DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models

• URL: http://arxiv.org/abs/2509.21655v1
• Date: Thu, 25 Sep 2025 22:21:59 GMT
• Title: DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models
• Abstract summary: We study inference-time scaling for diffusion models, where the goal is to adapt a pre-trained model to new target distributions without retraining.<n>We introduce DriftLite, a lightweight, training-free particle-based approach that steers the inference dynamics on the fly with provably optimal stability.
• Score: 22.823183347642132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study inference-time scaling for diffusion models, where the goal is to adapt a pre-trained model to new target distributions without retraining. Existing guidance-based methods are simple but introduce bias, while particle-based corrections suffer from weight degeneracy and high computational cost. We introduce DriftLite, a lightweight, training-free particle-based approach that steers the inference dynamics on the fly with provably optimal stability control. DriftLite exploits a previously unexplored degree of freedom in the Fokker-Planck equation between the drift and particle potential, and yields two practical instantiations: Variance- and Energy-Controlling Guidance (VCG/ECG) for approximating the optimal drift with minimal overhead. Across Gaussian mixture models, particle systems, and large-scale protein-ligand co-folding problems, DriftLite consistently reduces variance and improves sample quality over pure guidance and sequential Monte Carlo baselines. These results highlight a principled, efficient route toward scalable inference-time adaptation of diffusion models.

