AI Research 技术调研

标签: bev-representation

此标签下有3条笔记。

  • 2026年7月16日

    HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation

    • driving-world-model
    • bev-representation
    • world-queries
    • internvl2
    • point-cloud-forecasting
    • scene-understanding
    • unified-understanding-generation
    • nuscenes
    • iccv2025
  • 2026年7月16日

    DriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving

    • driving-world-model
    • vision-language-action
    • latent-space-world-model
    • flow-matching
    • diffusion-transformer
    • bev-representation
    • navsim
    • nuscenes
    • closed-loop-planning
    • internvl
  • 2026年7月16日

    Hermes++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

    • driving-world-model
    • bev-representation
    • world-queries
    • current-to-future-link
    • joint-geometric-optimization
    • unified-understanding-generation
    • internvl2
    • point-cloud-forecasting
    • nuscenes
    • extended-journal-version

  • GitHub