Jiaxing You

PhysQK-AD: Convection-Diffusion-Driven Token Coordinate Evolution — From Pure Diffusion to a Learnable Convection-Diffusion Mixture

We report PhysQK-AD, a sequence model in which token coordinates evolve under convection–diffusion dynamics. In a small controlled setting (d=256, 4 layers, seq=128, 20 epochs), pure-diffusion PhysQK is close to a same-size multi-head attention baseline in validation loss (Δ ≈ +0...

PhysQK-AD: Convection-Diffusion-Driven Token Coordinate Evolution — From Pure Diffusion to a Learnable Convection-Diffusion Mixture

Modern language models are built almost entirely on Transformer self-attention. PhysQK (published separately, DOI 10.5281/zenodo.21870472) proposed an orthogonal path: retain the standard Transformer stack (windowed self-attention + FFN), and augment it with pure-diffusion dynami...