-radar": 1,
      "dataset": 19,
      "transformer": 47,
      "diffusion": 25,
      "manipulation": 11,
      "VLM": 21,
      "flow-matching": 8,
      "sim2real": 4,
      "navigation": 2,
      "tactile": 2,
      "locomotion": 2,
      "world-model": 6,
      "mamba-ssm": 4
    },
    "vision": {
      "language": 46,
      "imitation": 25,
      "VLA": 17,
      "open-source": 2,
      "RF-radar": 10,
      "dataset": 26,
      "transformer": 55,
      "audio-speech": 10,
      "diffusion": 38,
      "sim2real": 9,
      "manipulation": 22,
      "VLM": 23,
      "RL": 14,
      "3D": 17,
      "flow-matching": 9,
      "navigation": 9,
      "locomotion": 1,
      "tactile": 5,
      "mamba-ssm": 4,
      "world-model": 4
    },
    "imitation": {
      "language": 17,
      "vision": 25,
      "transformer": 24,
      "audio-speech": 1,
      "manipulation": 20,
      "RL": 19,
      "dataset": 7,
      "diffusion": 30,
      "VLA": 11,
      "sim2real": 10,
      "VLM": 3,
      "navigation": 4,
      "3D": 8,
      "flow-matching": 7,
      "RF-radar": 1,
      "locomotion": 1,
      "tactile": 1,
      "mamba-ssm": 2,
      "world-model": 4
    },
    "diffusion": {
      "3D": 13,
      "world-model": 8,
      "VLA": 18,
      "transformer": 42,
      "vision": 38,
      "audio-speech": 3,
      "dataset": 9,
      "imitation": 30,
      "sim2real": 7,
      "VLM": 6,
      "manipulation": 22,
      "RL": 18,
      "language": 25,
      "navigation": 6,
      "flow-matching": 13,
      "RF-radar": 3,
      "locomotion": 2,
      "tactile": 1,
      "mamba-ssm": 2
    },
    "3D": {
      "diffusion": 13,
      "language": 6,
      "VLA": 5,
      "RF-radar": 8,
      "navigation": 2,
      "vision": 17,
      "manipulation": 9,
      "RL": 9,
      "sim2real": 4,
      "transformer": 10,
      "imitation": 8,
      "dataset": 7,
      "tactile": 1,
      "audio-speech": 2,
      "locomotion": 1,
      "VLM": 2
    },
    "RL": {
      "language": 18,
      "manipulation": 13,
      "navigation": 4,
      "dataset": 8,
      "imitation": 19,
      "diffusion": 18,
      "transformer": 18,
      "vision": 14,
      "VLA": 8,
      "VLM": 3,
      "3D": 9,
      "sim2real": 8,
      "locomotion": 4,
      "world-model": 12,
      "mamba-ssm": 6
    },
    "VLA": {
      "language": 22,
      "vision": 17,
      "open-source": 1,
      "audio-speech": 1,
      "3D": 5,
      "diffusion": 18,
      "world-model": 4,
      "transformer": 19,
      "imitation": 11,
      "sim2real": 6,
      "manipulation": 6,
      "VLM": 9,
      "RL": 8,
      "navigation": 1,
      "dataset": 5,
      "flow-matching": 6,
      "tactile": 2,
      "mamba-ssm": 3
    },
    "open-source": {
      "language": 2,
      "vision": 2,
      "VLA": 1,
      "VLM": 1,
      "dataset": 1
    },
    "audio-speech": {
      "language": 7,
      "VLA": 1,
      "navigation": 4,
      "transformer": 13,
      "vision": 10,
      "dataset": 6,
      "imitation": 1,
      "diffusion": 3,
      "tactile": 1,
      "3D": 2,
      "RF-radar": 3
    },
    "world-model": {
      "diffusion": 8,
      "VLA": 4,
      "language": 6,
      "locomotion": 1,
      "dataset": 2,
      "transformer": 8,
      "RL": 12,
      "mamba-ssm": 6,
      "vision": 4,
      "imitation": 4,
      "sim2real": 2,
      "navigation": 1,
      "VLM": 1
    },
    "RF-radar": {
      "3D": 8,
      "navigation": 7,
      "language": 1,
      "vision": 10,
      "dataset": 4,
