arXiv AI
Jun 16
Efficient Flow Matching using Latent Variables
arXiv:2505. 04486v4 Announce Type: replace-cross Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models.
Joint Flow Matching for Generator-Consistent Classification
arXiv:2607. 23946v1 Announce Type: new Abstract: We introduce Joint Flow Matching (JFM), a training framework for continuous normalising flows over multiple variables.
Related stories
arXiv Machine Learning
Jun 2
Exploring and Exploiting Stability in Latent Flow Matching
arXiv:2605. 08398v2 Announce Type: replace Abstract: In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage.
arXiv Machine Learning
1d ago
A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions
arXiv:2605.06272v2 Announce Type: replace Abstract: While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation fr...
arXiv AI
Jul 15
Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models
arXiv:2607. 12171v1 Announce Type: cross Abstract: In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising.
arXiv Machine Learning
Jun 2
Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching
arXiv:2605. 00941v4 Announce Type: replace Abstract: Flow matching has become a leading framework for generative modeling, but quantifying the uncertainty of its samples remains an open problem.
arXiv AI
Jun 10
A Theory on Flow Matching with Neural Networks
arXiv:2606. 10089v1 Announce Type: cross Abstract: In this work, we develop theoretical foundation for flow matching with neural-network-parameterized conditional velocity fields.
Hugging Face Trending Papers
Jul 13
Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models
In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising. Although prior work shows that these parameterizations lead to different empirical behaviors, the mechanisms underlying their respective advantages remain to be underexplored, and how to combine them effectively is still unclear.
arXiv Machine Learning
Aug 27
Continuous Adversarial Flow Models
The paper introduces continuous adversarial flow models, a continuous-time flow framework trained with an adversarial objective that replaces the fixed mean-squared-error criterion of flow matching. By incorporating a learned discriminator, the method guides training toward a different generalized distribution, yielding samples more closely aligned with the target data distribution. Applied as a post‑training step, it markedly improves ImageNet 256px generation metrics—reducing the guidance‑free FID of latent‑space SiT from 8.26 to 3.63 and of pixel‑space JiT from 7.17 to 3.57—and also enhances guided generation and text‑to‑image benchmarks.
arXiv Machine Learning
1d ago
Unifying Distributional Training for One-Step Visual Generation
arXiv:2609.35763v3 Announce Type: replace Abstract: Distributional training provides collective supervision for one-step visual generation by matching real and generated features in frozen representa...
arXiv Machine Learning
Jun 5
Zero-Flow Encoders
arXiv:2602. 00797v2 Announce Type: replace-cross Abstract: Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions.
arXiv Machine Learning
Jun 26
DanceOPD: On-Policy Generative Field Distillation
arXiv:2606. 27377v1 Announce Type: cross Abstract: Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing.
arXiv Machine Learning
Jul 22
Decafs: Disentangled Conditional adversarial Flows
arXiv:2607. 18755v1 Announce Type: new Abstract: Flow-based models have established state-of-the-art performance in generative modeling across domains, but are hard to interpret due to their complex latent embeddings.