results/va_models.json

[
  {
    "id": 1,
    "model": "LBC",
    "venue": "CoRL'20",
    "input": [
      "camera"
    ],
    "dataset": [
      "CARLA",
      "NoCrash"
    ],
    "vision": "ResNet",
    "action": "RL",
    "output": "Ctrl.+Traj.",
    "category": "Action-Only Models"
  },
  {
    "id": 2,
    "model": "Latent-DRL",
    "venue": "CVPR'20",
    "input": [
      "camera"
    ],
    "dataset": [
      "CARLA"
    ],
    "vision": "ResNet",
    "action": "RL",
    "output": "Ctrl.",
    "category": "Action-Only Models"
  },
  {
    "id": 3,
    "model": "NEAT",
    "venue": "ICCV'21",
    "input": [
      "camera"
    ],
    "dataset": [
      "CARLA"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Action-Only Models"
  },
  {
    "id": 4,
    "model": "Roach",
    "venue": "ICCV'21",
    "input": [
      "camera"
    ],
    "dataset": [
      "CARLA",
      "NoCrash"
    ],
    "vision": "ResNet",
    "action": "RL",
    "output": "Ctrl.",
    "category": "Action-Only Models"
  },
  {
    "id": 5,
    "model": "WoR",
    "venue": "ICCV'21",
    "input": [
      "camera"
    ],
    "dataset": [
      "CARLA",
      "NoCrash",
      "ProcGen"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Ctrl.",
    "category": "Action-Only Models"
  },
  {
    "id": 6,
    "model": "TCP",
    "venue": "NeurIPS'22",
    "input": [
      "camera"
    ],
    "dataset": [
      "CARLA"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Ctrl.+Traj.",
    "category": "Action-Only Models"
  },
  {
    "id": 7,
    "model": "Urban-Driver",
    "venue": "CoRL'22",
    "input": [
      "camera"
    ],
    "dataset": [
      "Lyft"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Action-Only Models"
  },
  {
    "id": 8,
    "model": "LAV",
    "venue": "CVPR'22",
    "input": [
      "camera",
      "lidar"
    ],
    "dataset": [
      "CARLA"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Ctrl.+Traj.",
    "category": "Action-Only Models"
  },
  {
    "id": 9,
    "model": "TransFuser",
    "venue": "TPAMI'23",
    "input": [
      "camera",
      "lidar"
    ],
    "dataset": [
      "CARLA"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Action-Only Models"
  },
  {
    "id": 10,
    "model": "GRI",
    "venue": "Robotics'23",
    "input": [
      "camera"
    ],
    "dataset": [
      "CARLA"
    ],
    "vision": "EfficientNet",
    "action": "RL",
    "output": "Ctrl.",
    "category": "Action-Only Models"
  },
  {
    "id": 11,
    "model": "BEVPlanner",
    "venue": "CVPR'24",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Action-Only Models"
  },
  {
    "id": 12,
    "model": "Raw2Drive",
    "venue": "NeurIPS'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "CARLA",
      "Bench2Drive"
    ],
    "vision": "ResNet",
    "action": "RL",
    "output": "Ctrl.",
    "category": "Action-Only Models"
  },
  {
    "id": 13,
    "model": "RAD",
    "venue": "NeurIPS'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "Private"
    ],
    "vision": "ResNet",
    "action": "RL",
    "output": "Traj.",
    "category": "Action-Only Models"
  },
  {
    "id": 14,
    "model": "TrajDiff",
    "venue": "arXiv'25",
    "input": [
      "camera",
      "lidar",
      "status"
    ],
    "dataset": [
      "NAVSIM"
    ],
    "vision": "ResNet",
    "action": "GEN",
    "output": "Traj.",
    "category": "Action-Only Models"
  },
  {
    "id": 15,
    "model": "ST-P3",
    "venue": "ECCV'22",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes",
      "CARLA"
    ],
    "vision": "EfficientNet",
    "action": "SEL",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 16,
    "model": "UniAD",
    "venue": "CVPR'23",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 17,
    "model": "VAD",
    "venue": "ICCV'23",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 18,
    "model": "OccNet",
    "venue": "ICCV'23",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes",
      "OpenOcc"
    ],
    "vision": "ResNet",
    "action": "SEL",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 19,
    "model": "GenAD",
    "venue": "ECCV'24",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "GEN",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 20,
    "model": "PARA-Drive",
