归一化层能实现跨空间维度的信息传递，可能影响扩散模型轨迹生成。
Spooky Action at a Distance: Normalization Layers Enable Side-Channel Spatial Communication
- 利用归一化层构建迭代消息传递机制
- 信息可超越局部感受野范围传播
- 适合关注空间通信效应的研究者
本研究发现，归一化层可在输入张量的空间维度间促进显著的信息交流。通过一个基于卷积架构的简化定位任务，我们证明归一化层能实现迭代式消息传递，使信息聚合范围超出局部感受野。结果表明，在需要保持空间感受野局限性的扩散模型轨迹生成等应用中，应谨慎使用归一化层。
原文摘要 · Abstract (English)
This work shows that normalization layers can facilitate a surprising degree of communication across the spatial dimensions of an input tensor. We study a toy localization task with a convolutional architecture and show that normalization layers enable an iterative message passing procedure, allowing information aggregation from well outside the local receptive field. Our results suggest that normalization layers should be employed with caution in applications such as diffusion-based trajectory generation, where maintaining a spatially limited receptive field is crucial.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。