PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models

• URL: http://arxiv.org/abs/2606.22958v1
• Date: Mon, 22 Jun 2026 07:36:36 GMT
• Title: PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models
• Abstract summary: Inference-time alignment of pretrained text-to-image models is typically performed along a single control axis.<n>We propose PG-MAP, a training-free framework that formulates inference-time alignment as a trajectory-level Gibbs-MAP / proximal energy optimization.
• Score: 0.8594140167290097
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inference-time alignment of pretrained text-to-image models is typically performed along a single control axis, such as classifier-free guidance, attention editing, or reward-based latent perturbations. This limitation prevents modeling joint dependencies between conditioning and latent variables and hinders transfer across generative transports. We propose PG-MAP, a training-free framework that formulates inference-time alignment as a trajectory-level Gibbs-MAP / proximal energy optimization over the conditioning $c$ and latent state $z_t$ via a forward-consistency coupling, optionally guided by a frozen preference reward. This joint formulation enables coordinated updates across modalities while remaining compatible with both diffusion and flow-matching models through transport-specific adaptations. Across diffusion backbones (SD~1.5, SDXL), PG-MAP consistently improves alignment metrics such as PickScore and Aesthetic, and can be effectively combined with tuned classifier-free guidance to achieve the strongest overall performance. On flow-matching models (SD3.5-medium), the framework reduces to a latent-only variant, achieving $\mathbf{91.9\%}$ PickScore and $75.7\%$ HPS win rates against a static baseline, with controlled experiments ruling out noise-related artifacts. Human evaluations further confirm consistent preference over strong baselines, including tuned CFG and compute-matched universal guidance. Finally, an oracle-routing analysis shows that the relative importance of conditioning and latent optimization depends on prompt types, surfacing further headroom that a per-prompt selector could exploit.

Related papers

• Information-Theoretic Classifier-Free Guidance with Adaptive Schedule Optimization [15.35957804795103]
  Diffusion models have achieved strong performance in image, text-to-image, and video generation.<n>We propose an information-theoretic framework for CFG schedule optimization.<n>On ImageNet-512 with EDM-XXL and COCO with SD-XL, the learned schedules achieve competitive or improved trade-offs over constant guidance.
  arXiv  Detail & Related papers  (2026-06-23T00:04:04Z)
• MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation [65.068801413044]
  Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams.<n>We introduce MoASE, a mixture-of-experts that disentangles domain-agnostic structure from domain-specific texture.
  arXiv  Detail & Related papers  (2026-05-18T01:52:12Z)
• Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers [12.948398661304184]
  Diffusion-APO is a trajectory-aware algorithm for aligning video diffusion models with human intent.<n>We introduce a unified and modular RLHF framework that integrates online ranking, half-online anchoring, offline refinement, and distillation-aware drift correction.<n>We demonstrate that Diffusion-APO consistently outperforms standard baselines in visual quality and instruction following.
  arXiv  Detail & Related papers  (2026-05-08T09:37:46Z)
• Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline [7.967038299436285]
  We propose a deterministic adjoint matching framework that formulates human preference alignment for flow-based generative models.<n>Building on this perspective, we introduce a truncated adjoint scheme that focuses on the terminal portion of the trajectory.<n>We further generalize the framework beyond standard KL-based regularization, allowing more flexible trade-offs between alignment strength and distributional preservation.
  arXiv  Detail & Related papers  (2026-05-07T17:12:47Z)
• 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)
• Preconditioned Score and Flow Matching [15.378063594292955]
  We show that the covariance $_t$ of $p_t$ governs optimization bias.<n>We propose reversible, label-conditional emphpreconditioning maps that reshape the geometry of $p_t$.<n>We show that preconditioning consistently yields better-trained models by avoiding suboptimal plateaus.
  arXiv  Detail & Related papers  (2026-03-02T19:09:15Z)
• Adaptive Linear Path Model-Based Diffusion [52.84663832658799]
  We introduce Linear Path Model-Based Diffusion (LP-MBD), which replaces the variance-preserving schedule with a flow-matching linear probability path.<n>We also propose Adaptive LP-MBD (ALP-MBD), which leverages reinforcement learning to adjust diffusion steps and noise levels according to task complexity and environmental conditions.
  arXiv  Detail & Related papers  (2026-02-02T21:33:03Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Improving Classifier-Free Guidance of Flow Matching via Manifold Projection [3.6087998976768128]
  We provide a principled interpretation of CFG through the lens of optimization.<n>We reformulate the CFG sampling as a homotopy optimization with manifold constraint.<n>Our proposed methods are training-free and consistently refine generation fidelity, prompt alignment, and robustness to the guidance scale.
  arXiv  Detail & Related papers  (2026-01-29T15:49:31Z)
• Rectified-CFG++ for Flow Based Models [26.896426878221718]
  We present Rectified-C++, an adaptive predictor-corrector guidance that couples the deterministic efficiency of rectified flows with a geometry-aware conditioning rule.<n>Experiments on large-scale text-to-image models (Flux, Stable Diffusion 3/3.5, Lumina) show that Rectified-C++ consistently outperforms standard CFG on benchmark datasets.
  arXiv  Detail & Related papers  (2025-10-09T00:00:47Z)
• Adaptive Deadline and Batch Layered Synchronized Federated Learning [66.93447103966439]
  Federated learning (FL) enables collaborative model training across distributed edge devices while preserving data privacy, and typically operates in a round-based synchronous manner.<n>We propose ADEL-FL, a novel framework that jointly optimize per-round deadlines and user-specific batch sizes for layer-wise aggregation.
  arXiv  Detail & Related papers  (2025-05-29T19:59:18Z)
• Comparing Probability Distributions with Conditional Transport [63.11403041984197]
  We propose conditional transport (CT) as a new divergence and approximate it with the amortized CT (ACT) cost. ACT amortizes the computation of its conditional transport plans and comes with unbiased sample gradients that are straightforward to compute. On a wide variety of benchmark datasets generative modeling, substituting the default statistical distance of an existing generative adversarial network with ACT is shown to consistently improve the performance.
  arXiv  Detail & Related papers  (2020-12-28T05:14:22Z)

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.