Multi-Scale Local Speculative Decoding for Image Generation

• URL: http://arxiv.org/abs/2601.05149v1
• Date: Thu, 08 Jan 2026 17:39:35 GMT
• Title: Multi-Scale Local Speculative Decoding for Image Generation
• Authors: Elia Peruzzo, Guillaume Sautière, Amirhossein Habibian,
• Abstract summary: We introduce Multi-Scale Local Speculative Decoding (MuLo-SD)<n>MuLo-SD combines multi-resolution drafting with spatially informed verification to accelerate AR image generation.<n>We demonstrate that MuLo-SD achieves substantial speedups up to $mathbf1.7times$.
• Score: 10.239314110594249
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive (AR) models have achieved remarkable success in image synthesis, yet their sequential nature imposes significant latency constraints. Speculative Decoding offers a promising avenue for acceleration, but existing approaches are limited by token-level ambiguity and lack of spatial awareness. In this work, we introduce Multi-Scale Local Speculative Decoding (MuLo-SD), a novel framework that combines multi-resolution drafting with spatially informed verification to accelerate AR image generation. Our method leverages a low-resolution drafter paired with learned up-samplers to propose candidate image tokens, which are then verified in parallel by a high-resolution target model. Crucially, we incorporate a local rejection and resampling mechanism, enabling efficient correction of draft errors by focusing on spatial neighborhoods rather than raster-scan resampling after the first rejection. We demonstrate that MuLo-SD achieves substantial speedups - up to $\mathbf{1.7\times}$ - outperforming strong speculative decoding baselines such as EAGLE-2 and LANTERN in terms of acceleration, while maintaining comparable semantic alignment and perceptual quality. These results are validated using GenEval, DPG-Bench, and FID/HPSv2 on the MS-COCO 5k validation split. Extensive ablations highlight the impact of up-sampling design, probability pooling, and local rejection and resampling with neighborhood expansion. Our approach sets a new state-of-the-art in speculative decoding for image synthesis, bridging the gap between efficiency and fidelity.

Related papers

• Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing [62.94394079771687]
  A burgeoning trend is to adopt high-dimensional features from representation encoders as generative latents.<n>We propose a systematic framework to adapt understanding-oriented encoder features for generative tasks.<n>We show that our approach achieves state-of-the-art reconstruction, faster convergence, and substantial performance gains in both Text-to-Image (T2I) and image editing tasks.
  arXiv  Detail & Related papers  (2025-12-19T18:59:57Z)
• SFTok: Bridging the Performance Gap in Discrete Tokenizers [72.9996757048065]
  We propose textbfSFTok, a discrete tokenizer that incorporates a multi-step iterative mechanism for precise reconstruction.<n>At a high compression rate of only 64 tokens per image, SFTok achieves state-of-the-art reconstruction quality on ImageNet.
  arXiv  Detail & Related papers  (2025-12-18T18:59:04Z)
• Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation [75.58269386927076]
  Autoregressive (AR) models are often dismissed as impractical due to prohibitive computational cost.<n>This work re-thinks this paradigm, introducing a framework built on hierarchical parallelism and progressive adaptation.<n> Experiments on diverse datasets (natural, satellite, medical) validate that our method achieves new state-of-the-art compression.
  arXiv  Detail & Related papers  (2025-11-14T06:27:58Z)
• 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)
• Beyond Frequency: Scoring-Driven Debiasing for Object Detection via Blueprint-Prompted Image Synthesis [97.37770785712475]
  We present a generation-based debiasing framework for object detection.<n>Our method significantly narrows the performance gap for underrepresented object groups.
  arXiv  Detail & Related papers  (2025-10-21T02:19:12Z)
• Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis [40.93077975823353]
  Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability.<n>However, the computational overhead in high-resolution stages remains a critical challenge due to the substantial number of tokens involved.<n>We introduce Sparsevar, a plug-and-play acceleration framework for next-scale prediction that dynamically excludes low-frequency tokens during inference without requiring additional training.
  arXiv  Detail & Related papers  (2025-07-28T01:13:24Z)
• LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding [30.630803933771865]
  Experimental results demonstrate the efficacy of our method in providing a substantial speed-up over speculative decoding.<n> LANTERN increases speed-ups by $mathbf1.75times$ and $mathbf1.82times$, as compared to greedy decoding and random sampling.
  arXiv  Detail & Related papers  (2024-10-04T12:21:03Z)
• Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE [51.09507030387935]
  Wasserstein autoencoder (WAE) shows that matching two distributions is equivalent to minimizing a simple autoencoder (AE) loss under the constraint that the latent space of this AE matches a pre-specified prior distribution. We propose to use the contrastive learning framework that has been shown to be effective for self-supervised representation learning, as a means to resolve this problem. We show that using the contrastive learning framework to optimize the WAE loss achieves faster convergence and more stable optimization compared with existing popular algorithms for WAE.
  arXiv  Detail & Related papers  (2021-10-19T22:55:47Z)
• Generalized Octave Convolutions for Learned Multi-Frequency Image Compression [20.504561050200365]
  We propose the first learned multi-frequency image compression and entropy coding approach. It is based on the recently developed octave convolutions to factorize the latents into high and low frequency (resolution) components. We show that the proposed generalized octave convolution can improve the performance of other auto-encoder-based computer vision tasks.
  arXiv  Detail & Related papers  (2020-02-24T01:35:29Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

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.