A parallel-in-time τ-leaping sampler for absorbing discrete diffusion models is introduced, with an exponential-factorial convergence proof and empirical speedups of 7-9× on synthetic tasks and 1.45-1.86× on image/text tasks while using 50% fewer NFE.
arXiv preprint arXiv:2402.08095 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
GADD achieves O(polylog(ε^{-1})) sampling complexity for uniform-rate discrete diffusion models via Gibbs correctors derived from the score function, with supporting experiments on text and music.
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
citing papers explorer
-
Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling
A parallel-in-time τ-leaping sampler for absorbing discrete diffusion models is introduced, with an exponential-factorial convergence proof and empirical speedups of 7-9× on synthetic tasks and 1.45-1.86× on image/text tasks while using 50% fewer NFE.
-
From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
GADD achieves O(polylog(ε^{-1})) sampling complexity for uniform-rate discrete diffusion models via Gibbs correctors derived from the score function, with supporting experiments on text and music.
-
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.