REVIEW 6 cited by
Flow Generator Matching
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In the realm of Artificial Intelligence Generated Content (AIGC), flow-matching models have emerged as a powerhouse, achieving success due to their robust theoretical underpinnings and solid ability for large-scale generative modeling. These models have demonstrated state-of-the-art performance, but their brilliance comes at a cost. The process of sampling from these models is notoriously demanding on computational resources, as it necessitates the use of multi-step numerical ordinary differential equations (ODEs). Against this backdrop, this paper presents a novel solution with theoretical guarantees in the form of Flow Generator Matching (FGM), an innovative approach designed to accelerate the sampling of flow-matching models into a one-step generation, while maintaining the original performance. On the CIFAR10 unconditional generation benchmark, our one-step FGM model achieves a new record Fr\'echet Inception Distance (FID) score of 3.08 among few-step flow-matching-based models, outperforming original 50-step flow-matching models. Furthermore, we use the FGM to distill the Stable Diffusion 3, a leading text-to-image flow-matching model based on the MM-DiT architecture. The resulting MM-DiT-FGM one-step text-to-image model demonstrates outstanding industry-level performance. When evaluated on the GenEval benchmark, MM-DiT-FGM has delivered remarkable generating qualities, rivaling other multi-step models in light of the efficiency of a single generation step.
Forward citations
Cited by 6 Pith papers
-
Amortized Moment Matching for Visual Generation
Amortized Fréchet Distance uses neural nets to match conditional means and covariances, yielding stronger one-step visual generators than explicit FD-loss or multi-step teachers.
-
IDLM: Inverse-distilled Diffusion Language Models
IDLM distills pretrained discrete diffusion language models into few-step generators, cutting inference steps by 4–64× with roughly matched GenPPL and entropy.
-
Overclocking Electrostatic Generative Models
IPFM trains a few-step generator to reproduce the teacher PFGM++ electrostatic field, matches or beats teacher FID on CIFAR-10 and FFHQ, and recovers SiD as D goes to infinity.
-
Distributional Diffusion Models with Scoring Rules
Training diffusion models to output a sample from the posterior distribution of clean data given noisy data, via an energy scoring rule, improves few-step generation quality on images and robot trajectories.
-
Inverse Bridge Matching Distillation
Inverse Bridge Matching Distillation converts a trained diffusion bridge model into a one-step or few-step generator by matching the teacher's drift through a tractable inverse bridge matching objective.
-
Straight-Path Flow Matching for Incomplete Multi-View Clustering
Straight-path flow matching between paired latent representations outperforms diffusion-based methods for incomplete multi-view clustering by preserving cluster structure during view completion.
Discussion (0). Continue with ORCID to comment.