D2PO: Optimizing Diffusion Samplers via Dynamic Preference

• URL: http://arxiv.org/abs/2607.06609v1
• Date: Tue, 07 Jul 2026 06:05:42 GMT
• Title: D2PO: Optimizing Diffusion Samplers via Dynamic Preference
• Abstract summary: D2PO is a principled framework for optimizing diffusion sampling policies.<n>We introduce dynamic preferences, where the preferred samples used for alignment progressively improve.<n>Experiments demonstrate that D2PO aligns diffusion samplers with perceptual quality more faithfully.
• Score: 55.530862428116244
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diffusion sampling policies with respect to timestep schedules and classifier-free guidance (CFG) weights. Our work is motivated by a fundamental limitation of existing student-teacher regression frameworks; low-NFE student samplers are trained to mimic high-NFEteachers, often sacrificing high-frequency texture fidelity while preserving coarse global structures, thereby misaligning the sampler with perceptual quality. D2PO addresses this challenge by reformulating sampler optimization as a preference-based alignment problem, leveraging the Direct Preference Optimization (DPO) framework. To make DPO applicable to diffusion samplers, we model the sampling policy as an energy-based model (EBM), transforming preference comparisons into tractable energy differences. We further introduce a novel energy formulation derived directly from the pretrained score network, enabling preference evaluation in perturbed spaces that jointly capture structural consistency and fine-grained details. Moreover, we introduce dynamic preferences, where the preferred samples used for alignment progressively improve as the sampling policies are learned. This self-improving mechanism replaces rigid static teacher supervision with an iterative, preference-guided refinement process, providing progressively stronger alignment signals. Extensive experiments demonstrate that D2PO aligns diffusion samplers with perceptual quality more faithfully, unlocking the full potential of high-quality teachers and consistently outperforming conventional regression-based schedulers under low-NFE constraints.

Related papers

• Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization [85.4863852505905]
  We introduce unsupervised reward optimization of protein language models (PLMs)<n>Our key insight is that task-agnostic rewards, which combine intrinsic model uncertainty with semantic consistency informed by protein representation models, exhibit strong correlation with controllability measures across base models and temperature regimes.<n>Our framework provides a scalable pathway toward controllable biomolecular design in settings where labeled preferences or experimental feedback are scarce or unavailable.
  arXiv  Detail & Related papers  (2026-06-17T11:42:01Z)
• How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics [65.67654005892469]
  We show that proper instance-dependent sampling can yield stronger ranking guarantees, while skewed on-policy sampling can induce excessive concentration under structured preferences.<n>We then analyze iterative alignment dynamics in which the learned policy feeds back into future sampling and reference policies.<n>Our theoretical insights extend to Direct Preference Optimization, indicating the phenomena we captured are common to a broader class of preference-alignment methods.
  arXiv  Detail & Related papers  (2026-02-12T17:11:08Z)
• AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models [54.56296715999545]
  Reinforcement learning from human feedback shows promise for aligning diffusion and flow models.<n>Policy optimization methods such as GRPO suffer from inefficient and static sampling strategies.<n>We propose Adaptive Entropy-Guided Policy Optimization (AEGPO), a novel dual-signal, dual-level adaptive optimization strategy.
  arXiv  Detail & Related papers  (2026-02-06T16:09:50Z)
• Beyond Reward Margin: Rethinking and Resolving Likelihood Displacement in Diffusion Models via Video Generation [6.597818816347323]
  Direct Preference Optimization aims to align generative outputs with human preferences by distinguishing between chosen and rejected samples.<n>A critical limitation of DPO is likelihood displacement, where the probabilities of chosen samples paradoxically decrease during training.<n>We introduce a novel solution named Policy-Guided DPO, combining Adaptive Rejection Scaling (ARS) and Implicit Preference Regularization (IPR)<n>Experiments show that PG-DPO outperforms existing methods in both quantitative metrics and qualitative evaluations.
  arXiv  Detail & Related papers  (2025-11-24T12:37:49Z)
• 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)
• ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning [17.928214942495412]
  ACPO employs a dynamic curriculum that orchestrates a principled transition from a stable, near on-policy exploration phase to an efficient, off-policy exploitation phase.<n>We conduct extensive experiments on a suite of challenging multimodal reasoning benchmarks, including MathVista, LogicVista, and MMMU-Pro.<n>Results demonstrate that ACPO consistently outperforms strong baselines such as DAPO and PAPO, achieving state-of-the-art performance, accelerated convergence, and superior training stability.
  arXiv  Detail & Related papers  (2025-10-01T09:11:27Z)
• Prior-Guided Diffusion Planning for Offline Reinforcement Learning [5.819784482811376]
  Prior Guidance (PG) is a novel guided sampling framework that replaces the standard Gaussian prior of a behavior-cloned diffusion model.<n>We present an efficient training strategy that applies behavior regularization in latent space, and empirically demonstrate that PG outperforms state-the-art diffusion policies and planners across diverse long-horizon offline RL benchmarks.
  arXiv  Detail & Related papers  (2025-05-16T05:39:02Z)
• Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking [50.325021634589596]
  We propose a Tailored Optimization Preference (TailorPO) framework for aligning diffusion models with human preference.<n>Our approach directly ranks intermediate noisy samples based on their step-wise reward, and effectively resolves the gradient direction issues.<n> Experimental results demonstrate that our method significantly improves the model's ability to generate aesthetically pleasing and human-preferred images.
  arXiv  Detail & Related papers  (2025-02-01T16:08:43Z)

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.