Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching

• URL: http://arxiv.org/abs/2602.05951v1
• Date: Thu, 05 Feb 2026 18:08:20 GMT
• Title: Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
• Authors: Junwan Kim, Jiho Park, Seonghu Jeon, Seungryong Kim,
• Abstract summary: Flow matching has emerged as a promising alternative to diffusion-based generative models.<n>We show that principled design of the source distribution is not only feasible but also beneficial at the scale of modern text-to-image systems.
• Score: 34.811045663987805
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing arbitrary source distributions, most existing approaches rely on a standard Gaussian distribution, a choice inherited from diffusion models, and rarely consider the source distribution itself as an optimization target in such settings. In this work, we show that principled design of the source distribution is not only feasible but also beneficial at the scale of modern text-to-image systems. Specifically, we propose learning a condition-dependent source distribution under flow matching objective that better exploit rich conditioning signals. We identify key failure modes that arise when directly incorporating conditioning into the source, including distributional collapse and instability, and show that appropriate variance regularization and directional alignment between source and target are critical for stable and effective learning. We further analyze how the choice of target representation space impacts flow matching with structured sources, revealing regimes in which such designs are most effective. Extensive experiments across multiple text-to-image benchmarks demonstrate consistent and robust improvements, including up to a 3x faster convergence in FID, highlighting the practical benefits of a principled source distribution design for conditional flow matching.

Related papers

• Is There a Better Source Distribution than Gaussian? Exploring Source Distributions for Image Flow Matching [27.47409979324549]
  Flow matching has emerged as a powerful generative modeling approach with flexible choices of source distribution.<n>We propose a novel 2D simulation that captures high-dimensional geometric properties in an interpretable 2D setting.<n>We propose a framework that combines norm-aligned training with directionally-pruned sampling.
  arXiv  Detail & Related papers  (2025-12-20T02:44:54Z)
• Distribution Matching Variational AutoEncoder [24.58582338610613]
  Existing approaches such as VAEs implicitly constrain the latent space without explicitly shaping its distribution.<n>We introduce textbfDistribution-Matching VAE (textbfDMVAE), which explicitly aligns the encoder's latent distribution with an arbitrary reference distribution.<n>Our results suggest that choosing a suitable latent distribution structure (achieved via distribution-level alignment) is key to bridging the gap between easy-to-model latents and high-fidelity image synthesis.
  arXiv  Detail & Related papers  (2025-12-08T17:59:47Z)
• Conformal Prediction for Multi-Source Detection on a Network [59.17729745907474]
  We study the multi-source detection problem.<n>Given snapshot observations of node infection status on a graph, estimate the set of source nodes that initiated the propagation.<n>We propose a novel conformal prediction framework that provides statistically valid recall guarantees for source set detection.
  arXiv  Detail & Related papers  (2025-11-12T01:09:56Z)
• Source-Guided Flow Matching [7.888172595458005]
  We propose the Source-Guided Flow Matching framework.<n>It modifies the source distribution directly while keeping the pre-trained vector field intact.<n>This reduces the guidance problem to a well-defined problem of sampling from the source distribution.
  arXiv  Detail & Related papers  (2025-08-20T15:56:25Z)
• Aligning Latent Spaces with Flow Priors [72.24305287508474]
  This paper presents a novel framework for aligning learnable latent spaces to arbitrary target distributions by leveraging flow-based generative models as priors.<n> Notably, the proposed method eliminates computationally expensive likelihood evaluations and avoids ODE solving during optimization.
  arXiv  Detail & Related papers  (2025-06-05T16:59:53Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach [53.32564762183639]
  We introduce a novel, unified theoretical framework for watermarking Large Language Models (LLMs)<n>Our approach aims to maximize detection performance while maintaining control over the worst-case false positive rate (FPR) and distortion on text quality.<n>We propose a distortion-free, distribution-adaptive watermarking algorithm (DAWA) that leverages a surrogate model for model-agnosticism and efficiency.
  arXiv  Detail & Related papers  (2024-10-03T18:28:10Z)
• Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
  In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
  arXiv  Detail & Related papers  (2024-01-29T02:08:40Z)
• The Score-Difference Flow for Implicit Generative Modeling [1.1929584800629673]
  Implicit generative modeling aims to produce samples of synthetic data matching a target data distribution.<n>Recent work has approached the IGM problem from the perspective of pushing synthetic source data toward the target distribution.<n>We present the score difference between arbitrary target and source distributions as a flow that optimally reduces the Kullback-Leibler divergence between them.
  arXiv  Detail & Related papers  (2023-04-25T15:21:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.