Flow matching (FM) is a general framework for defining probability paths via
Ordinary Differential Equations (ODEs) to transform between noise and data
samples. Recent approaches attempt to straighten these flow trajectories to
generate high-quality samples with fewer function evaluations, typically
through iterative rectification methods or optimal transport solutions. In this
paper, we introduce Consistency Flow Matching (Consistency-FM), a novel FM
method that explicitly enforces self-consistency in the velocity field.
Consistency-FM directly defines straight flows starting from different times to
the same endpoint, imposing constraints on their velocity values. Additionally,
we propose a multi-segment training approach for Consistency-FM to enhance
expressiveness, achieving a better trade-off between sampling quality and
speed. Preliminary experiments demonstrate that our Consistency-FM
significantly improves training efficiency by converging 4.4x faster than
consistency models and 1.7x faster than rectified flow models while achieving
better generation quality. Our code is available at:
this https URL

Consistency Flow Matching (Consistency-FM) is a novel flow matching method that enforces self-consistency in the velocity field, achieving better sampling quality and training efficiency.

一致性流匹配：通过速度一致性定义直线流

Consistency Flow Matching: Defining Straight Flows with Velocity  Consistency

Diffusion models are relatively easy to train but require many steps to
generate samples. Consistency models are far more difficult to train, but
generate samples in a single step.
In this paper we propose Multistep Consistency Models: A unification between
Consistency Models (Song et al., 2023) and TRACT (Berthelot et al., 2023) that
can interpolate between a consistency model and a diffusion model: a trade-off
between sampling speed and sampling quality. Specifically, a 1-step consistency
model is a conventional consistency model whereas we show that a $\infty$-step
consistency model is a diffusion model.
Multistep Consistency Models work really well in practice. By increasing the
sample budget from a single step to 2-8 steps, we can train models more easily
that generate higher quality samples, while retaining much of the sampling
speed benefits. Notable results are 1.4 FID on Imagenet 64 in 8 step and 2.1
FID on Imagenet128 in 8 steps with consistency distillation. We also show that
our method scales to a text-to-image diffusion model, generating samples that
are very close to the quality of the original model.

多步一致性模型是一种介于一致性模型和扩散模型之间的统一方法，通过增加采样步骤可以更容易地训练出高质量样本，保持了大部分采样速度的优势。

多步骤一致性模型

Multistep Consistency Models

Tabular data synthesis is a long-standing research topic in machine learning.
Many different methods have been proposed over the past decades, ranging from
statistical methods to deep generative methods. However, it has not always been
successful due to the complicated nature of real-world tabular data. In this
paper, we present a new model named Score-based Tabular data Synthesis (STaSy)
and its training strategy based on the paradigm of score-based generative
modeling. Despite the fact that score-based generative models have resolved
many issues in generative models, there still exists room for improvement in
tabular data synthesis. Our proposed training strategy includes a self-paced
learning technique and a fine-tuning strategy, which further increases the
sampling quality and diversity by stabilizing the denoising score matching
training. Furthermore, we also conduct rigorous experimental studies in terms
of the generative task trilemma: sampling quality, diversity, and time. In our
experiments with 15 benchmark tabular datasets and 7 baselines, our method
outperforms existing methods in terms of task-dependant evaluations and
diversity.

本文提出了一种名为 STaSy 的新模型和它基于评分的生成模型训练策略，在实验中，该模型在生成任务中较现有方法表现更好，提升了样本质量和多样性。

STaSy: 基于得分的表格数据合成

STaSy: Score-based Tabular data Synthesis

Score-based generative models (SGMs) are a recently proposed paradigm for
deep generative tasks and now show the state-of-the-art sampling performance.
It is known that the original SGM design solves the two problems of the
generative trilemma: i) sampling quality, and ii) sampling diversity. However,
the last problem of the trilemma was not solved, i.e., their training/sampling
complexity is notoriously high. To this end, distilling SGMs into simpler
models, e.g., generative adversarial networks (GANs), is gathering much
attention currently. We present an enhanced distillation method, called
straight-path interpolation GAN (SPI-GAN), which can be compared to the
state-of-the-art shortcut-based distillation method, called denoising diffusion
GAN (DD-GAN). However, our method corresponds to an extreme method that does
not use any intermediate shortcut information of the reverse SDE path, in which
case DD-GAN fails to obtain good results. Nevertheless, our straight-path
interpolation method greatly stabilizes the overall training process. As a
result, SPI-GAN is one of the best models in terms of the sampling
quality/diversity/time for CIFAR-10, CelebA-HQ-256, and LSUN-Church-256.

通过一种增强的简化方法 -- 直线插值生成器对抗网络直接 (SPI-GAN) 进行蒸馏，取代其他常规方法，在 CIFAR-10、CelebA-HQ-256 和 LSUN-Church-256 的采样 质量 / 多样性 / 时间 方面获得更好的表现，解决了生成三重奏问题中的采样质量问题。