PathRelax: Parallel-Path Relaxed Speculative Jacobi Decoding for Accelerating Auto-Regressive Text-to-Image Generation

• URL: http://arxiv.org/abs/2606.10492v1
• Date: Tue, 09 Jun 2026 07:16:23 GMT
• Title: PathRelax: Parallel-Path Relaxed Speculative Jacobi Decoding for Accelerating Auto-Regressive Text-to-Image Generation
• Abstract summary: Current methods for accelerating autoregressive text-to-image models rely on chain-structured token sequences.<n>We propose parallel-path cross-relaxed speculative Jacobi decoding (textbfPathSpec), a novel framework that enhances efficiency through a multi-sequence draft tree structure.<n>Our method achieves a speedup ratio of 4.14 $times$, 3.95$times$, and 4.18$times$, respectively.
• Score: 23.998186429836377
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The growing need for high-resolution image generation in autoregressive text-to-image models has resulted in extended token sequences, significantly increasing computational costs and inference times. However, existing state-of-the-art methods for accelerating autoregressive text-to-image models rely on chain-structured draft token sequences, leading to inefficient draft token search and limited acceptance lengths. To address this, we propose parallel-path cross-relaxed speculative Jacobi decoding (\textbf{PathSpec}), a novel framework that enhances efficiency through a multi-sequence draft tree structure. Our parallel-path speculative Jacobi decoding (\textbf{PathExplore}) expands the token search space, achieving a higher speedup ratio without sacrificing image quality. Additionally, we introduce cross-path relaxed verification (\textbf{PathRelax}) that exploits semantic similarities across sequences to further boost token acceptance rates. Evaluated on the Parti-Prompts, MSCOCO2017, and T2ICompBench datasets, our method achieves a speedup ratio of 4.14 $\times$, 3.95$\times$, and 4.18$\times$, respectively. Remarkably, PathExplore, without any relaxed sampling, outperforms relaxed sampling methods in the speedup ratio, such as GSD and LANTERN. Moreover, PathRelax's relaxation mechanism can be seamlessly integrated with other relaxation techniques, enabling further acceleration and providing an efficient solution for real-time text-to-image generation. Our code is available at https://github.com/Haodong-Lei-Ray/PathSpec.

Related papers

• Parallel Jacobi Decoding for Fast Autoregressive Image Generation [8.289611849434959]
  Autoregressive (AR) models have demonstrated remarkable performance in generating high-fidelity images.<n>Their inherently sequential next-token prediction leads to significantly slower inference.<n>Recent studies have introduced Jacobi-style decoding to accelerate autoregressive image generation.<n>We propose Parallel Jacobi Decoding (PJD), a training-free decoding approach that expands draft tokens in the two-dimensional spatial domain.
  arXiv  Detail & Related papers  (2026-06-04T04:50:22Z)
• Improving Flexible Image Tokenizers for Autoregressive Image Generation [53.238708824055664]
  textbfReToK is a flexible tokenizer with underlineRedundant underlineToken Padding and Hierarchical Semantic Regularization.<n>Our method achieves superior generation performance compared with both flexible and fixed-length tokenizers.
  arXiv  Detail & Related papers  (2026-01-04T14:11:45Z)
• SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation [92.34355601866629]
  Large autoregressive models can generate high-quality, high-resolution images but suffer from slow generation speed.<n>We propose Speculative Jacobi Decoding++ (SJD++), a training-free probabilistic parallel decoding algorithm.<n>SJD++ performs multi-token prediction in each forward pass, drastically reducing generation steps.
  arXiv  Detail & Related papers  (2025-12-08T12:36:43Z)
• dParallel: Learnable Parallel Decoding for dLLMs [77.24184219948337]
  Diffusion large language models (dLLMs) offer parallel token prediction and lower inference latency.<n>Existing open-source models still require nearly token-length decoding steps to ensure performance.<n>We introduce dParallel, a simple and effective method that unlocks the inherent parallelism of dLLMs for fast sampling.
  arXiv  Detail & Related papers  (2025-09-30T16:32:52Z)
• FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge [60.000984252907195]
  Auto-regressive (AR) models have recently shown promise in visual generation tasks due to their superior sampling efficiency.<n>Video generation requires a substantially larger number of tokens to produce coherent temporal frames, resulting in significant overhead during the decoding phase.<n>We propose the textbfFastCar framework to accelerate the decode phase for the AR video generation by exploring the temporal redundancy.
  arXiv  Detail & Related papers  (2025-05-17T05:00:39Z)
• Parallelized Autoregressive Visual Generation [65.9579525736345]
  We propose a simple yet effective approach for parallelized autoregressive visual generation.<n>Our method achieves a 3.6x speedup with comparable quality and up to 9.5x speedup with minimal quality degradation across both image and video generation tasks.
  arXiv  Detail & Related papers  (2024-12-19T17:59:54Z)
• ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality [19.486745219466666]
  ZipAR is a training-free, plug-and-play parallel decoding framework for auto-regressive (AR) visual generation.<n>ZipAR can reduce the number of model forward passes by up to 91% on the Emu3-Gen model without requiring any additional retraining.
  arXiv  Detail & Related papers  (2024-12-05T10:57:08Z)
• Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding [60.188309982690335]
  We propose a training-free probabilistic parallel decoding algorithm, Speculative Jacobi Decoding (SJD)<n>SJD accelerates the inference of auto-regressive text-to-image generation while maintaining the randomness in sampling-based token decoding.<n>Specifically, SJD facilitates the model to predict multiple tokens at each step and accepts tokens based on the probabilistic criterion.
  arXiv  Detail & Related papers  (2024-10-02T16:05:27Z)

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.