AI Research 技术调研

标签: internvl

此标签下有2条笔记。

  • 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6月25日

    InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

    • unified
    • mllm
    • mmdit
    • flow-matching
    • image-editing
    • text-rendering
    • cot
    • internvl

  • GitHub