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.
Compositional Generative Modeling from Decentralized Data
arXiv:2606. 10153v1 Announce Type: new Abstract: Learning the compositional nature of the physical world requires joint observation of interacting factors.
Related stories
arXiv AI
Jun 16
Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environments
arXiv:2505. 19699v2 Announce Type: replace-cross Abstract: Federated Learning (FL) is a decentralized machine learning paradigm that enables clients to collaboratively train models while preserving data privacy.
arXiv AI
Jun 12
Decentralized Autoregressive Generation
arXiv:2601. 03184v3 Announce Type: replace-cross Abstract: The decentralization of autoregressive generation has attracted considerable attention in recent years as a solution to scaling bottlenecks.
arXiv Machine Learning
Jun 30
Simplifying Flow Matching Transformations with Low-Rank Mixture Models
arXiv:2606. 29724v1 Announce Type: new Abstract: Normalizing flows are powerful generative models that learn an invertible mapping between complex data distributions and simple latent distributions, typically a standard normal density.
arXiv Machine Learning
Jul 28
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.
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.
Hugging Face Trending Papers
Jun 29
Simplifying Flow Matching Transformations with Low-Rank Mixture Models
Normalizing flows are powerful generative models that learn an invertible mapping between complex data distributions and simple latent distributions, typically a standard normal density. However, this choice of latent density can impose unnecessary complexity on the learned flow transformation due to the topological mismatch between the latent and data densities, leading to slower training and suboptimal performance.
arXiv Computer Vision
Aug 26
Representation Learning in Diffusion and Flow-based Model: An Application Aspect
The article surveys how diffusion and flow-based generative models learn rich visual representations and how these representations can be used to improve generation and other perception tasks. It introduces a three-tier framework that categorizes work into improving generative quality via representation learning, extracting representations for perception, and developing unified applications. The survey covers downstream tasks such as image classification, dense prediction, instance-level perception, and annotation-scarce scenarios, offering a taxonomy and highlighting future research directions.
Hugging Face Trending Papers
Aug 25
Representation Learning in Diffusion and Flow-based Model: An Application Aspect
Diffusion models and flow-based models have recently become the dominant paradigms in generative modeling, largely due to their ability to learn rich, multi-level visual representations through large-...
arXiv AI
4d ago
What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectives
arXiv:2510.03075v4 Announce Type: replace-cross Abstract: Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models....
arXiv Machine Learning
Jul 14
From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
arXiv:2607. 11758v1 Announce Type: new Abstract: Discrete diffusion models offer a powerful framework for solving complex reasoning tasks, particularly through compositional generation, which combines multiple pre-trained experts to generalize beyond their individual training data.
arXiv AI
Aug 11
Compositional Cross-Modality Translation via Whole-Volume Multitask Latent Flow Matching
arXiv:2608. 08135v1 Announce Type: cross Abstract: Cross-modality medical image translation can reduce the burden of multi-modal acquisitions, yet the field remains constrained by two coupled limitations: methods operate on 2D slices or 3D patches rather than whole volumes, and train a separate model for each translation task.