# One-Step Generative Modeling

Probabilistic traffic forecasting has relied on multi-step diffusion sampling, which is slow and often trails deterministic baselines on point accuracy. CoReFlow learns the flow map, the solution operator of the probability-flow ODE, directly and relaxes trajectory consistency through the conditional mean, so a single forward pass produces the full forecast. On four real road-network datasets, PEMS03, PEMS04, PEMS07 and PEMS08, it ranks first in 11 of 12 deterministic metric cases and takes all 14 reported comparisons against generative baselines on PEMS07 and PEMS08.

Probabilistic traffic forecasting has relied on multi-step diffusion sampling, which is slow and often trails deterministic baselines on point accuracy. CoReFlow learns the flow map, the solution operator of the probability-flow ODE, directly and relaxes trajectory consistency through the conditional mean, so a single forward pass produces the full forecast. On four real road-network datasets, PEMS03, PEMS04, PEMS07 and PEMS08, it ranks first in 11 of 12 deterministic metric cases and takes all 14 reported comparisons against generative baselines on PEMS07 and PEMS08.

Few-step text-to-image generation must render prompt details with very few sampling steps, and distribution matching distillation (DMD) relies on learned score differences whose statistics need not align. Intrinsic Distribution Matching keeps the full DMD correction and adds a moment constraint on the means and per-coordinate standard deviations of the generator's exponential-moving-average features, with no external feature encoder. On Z-Image-Turbo 6B at two network evaluations it reaches 94.25% and 90.20% on Chinese and English LongText-Bench, the highest scores among the compared methods at that budget.

Few-step text-to-image generation must render prompt details with very few sampling steps, and distribution matching distillation (DMD) relies on learned score differences whose statistics need not align. Intrinsic Distribution Matching keeps the full DMD correction and adds a moment constraint on the means and per-coordinate standard deviations of the generator's exponential-moving-average features, with no external feature encoder. On Z-Image-Turbo 6B at two network evaluations it reaches 94.25% and 90.20% on Chinese and English LongText-Bench, the highest scores among the compared methods at that budget.