AI Research 技术调研

标签: VLN-CE

此标签下有3条笔记。

  • 2026年7月16日

    NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation

    • vision-language-navigation
    • VLN-CE
    • video-VLM
    • sim2real
    • RGB-only
    • embodied-navigation
    • LLaMA-VID
    • Vicuna-7B
    • RSS2024
  • 2026年7月16日

    Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks

    • vision-language-action
    • embodied-navigation
    • VLN-CE
    • ObjectNav
    • EQA
    • human-following
    • video-VLM
    • task-unification
    • Vicuna-7B
    • RSS2025
  • 2026年7月16日

    Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation

    • zero-shot-navigation
    • training-free
    • agentic-navigation
    • VLN-CE
    • ObjectNav
    • EQA
    • Aerial-VLN
    • cross-embodiment
    • MLLM-agent
    • backtracking

  • GitHub