AI Research 技术调研

标签: wan2.2

此标签下有4条笔记。

  • 2026年7月16日

    InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization

    • vla
    • mixture-of-transformers
    • latent-foresight
    • world-model
    • flow-matching
    • qwen3.5
    • gated-deltanet
    • wan2.2
    • compositional-generalization
    • fast-tokenizer
  • 2026年7月16日

    RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

    • world-model
    • 4d-scene-modeling
    • rgb-depth-optical-flow
    • tri-branch-diffusion
    • wan2.2
    • robotic-manipulation
    • bimanual-manipulation
    • inverse-dynamics-policy
    • cross-modal-attention
    • rynn-series
  • 2026年7月16日

    DreamX-World 1.0: A General-Purpose Interactive World Model

    • world-model
    • video-generation
    • camera-control
    • autoregressive
    • diffusion-transformer
    • memory-conditioning
    • event-control
    • reinforcement-learning
    • wan2.2
    • alibaba
  • 2026年7月16日

    MoWorld: A Flash World Model

    • world-model
    • flash-world-model
    • video-generation
    • camera-control
    • autoregressive-distillation
    • diffusion-transformer
    • npu
    • ascend
    • wan2.2
    • self-forcing

  • GitHub