FLDD learns non-Markovian marginal and posterior distributions for the forward process so a factorized reverse process can match the target better and produce higher-quality samples in fewer steps.
Meng Liu, Keqiang Yan, Bora Oztekin, and Shuiwang Ji
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
FLDD learns non-Markovian marginal and posterior distributions for the forward process so a factorized reverse process can match the target better and produce higher-quality samples in fewer steps.