    "venue": "CVPR'24",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 21,
    "model": "Hydra-MDP",
    "venue": "CVPRW'24",
    "input": [
      "camera",
      "lidar"
    ],
    "dataset": [
      "NAVSIM"
    ],
    "vision": "ResNet",
    "action": "SEL",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 22,
    "model": "SparseAD",
    "venue": "arXiv'24",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 23,
    "model": "GaussianAD",
    "venue": "arXiv'24",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 24,
    "model": "DiFSD",
    "venue": "arXiv'24",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "GEN",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 25,
    "model": "DriveTransformer",
    "venue": "ICLR'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes",
      "Bench2Drive"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 26,
    "model": "SparseDrive",
    "venue": "ICRA'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 27,
    "model": "DiffusionDrive",
    "venue": "CVPR'25",
    "input": [
      "camera",
      "lidar"
    ],
    "dataset": [
      "nuScenes",
      "NAVSIM"
    ],
    "vision": "ResNet",
    "action": "GEN",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 28,
    "model": "GoalFlow",
    "venue": "CVPR'25",
    "input": [
      "camera",
      "lidar",
      "status"
    ],
    "dataset": [
      "NAVSIM"
    ],
    "vision": "VoVNet",
    "action": "GEN",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 29,
    "model": "GuideFlow",
    "venue": "arXiv'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes",
      "NAVSIM",
      "Bench2Drive"
    ],
    "vision": "ResNet",
    "action": "GEN",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 30,
    "model": "ETA",
    "venue": "arXiv'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "Bench2Drive"
    ],
    "vision": "CLIP-ViT",
    "action": "REG",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 31,
    "model": "Geo",
    "venue": "arXiv'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 32,
    "model": "DiffusionDriveV2",
    "venue": "arXiv'25",
    "input": [
      "camera",
      "lidar"
    ],
    "dataset": [
      "NAVSIM"
    ],
    "vision": "ResNet",
    "action": "GEN",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 33,
    "model": "NaviHydra",
    "venue": "arXiv'25",
    "input": [
      "camera",
      "lidar"
    ],
    "dataset": [
      "NAVSIM"
    ],
    "vision": "ResNet",
    "action": "SEL",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 34,
    "model": "Mimir",
    "venue": "arXiv'25",
    "input": [
      "camera",
      "lidar"
    ],
    "dataset": [
      "NAVSIM"
    ],
    "vision": "ResNet",
    "action": "GEN",
    "output": "Traj.",
    "category": "Perception-Action Models"
  },
  {
    "id": 35,
    "model": "DriveDreamer",
    "venue": "ECCV'24",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "SD",
    "action": "REG",
    "output": "Traj.",
    "category": "Image-Based World Models"
  },
  {
    "id": 36,
    "model": "GenAD",
    "venue": "CVPR'24",
    "input": [
      "camera"
    ],
    "dataset": [
      "OpenDV"
    ],
    "vision": "SDXL",
    "action": "REG",
    "output": "Traj.",
    "category": "Image-Based World Models"
  },
  {
    "id": 37,
    "model": "Drive-WM",
    "venue": "CVPR'24",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ConvNeXt",
    "action": "SEL",
    "output": "Traj.",
    "category": "Image-Based World Models"
  },
  {
    "id": 38,
    "model": "DrivingWorld",
    "venue": "arXiv'24",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "nuPlan"
    ],
    "vision": "VQ-VAE",
    "action": "REG",
    "output": "Traj.",
    "category": "Image-Based World Models"
  },
  {
    "id": 39,
    "model": "Imagine-2-Drive",
    "venue": "IROS'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "CARLA"
    ],
    "vision": "SVD",
    "action": "SEL",
    "output": "Traj.",
    "category": "Image-Based World Models"
  },
  {
    "id": 40,
    "model": "DrivingGPT",
    "venue": "ICCV'25",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "nuPlan",
      "NAVSIM"
    ],
    "vision": "VQ-VAE",
    "action": "REG",
    "output": "Traj.",
    "category": "Image-Based World Models"