      "diffusion": 3,
      "flow-matching": 1,
      "transformer": 5,
      "imitation": 1,
      "audio-speech": 3
    },
    "navigation": {
      "3D": 2,
      "RF-radar": 7,
      "audio-speech": 4,
      "manipulation": 5,
      "RL": 4,
      "dataset": 3,
      "diffusion": 6,
      "imitation": 4,
      "VLA": 1,
      "sim2real": 3,
      "flow-matching": 1,
      "transformer": 6,
      "vision": 9,
      "locomotion": 2,
      "tactile": 1,
      "language": 2,
      "world-model": 1
    },
    "dataset": {
      "language": 19,
      "vision": 26,
      "RF-radar": 4,
      "transformer": 15,
      "audio-speech": 6,
      "diffusion": 9,
      "manipulation": 11,
      "navigation": 3,
      "RL": 8,
      "imitation": 7,
      "sim2real": 6,
      "3D": 7,
      "flow-matching": 1,
      "VLA": 5,
      "tactile": 2,
      "locomotion": 2,
      "world-model": 2,
      "VLM": 12,
      "open-source": 1,
      "mamba-ssm": 1
    },
    "transformer": {
      "language": 47,
      "audio-speech": 13,
      "vision": 55,
      "dataset": 15,
      "imitation": 24,
      "diffusion": 42,
      "VLA": 19,
      "sim2real": 4,
      "VLM": 17,
      "manipulation": 13,
      "RL": 18,
      "3D": 10,
      "flow-matching": 10,
      "RF-radar": 5,
      "navigation": 6,
      "locomotion": 2,
      "tactile": 4,
      "world-model": 8,
      "mamba-ssm": 5
    },
    "manipulation": {
      "navigation": 5,
      "RL": 13,
      "dataset": 11,
      "imitation": 20,
      "vision": 22,
      "VLA": 6,
      "diffusion": 22,
      "sim2real": 9,
      "transformer": 13,
      "language": 11,
      "3D": 9,
      "flow-matching": 6,
      "VLM": 2,
      "tactile": 1,
      "locomotion": 3
    },
    "sim2real": {
      "diffusion": 7,
      "transformer": 4,
      "vision": 9,
      "imitation": 10,
      "VLA": 6,
      "manipulation": 9,
      "dataset": 6,
      "navigation": 3,
      "3D": 4,
      "RL": 8,
      "locomotion": 4,
      "language": 4,
      "tactile": 1,
      "mamba-ssm": 1,
      "world-model": 2,
      "VLM": 1
    },
    "VLM": {
      "diffusion": 6,
      "transformer": 17,
      "vision": 23,
      "imitation": 3,
      "VLA": 9,
      "language": 21,
      "RL": 3,
      "manipulation": 2,
      "flow-matching": 2,
      "3D": 2,
      "dataset": 12,
      "mamba-ssm": 1,
      "open-source": 1,
      "world-model": 1,
      "sim2real": 1
    },
    "flow-matching": {
      "diffusion": 13,
      "transformer": 10,
      "RF-radar": 1,
      "navigation": 1,
      "imitation": 7,
      "vision": 9,
      "manipulation": 6,
      "dataset": 1,
      "language": 8,
      "VLA": 6,
      "VLM": 2
    },
    "locomotion": {
      "diffusion": 2,
      "transformer": 2,
      "RL": 4,
      "imitation": 1,
      "sim2real": 4,
      "vision": 1,
      "navigation": 2,
      "language": 2,
      "world-model": 1,
      "dataset": 2,
      "manipulation": 3,
      "3D": 1
    },
    "tactile": {
      "vision": 5,
      "audio-speech": 1,
      "navigation": 1,
      "transformer": 4,
      "manipulation": 1,
      "dataset": 2,
      "VLA": 2,
      "sim2real": 1,
      "language": 2,
      "imitation": 1,
      "diffusion": 1,
      "3D": 1
    },
    "mamba-ssm": {
      "diffusion": 2,
      "transformer": 5,
      "language": 4,
      "vision": 4,
      "VLA": 3,
      "VLM": 1,
      "RL": 6,
      "world-model": 6,
      "imitation": 2,
      "sim2real": 1,
      "dataset": 1
    }
  }
}