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.
Generative modeling by estimating gradients of the data distribution
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Mercury Coder diffusion LLMs achieve throughputs of 1109 and 737 tokens per second on H100 GPUs, up to 10x faster than frontier models with comparable quality.
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.
-
Mercury: Ultra-Fast Language Models Based on Diffusion
Mercury Coder diffusion LLMs achieve throughputs of 1109 and 737 tokens per second on H100 GPUs, up to 10x faster than frontier models with comparable quality.