Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning

• URL: http://arxiv.org/abs/2606.22394v1
• Date: Sun, 21 Jun 2026 08:49:50 GMT
• Title: Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
• Abstract summary: consistency distillation has significantly accelerated the inference of diffusion models.<n>We propose Curvature-Adaptive Consistency Flow Matching to address the limitations of static sampling.<n>Our approach achieves new state-of-the-art results on large-scale models such as FLUX and SDXL.
• Score: 8.422673935994451
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Consistency distillation has significantly accelerated the inference of diffusion models. In this work, we reveal an intriguing asymmetry: while Logit-Normal sampling priors are highly efficacious for standard iterative generation, consistency distillation exhibits a distinctly different difficulty profile (e.g., U-shaped). We identify that the primary optimization bottlenecks reside at the boundary stages (initialization or final refinement) rather than the intermediate steps. To address the limitations of static sampling in accommodating evolving learning requirements, we propose Curvature-Adaptive Consistency Flow Matching (CACFM). By formulating distillation as a dynamic decision process, CACFM employs a lightweight Reinforcement Learning agent to actively probe Probability Flow ODE trajectories, automatically constructing an efficiency-oriented curriculum that prioritizes critical regions without manual scheduling. Integrated with a novel Flow Distribution Matching Distillation (DMD) objective, our approach achieves new state-of-the-art results on large-scale models such as FLUX and SDXL. It effectively mitigates structural deformities and preserves high-frequency details in extreme few-step regimes, achieving unprecedented visual fidelity.

Related papers

• Perceptual Flow Matching for Few-Step Generative Modeling [64.26537634881244]
  Perceptual Flow Matching is a framework for few-step generation in flow-matching models.<n>We show that PFM produces high-quality few-step generators when supervised in an appropriate representation space.
  arXiv  Detail & Related papers  (2026-07-03T17:55:01Z)
• Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models [34.59515048908997]
  Mean Flow Distillation (MFD) is a novel distillation framework tailored for flow matching models.<n>MFD acts as a temporal low-pass filter, effectively suppressing the high-frequency optimization noise.<n>We prove the Mean Flow Matching Theorem, establishing that matching expected average velocities is sufficient for strict distribution alignment.
  arXiv  Detail & Related papers  (2026-06-09T17:39:19Z)
• InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching [1.974921946982281]
  Flow Matching (FM) has emerged as a leading approach for high-fidelity visual generation.<n>FM models are sensitive to dataset biases, which cause severe semantic degradation when generating out-of-distribution or minority-class samples.<n>We introduce InjectFlow, a novel, training-free method by injecting semantics during the initial velocity field.
  arXiv  Detail & Related papers  (2026-03-19T11:07:14Z)
• Active Flow Matching [14.437387789022354]
  Active Flow Matching (AFM) reformulates variational objectives to operate on conditional endpoint distributions along the flow.<n>We derive forward and reverse Kullback-Leibler (KL) variants using self-normalised importance sampling.
  arXiv  Detail & Related papers  (2026-03-01T02:50:07Z)
• Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps [4.397130429878499]
  Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by high sampling costs.<n>We propose SDM, a principled framework that aligns the numerical solver with the intrinsic properties of the diffusion trajectory.<n>By analyzing the ODE dynamics, we show that efficient low-order solvers suffice in early high-noise stages while higher-order solvers can be progressively deployed to handle the increasing non-linearity of later stages.
  arXiv  Detail & Related papers  (2026-02-13T05:02:07Z)
• Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamics [49.242224984144904]
  We propose Euphonium, a novel framework that steers generation via process reward gradient guided dynamics.<n>Our key insight is to formulate the sampling process as a theoretically principled algorithm that explicitly incorporates the gradient of a Process Reward Model.<n>We derive a distillation objective that internalizes the guidance signal into the flow network, eliminating inference-time dependency on the reward model.
  arXiv  Detail & Related papers  (2026-02-04T08:59:57Z)
• Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling [0.07646713951724012]
  One-step generative modeling seeks to generate high-quality data samples in a single function evaluation.<n>In this work, we introduce Modular MeanFlow, a flexible and theoretically grounded approach for learning time-averaged velocity fields.
  arXiv  Detail & Related papers  (2025-08-24T16:00:08Z)
• RAAG: Ratio Aware Adaptive Guidance [9.525432706814675]
  Flow-based generative models have achieved remarkable progress.<n>Applying a strong, fixed guidance scale throughout inference is poorly suited for the rapid, few-step sampling required by modern applications.<n>We propose a simple, theoretically grounded, adaptive guidance schedule that automatically dampens the guidance scale at early steps based on the evolving ratio.
  arXiv  Detail & Related papers  (2025-08-05T13:41:05Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Divergence Minimization Preference Optimization for Diffusion Model Alignment [66.31417479052774]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>DMPO can consistently outperform or match existing techniques across different base models and test sets.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation [82.39763984380625]
  We introduce denoising score distillation (DSD), a surprisingly effective and novel approach for training high-quality generative models from low-quality data.<n>DSD pretrains a diffusion model exclusively on noisy, corrupted samples and then distills it into a one-step generator capable of producing refined, clean outputs.
  arXiv  Detail & Related papers  (2025-03-10T17:44:46Z)
• Adding Additional Control to One-Step Diffusion with Joint Distribution Matching [58.37264951734603]
  JDM is a novel approach that minimizes the reverse KL divergence between image-condition joint distributions.<n>By deriving a tractable upper bound, JDM decouples fidelity learning from condition learning.<n>This asymmetric distillation scheme enables our one-step student to handle controls unknown to the teacher model.
  arXiv  Detail & Related papers  (2025-03-09T15:06:50Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)

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.