DRM: Diffusion-based Reward Model With Step-wise Guidance

• URL: http://arxiv.org/abs/2605.25661v1
• Date: Mon, 25 May 2026 10:11:32 GMT
• Title: DRM: Diffusion-based Reward Model With Step-wise Guidance
• Abstract summary: Diffusion-based Reward Model (DRM) is a novel paradigm that use the pre-trained diffusion model as a powerful evaluative backbone.<n>We propose Step-wise GRPO, a reinforcement learning algorithm that provides dense, per-step rewards to resolve the imprecise credit assignment problem.
• Score: 6.839893415984142
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual qualities-such as aesthetics, composition, and visual harmony. In this work, we argue that a model capable of high-fidelity generation must possess a profound understanding of these visual attributes. Based on this insight, we introduce the Diffusion-based Reward Model (DRM), a novel paradigm that use the pre-trained diffusion model as a powerful evaluative backbone. A key advantage of the DRM is its unique ability to assess not only the final image but also the noisy intermediate latents at any stage of the generative process. We leverage this step-wise evaluative capacity in two ways. First, we propose Step-wise GRPO, a reinforcement learning algorithm that provides dense, per-step rewards to resolve the imprecise credit assignment problem in GRPO algorithm, leading to more stable and effective alignment. Second, we introduce Step-wise Sampling, a novel inference strategy that employs the DRM as a dynamic guide to evaluate multiple generation paths at each step, steering the process towards higher-quality outcomes. Extensive experiments confirm that our approach significantly enhances the final quality of generated images. Code: https://github.com/jjaxonx/DRM.

Related papers

• Plug, Play, and Fortify: A Low-Cost Module for Robust Multimodal Image Understanding Models [6.350443894942629]
  Multimodal Weight Allocation Module (MWAM) is a plug-and-play component that dynamically re-balances the contribution of each branch during training.<n>MWAM delivers consistent performance gains across a wide range of tasks and modality combinations.
  arXiv  Detail & Related papers  (2026-02-26T05:51:41Z)
• Learning Ordinal Probabilistic Reward from Preferences [25.069054134899744]
  We introduce a novel reward modeling paradigm: Probabilistic Reward Model (PRM)<n>Instead of modeling reward as a deterministic scalar, our approach treats it as a random variable, learning a full probability distribution for the quality of each response.<n>Building on OPRM, we propose a data-efficient training strategy called Region Flooding Tuning (RgFT)
  arXiv  Detail & Related papers  (2026-02-13T06:43:02Z)
• Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models [23.128973540926552]
  Endogenous Reprompting transforms the model's understanding into an explicit generative reasoning step.<n>We show that SEER consistently outperforms state-of-the-art baselines in evaluation accuracy, reprompting efficiency, and generation quality.
  arXiv  Detail & Related papers  (2026-01-28T06:54:36Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models [53.19726629537694]
  Post-training alignment of video generation models with human preferences is a critical goal.<n>Current data collection paradigms, reliant on in-prompt pairwise annotations, suffer from labeling noise.<n>We propose SoliReward, a systematic framework for video RM training.
  arXiv  Detail & Related papers  (2025-12-17T14:28:23Z)
• Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models [40.82263997290613]
  We introduce MaskGRPO, the first viable approach to enable scalable multimodal reinforcement learning in discrete diffusion.<n>MaskGRPO brings more stable and efficient updates, leading to stronger reasoning performance and better generation quality.
  arXiv  Detail & Related papers  (2025-10-03T10:36:24Z)
• How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models [57.42800112251644]
  We propose Step AG, which is a simple, universally applicable adaptive guidance strategy.<n>Our evaluations focus on both image quality and image-text alignment.
  arXiv  Detail & Related papers  (2025-06-10T02:09:48Z)
• MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling [64.09238330331195]
  We propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework.<n>Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss in an efficient way.<n>We also propose a theoretically proven technique that addresses the numerical stability issue and a training strategy that balances the generation and understanding task goals.
  arXiv  Detail & Related papers  (2024-10-14T17:57:18Z)
• Model Inversion Attacks Through Target-Specific Conditional Diffusion Models [54.69008212790426]
  Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. We propose Diffusion-based Model Inversion (Diff-MI) attacks to alleviate these issues.
  arXiv  Detail & Related papers  (2024-07-16T06:38:49Z)
• Let's reward step by step: Step-Level reward model as the Navigators for Reasoning [64.27898739929734]
  Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase. We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs. To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
  arXiv  Detail & Related papers  (2023-10-16T05:21:50Z)

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.