Discrete diffusion models on Ising-like data exhibit analytically predictable speciation and collapse transitions in backward dynamics via high-temperature expansion and Random Energy Model condensation, with scaling matching continuous cases when noise varies with time.
Deep unsupervised learning using nonequilibrium thermodynamics
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Large-chunk online updates during inference let test-time training scale state capacity to 40% of model size and handle contexts up to 1M tokens without custom kernels.
HRSino adaptively allocates diffusion inference effort across spatial regions and scales for efficient high-resolution sinogram completion without training.
citing papers explorer
-
Dynamical Regimes of Discrete Diffusion Models
Discrete diffusion models on Ising-like data exhibit analytically predictable speciation and collapse transitions in backward dynamics via high-temperature expansion and Random Energy Model condensation, with scaling matching continuous cases when noise varies with time.
-
Test-Time Training Done Right
Large-chunk online updates during inference let test-time training scale state capacity to 40% of model size and handle contexts up to 1M tokens without custom kernels.
-
Training-Free Inference for High-Resolution Sinogram Completion
HRSino adaptively allocates diffusion inference effort across spatial regions and scales for efficient high-resolution sinogram completion without training.