paper-with-me

Papers

Parallel Jacobi Decoding for Fast Autoregressive Image Generation

2026-06-04 · Boya Liao, Ying Li, Siyong Jian, Huan Wang arxiv

Autoregressive (AR) models have demonstrated remarkable performance in generating high-fidelity images. However, their inherently sequential next-token prediction leads to significantly slower inference. Recent studies have introduced Jacobi-style decoding to accelerate autoregressive image generation. Extending the draft sequence initially improves efficiency, yet the acceleration quickly saturates as error propagation in the one-dimensional sequence hinders convergence. Observing that images exhibit strong local spatial correlations, we propose Parallel Jacobi Decoding (PJD), a training-free decoding approach that expands draft tokens in the two-dimensional spatial domain to enable efficient spatially parallel refinement. PJD adjusts the attention mask to mitigate error accumulation and improve convergence stability. Extensive experiments on diverse datasets show that PJD achieves 4.8x-6.4x acceleration across multiple autoregressive image generation models while maintaining competitive generation quality.

📄 PDF Abstract BibTeX arXiv:2606.05703

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation

2025-10-10 · Yao Teng, Fuyun Wang, Xian Liu, Zhekai Chen 외 arxiv

As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requiring thousands of model forward passes to…

Text-to-Image Generation

CLLMs: Consistency Large Language Models

2024-02-28 · Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng 외

Parallel decoding methods such as Jacobi decoding show promise for more efficient LLM inference as it breaks the sequential nature of the LLM decoding process and transforms it into parallelizable computation. However, i…

Accelerating Transformer Inference for Translation via Parallel Decoding

2023-05-17 · Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca 외

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and re…

Machine TranslationTranslation

SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation

2025-12-08 · Yao Teng, Zhihuan Jiang, Han Shi, Xian Liu 외 arxiv

Large autoregressive models can generate high-quality, high-resolution images but suffer from slow generation speed, because these models require hundreds to thousands of sequential forward passes for next-token predicti…

Text-to-Image Generation

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

2026-06-09 · Haodong Lei, Hongsong Wang, Bingxuan Dai, Pan Zhou arxiv

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 s…

Text-to-Image Generation