AI RESEARCH
PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers
arXiv CS.LG
•
ArXi:2603.13663v1 Announce Type: new The success of vision transformers-especially for generative modeling-is limited by the quadratic cost and weak spatial inductive bias of self-attention. We propose PDE-SSM, a spatial state-space block that replaces attention with a learnable convection-diffusion-reaction partial differential equation. This operator encodes a strong spatial prior by modeling information flow via physically grounded dynamics rather than all-to-all token interactions.