DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling

• URL: http://arxiv.org/abs/2603.11607v1
• Date: Thu, 12 Mar 2026 07:01:44 GMT
• Title: DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling
• Abstract summary: Dynamic Gradient Weighting (DyWeight) is a lightweight, learning-based multi-step solver.<n>DyWeight learns unconstrained time-varying parameters that adaptively aggregate historical gradients.<n>Experiments on CIFAR-10, FFHQ, AFHQv2, ImageNet64, LSUN-Bedroom, Stable Diffusion and FLUX.1-dev demonstrate that DyWeight achieves superior visual fidelity and stability.
• Score: 18.524470249911232
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion Models (DMs) have achieved state-of-the-art generative performance across multiple modalities, yet their sampling process remains prohibitively slow due to the need for hundreds of function evaluations. Recent progress in multi-step ODE solvers has greatly improved efficiency by reusing historical gradients, but existing methods rely on handcrafted coefficients that fail to adapt to the non-stationary dynamics of diffusion sampling. To address this limitation, we propose Dynamic Gradient Weighting (DyWeight), a lightweight, learning-based multi-step solver that introduces a streamlined implicit coupling paradigm. By relaxing classical numerical constraints, DyWeight learns unconstrained time-varying parameters that adaptively aggregate historical gradients while intrinsically scaling the effective step size. This implicit time calibration accurately aligns the solver's numerical trajectory with the model's internal denoising dynamics under large integration steps, avoiding complex decoupled parameterizations and optimizations. Extensive experiments on CIFAR-10, FFHQ, AFHQv2, ImageNet64, LSUN-Bedroom, Stable Diffusion and FLUX.1-dev demonstrate that DyWeight achieves superior visual fidelity and stability with significantly fewer function evaluations, establishing a new state-of-the-art among efficient diffusion solvers. Code is available at https://github.com/Westlake-AGI-Lab/DyWeight

Related papers

• NSFlow: End-to-End Differentiable Neuro-Symbolic Optical Flow for Visual Odometry [17.880222753550733]
  Sparse optical flow provides stable inter-frame correspondence in Visual Odometry (VO) and Visual-Inertial Odometry (VIO)<n>Modern regression-based learning methods, while more robust in complex scenes, are often computationally heavy and lack explicit geometric consistency.<n>We propose a hybrid neuro-symbolic framework that combines the strengths of both paradigms.
  arXiv  Detail & Related papers  (2026-09-05T13:09:10Z)
• 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)
• LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution [52.627063566555194]
  We introduce LSGQuant, a layer-sensitivity guided quantizing approach for one-step diffusion-based real-world VSR.<n>Our method incorporates a Dynamic Range Adaptive Quantizer (DRAQ) to fit video token activations.<n>Our method has nearly performance to origin model with full-precision and significantly exceeds existing quantization techniques.
  arXiv  Detail & Related papers  (2026-02-03T06:53:19Z)
• Parallel Diffusion Solver via Residual Dirichlet Policy Optimization [88.7827307535107]
  Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature.<n>Existing solver-based acceleration methods often face significant image quality degradation under a low-dimensional budget.<n>We propose the Ensemble Parallel Direction solver (dubbed as EPD-EPr), a novel ODE solver that mitigates these errors by incorporating multiple gradient parallel evaluations in each step.
  arXiv  Detail & Related papers  (2025-12-28T05:48:55Z)
• Towards Fast Coarse-graining and Equation Discovery with Foundation Inference Models [6.403678133359229]
  latent dynamics in high-dimensional recordings are often characterized by a much smaller set of effective variables.<n>Most machine learning approaches tackle these tasks jointly by training autoencoders together with models that enforce dynamical consistency.<n>We propose to decouple the two problems by leveraging the recently introduced Foundation Inference Models (FIMs)<n>A proof of concept on a double-well system with semicircle diffusion, embedded into synthetic video data, illustrates the potential of this approach for fast and reusable coarse-graining pipelines.
  arXiv  Detail & Related papers  (2025-10-14T15:17:23Z)
• Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models [53.087070073434845]
  Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature.<n>Existing solver-based acceleration methods often face image quality degradation under a low-latency budget.<n>We propose the Ensemble Parallel Direction solver (dubbed as ours), a novel ODE solver that mitigates truncation errors by incorporating multiple parallel gradient evaluations in each ODE step.
  arXiv  Detail & Related papers  (2025-07-20T03:08:06Z)
• Implicit Neural Differential Model for Spatiotemporal Dynamics [5.1854032131971195]
  We introduce Im-PiNDiff, a novel implicit physics-integrated neural differentiable solver for stabletemporal dynamics.<n>Inspired by deep equilibrium models, Im-PiNDiff advances the state using implicit fixed-point layers, enabling robust long-term simulation.<n>Im-PiNDiff achieves superior predictive performance, enhanced numerical stability, and substantial reductions in memory and cost.
  arXiv  Detail & Related papers  (2025-04-03T04:07:18Z)
• Taming Flow Matching with Unbalanced Optimal Transport into Fast Pansharpening [10.23957420290553]
  We propose the Optimal Transport Flow Matching framework to achieve one-step, high-quality pansharpening.<n>The OTFM framework enables simulation-free training and single-step inference while maintaining strict adherence to pansharpening constraints.
  arXiv  Detail & Related papers  (2025-03-19T08:10:49Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• Diffusion-Generative Multi-Fidelity Learning for Physical Simulation [24.723536390322582]
  We develop a diffusion-generative multi-fidelity learning method based on differential equations (SDE), where the generation is a continuous denoising process. By conditioning on additional inputs (temporal or spacial variables), our model can efficiently learn and predict multi-dimensional solution arrays.
  arXiv  Detail & Related papers  (2023-11-09T18:59:05Z)
• Value function estimation using conditional diffusion models for control [62.27184818047923]
  We propose a simple algorithm called Diffused Value Function (DVF) It learns a joint multi-step model of the environment-robot interaction dynamics using a diffusion model. We show how DVF can be used to efficiently capture the state visitation measure for multiple controllers.
  arXiv  Detail & Related papers  (2023-06-09T18:40:55Z)
• Hessian-Free High-Resolution Nesterov Acceleration for Sampling [55.498092486970364]
  Nesterov's Accelerated Gradient (NAG) for optimization has better performance than its continuous time limit (noiseless kinetic Langevin) when a finite step-size is employed. This work explores the sampling counterpart of this phenonemon and proposes a diffusion process, whose discretizations can yield accelerated gradient-based MCMC methods.
  arXiv  Detail & Related papers  (2020-06-16T15:07:37Z)

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.