Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models

• URL: http://arxiv.org/abs/2605.23522v1
• Date: Fri, 22 May 2026 11:37:22 GMT
• Title: Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
• Abstract summary: Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators.<n>The sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy.<n>We propose a new sampler that balances effective exploration with stability.
• Score: 56.67321805551389
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replacing the reverse-time Ordinary Differential Equation (ODE) with a Stochastic Differential Equation (SDE). The stochastic sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy, and its design can significantly affect the reward optimization performance. We break down the sampler design into two interdependent components: choosing the right amount of stochastic exploration, and discretizing the resulting SDE faithfully at the small step counts used in RL. To address the first component, we analyze the inherent tension between exploration and stability in denoising and derive an SDE schedule that balances the two. Turning to the discretization challenge, we use a toy example to show that existing samplers can deviate from the flow-matching process, either by introducing excessive discretization noise or by relying on heuristic rules that do not guarantee convergence to the data distribution. To address these issues, we propose Precise, a new stochastic sampler that balances effective exploration with stability. Crucially, Precise keeps the denoising trajectory SDE-consistent through a novel approximation that freezes the clean-latent posterior mean, resolving the excess noise issue in standard samplers. Extensive experiments demonstrate that this formulation leads to significantly faster and more stable reward optimization via reinforcement learning, achieving state-of-the-art alignment scores (e.g., PickScore, HPSv2.1) while requiring 13.1-53.2% less wall-clock training time to match the best in-domain performance of prior samplers.

Related papers

• LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction [59.32834240526981]
  Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE)<n>Existing GRPO methods for flow models replace the Euler-time ODE with aotropic differential equation (SDE) during training.<n>We introduce LC-GRPO, a flow-based GRPO framework with Langevin correction targeting the marginal distribution at the resulting timestep.
  arXiv  Detail & Related papers  (2026-08-06T04:47:57Z)
• Guided Flow Matching for Forward and Inverse PDE Problems with Sparse Observations: Algorithm and Theory [2.148615003900331]
  We present FM4PDE, a flow-matching generative framework that learns the joint distribution of PDE coefficients.<n>Experiments on static and time-dependent benchmark PDEs demonstrate competitive accuracy and faster inference than diffusion-based generative models.
  arXiv  Detail & Related papers  (2026-05-25T07:14:11Z)
• Rethinking Refinement: Correcting Generative Bias without Noise Injection [7.28668585578288]
  Generative models, including diffusion and flow-based models, often exhibit systematic biases that degrade sample quality.<n>We show that effective bias correction can be achieved as a post-hoc procedure, without noise injection or multi-step resampling.
  arXiv  Detail & Related papers  (2026-01-29T02:34:08Z)
• Low-Dimensional Adaptation of Rectified Flow: A New Perspective through the Lens of Diffusion and Stochastic Localization [59.04314685837778]
  Rectified flow (RF) has gained considerable popularity due to its generation efficiency and state-of-the-art performance.<n>In this paper, we investigate the degree to which RF automatically adapts to the intrinsic low dimensionality of the support of the target distribution to accelerate sampling.<n>We show that, using a carefully designed choice of the time-discretization scheme and with sufficiently accurate drift estimates, the RF sampler enjoys an complexity of order $O(k/varepsilon)$.
  arXiv  Detail & Related papers  (2026-01-21T22:09:27Z)
• Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions [23.147474211347856]
  We introduce Neural Flows (NSFs) and their latent variants, which directly learn (latent) SDE transition laws.<n>Experiments on synthetic SDE simulations and on real-world tracking and video data show that NSFs maintain distributional accuracy comparable to numerical approaches.
  arXiv  Detail & Related papers  (2025-10-29T17:59:06Z)
• G$^2$RPO: Granular GRPO for Precise Reward in Flow Models [74.21206048155669]
  We propose a novel Granular-GRPO (G$2$RPO) framework that achieves precise and comprehensive reward assessments of sampling directions.<n>We introduce a Multi-Granularity Advantage Integration module that aggregates advantages computed at multiple diffusion scales.<n>Our G$2$RPO significantly outperforms existing flow-based GRPO baselines.
  arXiv  Detail & Related papers  (2025-10-02T12:57:12Z)
• Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching [6.238027696245818]
  Reinforcement Learning (RL) has emerged as a powerful technique for improving image and video generation in Diffusion and Flow Matching models.<n>Our investigation reveals a significant drawback to this approach: SDE-based sampling introduces pronounced noise artifacts in the generated images.<n>Our proposed method, Coefficients-Preserving Sampling (CPS) eliminates these noise artifacts.
  arXiv  Detail & Related papers  (2025-09-07T07:25:00Z)
• 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)
• Flow-GRPO: Training Flow Matching Models via Online RL [80.62659379624867]
  We propose Flow-GRPO, the first method to integrate online policy reinforcement learning into flow matching models.<n>Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Differential Equation into an equivalent Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original number of inference steps.
  arXiv  Detail & Related papers  (2025-05-08T17:58:45Z)
• Stochastic Optimization with Optimal Importance Sampling [49.484190237840714]
  We propose an iterative-based algorithm that jointly updates the decision and the IS distribution without requiring time-scale separation between the two.<n>Our method achieves the lowest possible variable variance and guarantees global convergence under convexity of the objective and mild assumptions on the IS distribution family.
  arXiv  Detail & Related papers  (2025-04-04T16:10:18Z)

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.