Accelerating Inference of Masked Image Generators via Reinforcement Learning

• URL: http://arxiv.org/abs/2512.01094v1
• Date: Sun, 30 Nov 2025 21:28:00 GMT
• Title: Accelerating Inference of Masked Image Generators via Reinforcement Learning
• Authors: Pranav Subbaraman, Shufan Li, Siyan Zhao, Aditya Grover,
• Abstract summary: We propose Speed-RL, a novel paradigm for accelerating a pretrained MGM to generate high-quality images in fewer steps.<n>We show that the proposed method was able to accelerate the base model by a factor of 3x while maintaining comparable image quality.
• Score: 41.30941040845135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Masked Generative Models (MGM)s demonstrate strong capabilities in generating high-fidelity images. However, they need many sampling steps to create high-quality generations, resulting in slow inference speed. In this work, we propose Speed-RL, a novel paradigm for accelerating a pretrained MGMs to generate high-quality images in fewer steps. Unlike conventional distillation methods which formulate the acceleration problem as a distribution matching problem, where a few-step student model is trained to match the distribution generated by a many-step teacher model, we consider this problem as a reinforcement learning problem. Since the goal of acceleration is to generate high quality images in fewer steps, we can combine a quality reward with a speed reward and finetune the base model using reinforcement learning with the combined reward as the optimization target. Through extensive experiments, we show that the proposed method was able to accelerate the base model by a factor of 3x while maintaining comparable image quality.

Related papers

• Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation [87.00172597953228]
  Speculative decoding has shown promise in accelerating text generation without compromising quality.<n>We introduce Hawk, a new approach that harnesses the spatial structure of images to guide the speculative model toward more accurate and efficient predictions.<n> Experimental results on multiple text-to-image benchmarks demonstrate a 1.71x speedup over standard AR models.
  arXiv  Detail & Related papers  (2025-10-29T17:43:31Z)
• Boosting Generative Image Modeling via Joint Image-Feature Synthesis [15.133906625258797]
  We introduce a novel generative image modeling framework that seamlessly bridges the gap by leveraging a diffusion model to jointly model low-level image latents.<n>Our latent-semantic diffusion approach learns to generate coherent image-feature pairs from pure noise.<n>By eliminating the need for complex distillation objectives, our unified design simplifies training and unlocks a powerful new inference strategy: Representation Guidance.
  arXiv  Detail & Related papers  (2025-04-22T17:41:42Z)
• Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation [49.202383675543466]
  We present Acc3D to tackle the challenge of accelerating the diffusion process to generate 3D models from single images.<n>To derive high-quality reconstructions through few-step inferences, we emphasize the critical issue of regularizing the learning of score function in states of random noise.
  arXiv  Detail & Related papers  (2025-03-20T09:18:10Z)
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis [62.57727062920458]
  We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL.<n>We leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers.<n>Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images.
  arXiv  Detail & Related papers  (2024-10-10T17:59:17Z)
• RL for Consistency Models: Faster Reward Guided Text-to-Image Generation [15.238373471473645]
  We propose a framework for fine-tuning consistency models viaReinforcement Learning (RL) Our framework, called Reinforcement Learning for Consistency Model (RLCM), frames the iterative inference process of a consistency model as an RL procedure. Comparing to RL finetuned diffusion models, RLCM trains significantly faster, improves the quality of the generation measured under the reward objectives, and speeds up the inference procedure by generating high quality images with as few as two inference steps.
  arXiv  Detail & Related papers  (2024-03-25T15:40:22Z)
• Active Generation for Image Classification [45.93535669217115]
  We propose to address the efficiency of image generation by focusing on the specific needs and characteristics of the model. With a central tenet of active learning, our method, named ActGen, takes a training-aware approach to image generation.
  arXiv  Detail & Related papers  (2024-03-11T08:45:31Z)
• Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation [112.08287900261898]
  This paper proposes a novel self-cascade diffusion model for rapid adaptation to higher-resolution image and video generation. Our approach achieves a 5X training speed-up and requires only an additional 0.002M tuning parameters. Experiments demonstrate that our approach can quickly adapt to higher resolution image and video synthesis by fine-tuning for just 10k steps, with virtually no additional inference time.
  arXiv  Detail & Related papers  (2024-02-16T07:48:35Z)
• A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization [54.113083217869516]
  In this work, we first explore the computational redundancy part of the network. We then prune the redundancy blocks of the model and maintain the network performance. Thirdly, we propose a global-regional interactive (GRI) attention to speed up the computationally intensive attention part.
  arXiv  Detail & Related papers  (2023-12-24T15:37:47Z)
• LMD: Faster Image Reconstruction with Latent Masking Diffusion [28.54828478259779]
  Masked autoencoders (MAEs), as popular self-supervised vision learners, have demonstrated simpler and more effective image reconstruction and transfer capabilities on downstream tasks. This paper presents LMD, a faster image reconstruction framework with latent masking diffusion.
  arXiv  Detail & Related papers  (2023-12-13T08:36:51Z)
• CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation [49.3016007471979]
  Large generative diffusion models have revolutionized text-to-image generation and offer immense potential for conditional generation tasks. However, their widespread adoption is hindered by the high computational cost, which limits their real-time application. We introduce a novel method dubbed CoDi, that adapts a pre-trained latent diffusion model to accept additional image conditioning inputs.
  arXiv  Detail & Related papers  (2023-10-02T17:59:18Z)
• Accelerating Score-based Generative Models for High-Resolution Image Synthesis [42.076244561541706]
  Score-based generative models (SGMs) have recently emerged as a promising class of generative models. In this work, we consider the acceleration of high-resolution generation with SGMs. We introduce a novel Target Distribution Sampling Aware (TDAS) method by leveraging the structural priors in space and frequency domains.
  arXiv  Detail & Related papers  (2022-06-08T17:41:14Z)
• Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation [39.55651747758391]
  We propose to use Reinforced Adversarial Learning (RAL) based on policy gradient optimization for autoregressive models. RAL also empowers the collaboration between different modules of the VQ-VAE framework. The proposed method achieves state-of-the-art results on Celeba for 64 $times$ 64 image resolution.
  arXiv  Detail & Related papers  (2020-07-20T08:10:07Z)

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.