S-FLM is a hyperspherical latent flow language model that improves continuous flow language models on large-vocabulary reasoning tasks and closes the gap to masked diffusion at standard sampling temperature.
Flow straight and fast: Learning to generate and transfer data with rectified flow
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
Deriving the optimal coefficient for the conditional velocity field in MeanFlow training reduces gradient variance and improves sample quality in one-step generative models.
JFDL allows pre-trained Consistency Models to perform guided image generation post-hoc by aligning flow distributions, reducing FID scores on CIFAR-10 and ImageNet without needing a teacher model.
citing papers explorer
-
Language Modeling with Hyperspherical Flows
S-FLM is a hyperspherical latent flow language model that improves continuous flow language models on large-vocabulary reasoning tasks and closes the gap to masked diffusion at standard sampling temperature.
-
On Variance Reduction in Learning Mean Flows
Deriving the optimal coefficient for the conditional velocity field in MeanFlow training reduces gradient variance and improves sample quality in one-step generative models.
-
Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
JFDL allows pre-trained Consistency Models to perform guided image generation post-hoc by aligning flow distributions, reducing FID scores on CIFAR-10 and ImageNet without needing a teacher model.