AI Research 技术调研

标签: linear-attention

此标签下有3条笔记。

  • 2026年7月16日

    SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention

    • sara-rt
    • up-training
    • linear-attention
    • performer
    • kernelized-attention
    • rt-2
    • point-cloud-transformer
    • inference-speedup
    • on-robot-deployment
    • icra-best-paper
  • 2026年6月25日

    Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers

    • t2i
    • diffusion-transformer
    • linear-attention
    • deep-compression-ae
    • rectified-flow
    • efficient
    • on-device
    • gemma
  • 2026年6月25日

    SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

    • t2i
    • linear-attention
    • dit
    • model-growth
    • depth-pruning
    • inference-scaling
    • came-8bit
    • efficient-scaling
    • geneval
    • sana

  • GitHub