  },
  {
    "id": 41,
    "model": "Epona",
    "venue": "ICCV'25",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "nuScenes",
      "NAVSIM",
      "nuPlan"
    ],
    "vision": "DC-AE",
    "action": "REG",
    "output": "Traj.",
    "category": "Image-Based World Models"
  },
  {
    "id": 42,
    "model": "VaViM",
    "venue": "arXiv'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "OpenDV",
      "nuScenes",
      "nuPlan"
    ],
    "vision": "LLaMAGen",
    "action": "GEN",
    "output": "Traj.",
    "category": "Image-Based World Models"
  },
  {
    "id": 43,
    "model": "OccWorld",
    "venue": "ECCV'24",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "nuScenes",
      "Occ3D"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Occupancy-Based World Models"
  },
  {
    "id": 44,
    "model": "NeMo",
    "venue": "ECCV'24",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Occupancy-Based World Models"
  },
  {
    "id": 45,
    "model": "OccVAR",
    "venue": "-",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "nuScenes",
      "Occ3D"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Occupancy-Based World Models"
  },
  {
    "id": 46,
    "model": "RenderWorld",
    "venue": "arXiv'24",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes",
      "Occ3D"
    ],
    "vision": "Swin-T",
    "action": "REG",
    "output": "Traj.",
    "category": "Occupancy-Based World Models"
  },
  {
    "id": 47,
    "model": "DFIT-OccWorld",
    "venue": "arXiv'24",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "nuScenes",
      "Occ3D"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Occupancy-Based World Models"
  },
  {
    "id": 48,
    "model": "Drive-OccWorld",
    "venue": "AAAI'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes",
      "Cam4DOcc"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Occupancy-Based World Models"
  },
  {
    "id": 49,
    "model": "T³Former",
    "venue": "arXiv'25",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "nuScenes",
      "Occ3D"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Occupancy-Based World Models"
  },
  {
    "id": 50,
    "model": "AD-R1",
    "venue": "arXiv'25",
    "input": [
      "camera",
      "lidar",
      "status"
    ],
    "dataset": [
      "nuScenes",
      "NAVSIM"
    ],
    "vision": "-",
    "action": "RL",
    "output": "Traj.",
    "category": "Occupancy-Based World Models"
  },
  {
    "id": 51,
    "model": "Covariate-Shift",
    "venue": "arXiv'24",
    "input": [
      "camera",
      "status"
    ],
    "dataset": [
      "CARLA"
    ],
    "vision": "DINOv2",
    "action": "REG",
    "output": "Traj.",
    "category": "Latent-Based World Models"
  },
  {
    "id": 52,
    "model": "World4Drive",
    "venue": "ICCV'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes",
      "NAVSIM"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Latent-Based World Models"
  },
  {
    "id": 53,
    "model": "WoTE",
    "venue": "ICCV'25",
    "input": [
      "camera",
      "lidar"
    ],
    "dataset": [
      "NAVSIM",
      "Bench2Drive"
    ],
    "vision": "ResNet",
    "action": "SEL",
    "output": "Traj.",
    "category": "Latent-Based World Models"
  },
  {
    "id": 54,
    "model": "LAW",
    "venue": "ICLR'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes",
      "NAVSIM",
      "CARLA"
    ],
    "vision": "Swin-T",
    "action": "REG",
    "output": "Traj.",
    "category": "Latent-Based World Models"
  },
  {
    "id": 55,
    "model": "SSR",
    "venue": "ICLR'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes",
      "CARLA"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Latent-Based World Models"
  },
  {
    "id": 56,
    "model": "Echo-Planning",
    "venue": "arXiv'25",
    "input": [
      "camera"
    ],
    "dataset": [
      "nuScenes"
    ],
    "vision": "ResNet",
    "action": "REG",
    "output": "Traj.",
    "category": "Latent-Based World Models"
  },
  {
    "id": 57,
    "model": "SeerDrive",
    "venue": "NeurIPS'25",
    "input": [
      "camera",
      "lidar"
    ],
    "dataset": [
      "nuScenes",
      "NAVSIM"
    ],
    "vision": "VoVNet",
    "action": "SEL",
    "output": "Traj.",
    "category": "Latent-Based World Models"
  }
]