Gradual Fine-Tuning for Flow Matching Models

• URL: http://arxiv.org/abs/2601.22495v1
• Date: Fri, 30 Jan 2026 03:07:47 GMT
• Title: Gradual Fine-Tuning for Flow Matching Models
• Authors: Gudrun Thorkelsdottir, Arindam Banerjee,
• Abstract summary: Gradual Fine-Tuning (GFT) is a principled framework for fine-tuning flow-based generative models.<n>For flows, GFT defines a temperature-controlled sequence of intermediate objectives that smoothly interpolate between the pretrained and target drifts.<n>GFT improves convergence stability and shortens probability paths, resulting in faster inference, while maintaining generation quality comparable to standard fine-tuning.
• Score: 5.549222664526887
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning flow matching models is a central challenge in settings with limited data, evolving distributions, or strict efficiency demands, where unconstrained fine-tuning can erode the accuracy and efficiency gains learned during pretraining. Prior work has produced theoretical guarantees and empirical advances for reward-based fine-tuning formulations, but these methods often impose restrictions on permissible drift structure or training techniques. In this work, we propose Gradual Fine-Tuning (GFT), a principled framework for fine-tuning flow-based generative models when samples from the target distribution are available. For stochastic flows, GFT defines a temperature-controlled sequence of intermediate objectives that smoothly interpolate between the pretrained and target drifts, approaching the true target as the temperature approaches zero. We prove convergence results for both marginal and conditional GFT objectives, enabling the use of suitable (e.g., optimal transport) couplings during GFT while preserving correctness. Empirically, GFT improves convergence stability and shortens probability paths, resulting in faster inference, while maintaining generation quality comparable to standard fine-tuning. Our results position GFT as a theoretically grounded and practically effective alternative for scalable adaptation of flow matching models under distribution shift.

Related papers

• LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models [48.68246945083386]
  Likelihood-Free Policy Optimization (LFPO) is a native framework that maps the concept of vector field flow matching to the discrete token space.<n>LFPO formulates alignment as geometric velocity rectification, which directly optimize denoising logits via contrastive updates.<n>Experiments demonstrate that LFPO not only outperforms state-of-the-art baselines on code and reasoning benchmarks but also accelerates inference by approximately 20% through reduced diffusion steps.
  arXiv  Detail & Related papers  (2026-03-02T07:42:55Z)
• Diverging Flows: Detecting Extrapolations in Conditional Generation [3.1784840992666137]
  Diverging Flows is a novel approach that enables a single model to simultaneously perform conditional generation and native extrapolation detection.<n>It achieves effective detection of extrapolations without compromising predictive fidelity or inference latency.<n>These results establish Diverging Flows as a robust solution for trustworthy flow models, paving the way for reliable deployment in domains such as medicine, robotics, and climate science.
  arXiv  Detail & Related papers  (2026-02-13T16:15:58Z)
• Temporal Pair Consistency for Variance-Reduced Flow Matching [13.328987133593154]
  Temporal Pair Consistency (TPC) is a lightweight variance-reduction principle that couples velocity predictions at paired timesteps along the same probability path.<n>Instantiated within flow matching, TPC improves sample quality and efficiency across CIFAR-10 and ImageNet at multiple resolutions.
  arXiv  Detail & Related papers  (2026-02-04T00:05:21Z)
• Rethinking Test-Time Training: Tilting The Latent Distribution For Few-Shot Source-Free Adaptation [3.5808917363708743]
  We study test-time adaptation of foundation models for few-shot classification under a completely frozen-model regime.<n>We propose arguably the first training-free inference method that adapts predictions to the new task by performing a change of measure over the latent embedding distribution induced by the encoder.
  arXiv  Detail & Related papers  (2026-02-02T18:17:29Z)
• Improving Classifier-Free Guidance of Flow Matching via Manifold Projection [3.6087998976768128]
  We provide a principled interpretation of CFG through the lens of optimization.<n>We reformulate the CFG sampling as a homotopy optimization with manifold constraint.<n>Our proposed methods are training-free and consistently refine generation fidelity, prompt alignment, and robustness to the guidance scale.
  arXiv  Detail & Related papers  (2026-01-29T15:49:31Z)
• Rectified-CFG++ for Flow Based Models [26.896426878221718]
  We present Rectified-C++, an adaptive predictor-corrector guidance that couples the deterministic efficiency of rectified flows with a geometry-aware conditioning rule.<n>Experiments on large-scale text-to-image models (Flux, Stable Diffusion 3/3.5, Lumina) show that Rectified-C++ consistently outperforms standard CFG on benchmark datasets.
  arXiv  Detail & Related papers  (2025-10-09T00:00:47Z)
• Weighted Conditional Flow Matching [26.88652399504886]
  Conditional flow matching (CFM) has emerged as a powerful framework for training continuous normalizing flows.<n>We propose weighted Conditional Flow Matching (W-CFM), a novel approach that modifies the classical CFM loss by weighting each training pair $(x, y)$ with a Gibbs kernel.
  arXiv  Detail & Related papers  (2025-07-29T22:42:51Z)
• 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)
• Adaptive Deadline and Batch Layered Synchronized Federated Learning [66.93447103966439]
  Federated learning (FL) enables collaborative model training across distributed edge devices while preserving data privacy, and typically operates in a round-based synchronous manner.<n>We propose ADEL-FL, a novel framework that jointly optimize per-round deadlines and user-specific batch sizes for layer-wise aggregation.
  arXiv  Detail & Related papers  (2025-05-29T19:59:18Z)
• Visual Generation Without Guidance [54.556375372833685]
  We propose to build visual models that are free from sampling guided.<n>The resulting algorithm, Guidance-Free Training (GFT), matches the performance of CFG while reducing sampling to a single model, halving the cost.
  arXiv  Detail & Related papers  (2025-01-26T06:48:05Z)
• Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching [13.634043135217254]
  We propose Flow Matching-based Posterior Sampling (FMPS) to expand its application scope.<n>This correction term can be reformulated to incorporate a surrogate score function.<n>We show that FMPS achieves superior generation quality compared to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-11-12T08:14:39Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Improving and generalizing flow-based generative models with minibatch optimal transport [90.01613198337833]
  We introduce the generalized conditional flow matching (CFM) technique for continuous normalizing flows (CNFs) CFM features a stable regression objective like that used to train the flow in diffusion models but enjoys the efficient inference of deterministic flow models. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference.
  arXiv  Detail & Related papers  (2023-02-01T14:47:17Z)

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.