Related papers

• Scaling Reinforcement Learning for Diffusion Models via Velocity Matching [66.34541945134916]
  RewardBench fine-tuning is an important tool for adapting diffusion models to human preferences and task-specific objectives.<n>Unlike autoregressive models, diffusion models do not provide tractable likelihoods for generated samples.<n>We propose reward-based velocity matching (RVM), a simple trajectory-free update that acts directly on the velocity field.
  arXiv  Detail & Related papers  (2026-08-24T17:13:43Z)
• Inference-Time Alignment of Diffusion Models via Trust-Region Iterative Twisted Sequential Monte Carlo [15.105260031413698]
  We study inference-time alignment for diffusion-based generative models.<n>We propose a trust-region framework for learning twisting functions in SMC-based inference-time alignment.
  arXiv  Detail & Related papers  (2026-05-24T15:08:52Z)
• Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization [69.03519018775779]
  Group Relative Policy Optimization is essential for aligning video diffusion models with human preferences.<n>Existing efficiency methods compromise optimization, exhibiting severe instability and failing to reach full trajectory performance.<n>We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets.
  arXiv  Detail & Related papers  (2026-05-15T14:13:39Z)
• Curvature-Guided LoRA: Steering in the pretrained NTK subspace [60.35296431630704]
  We introduce the prediction alignment problem, aiming to match the predictor obtained via PEFT to that of full fine-tuning at the level of outputs.<n>We show that this objective naturally leads to a curvature-aware, second-order formulation, where optimal low-rank updates correspond to a Newton-like, curvature-whitened gradient.<n>Based on this insight, we propose Curvature-Guided LoRA (CG-LoRA), which selects and scales adaptation directions using local curvature information.
  arXiv  Detail & Related papers  (2026-03-31T14:46:39Z)
• Diffusion Controller: Framework, Algorithms and Parameterization [54.82539154511621]
  We present a unified control-theoretic view that casts reverse diffusion sampling as state-only control within (generalized) linearly-solvable Markov Decision Processes.<n>Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost.<n>Experiments on Stable Diffusion v1.4 show consistent gains in preference-alignment win rates and improved quality-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-03-07T01:49:59Z)
• DiffusionNFT: Online Diffusion Reinforcement with Forward Process [99.94852379720153]
  Diffusion Negative-aware FineTuning (DiffusionNFT) is a new online RL paradigm that optimize diffusion models directly on the forward process via flow matching.<n>DiffusionNFT is up to $25times$ more efficient than FlowGRPO in head-to-head comparisons, while being CFG-free.
  arXiv  Detail & Related papers  (2025-09-19T16:09:33Z)
• A-FloPS: Accelerating Diffusion Sampling with Adaptive Flow Path Sampler [21.134678093577193]
  A-FloPS is a principled, training-free framework for flow-based generative models.<n>We show that A-FloPS consistently outperforms state-of-the-art training-free samplers in both sample quality and efficiency.<n>With as few as $5$ function evaluations, A-FloPS achieves substantially lower FID and generates sharper, more coherent images.
  arXiv  Detail & Related papers  (2025-08-22T13:28:16Z)
• 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)
• Training-Free Stein Diffusion Guidance: Posterior Correction for Sampling Beyond High-Density Regions [46.59494117137471]
  Training free diffusion guidance provides a flexible way to leverage off-the-shelf classifiers without additional training.<n>We introduce Stein Diffusion Guidance (SDG), a novel training-free framework grounded in a surrogate SOC objective.<n>Experiments on molecular low-density sampling tasks suggest that SDG consistently surpasses standard training-free guidance methods.
  arXiv  Detail & Related papers  (2025-07-07T21:14:27Z)
• SCoT: Straight Consistent Trajectory for Pre-Trained Diffusion Model Distillations [31.60548236936739]
  We propose a Straight Consistent Trajectory(SCoT) model for pre-trained diffusion models.<n>SCoT enjoys the benefits of both approaches for fast sampling, producing trajectories with consistent and straight properties simultaneously.
  arXiv  Detail & Related papers  (2025-02-24T08:57:19Z)
• Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening [56.99266993852532]
  Diffusion-Sharpening is a fine-tuning approach that enhances downstream alignment by optimizing sampling trajectories.<n>Our method demonstrates superior training efficiency with faster convergence, and best inference efficiency without requiring additional NFEs.
  arXiv  Detail & Related papers  (2025-02-17T18:57:26Z)
• Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation [49.49868273653921]
  Diffusion models are promising for joint trajectory prediction and controllable generation in autonomous driving. We introduce Optimal Gaussian Diffusion (OGD) and Estimated Clean Manifold (ECM) Guidance. Our methodology streamlines the generative process, enabling practical applications with reduced computational overhead.
  arXiv  Detail & Related papers  (2024-08-01T17:59:59Z)
• Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review [63.31328039424469]
  This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. We explain the application of various RL algorithms, including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
  arXiv  Detail & Related papers  (2024-07-18T17:35:32Z)
• Learning to Approximate Particle Smoothing Trajectories via Diffusion Generative Models [16.196738720721417]
  Learning systems from sparse observations is critical in numerous fields, including biology, finance, and physics. We introduce a method that integrates conditional particle filtering with ancestral sampling and diffusion models. We demonstrate the approach in time-series generation and tasks, including vehicle tracking and single-cell RNA sequencing data.
  arXiv  Detail & Related papers  (2024-06-01T21:54:01Z)
• Unmasking Bias in Diffusion Model Training [40.90066994983719]
  Denoising diffusion models have emerged as a dominant approach for image generation. They still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be largely attributed to bias and suboptimality inherent in the default training paradigm.
  arXiv  Detail & Related papers  (2023-10-12T16:04:41Z)
• Physics-informed CoKriging model of a redox flow battery [68.8204255655161]
  Redox flow batteries (RFBs) offer the capability to store large amounts of energy cheaply and efficiently. There is a need for fast and accurate models of the charge-discharge curve of a RFB to potentially improve the battery capacity and performance. We develop a multifidelity model for predicting the charge-discharge curve of a RFB.
  arXiv  Detail & Related papers  (2021-06-17T00:49:55Z)
• Embedded training of neural-network sub-grid-scale turbulence models [0.0]
  The weights of a deep neural network model are optimized in conjunction with the governing flow equations to provide a model for sub-grid-scale stresses. The training is by a gradient descent method, which uses the adjoint Navier-Stokes equations to provide the end-to-end sensitivities of the model weights to the velocity fields.
  arXiv  Detail & Related papers  (2021-05-03T17:28:39Z)

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.