mlsanityData to 14 Oct 2026

Parallel Jacobi Decoding for Fast Autoregressive Image Generation

arXiv 2606.05703 ↗First posted 4 Jun 2026cs.CVcited by 2

Not on the map. Why?

Abstract (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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 56 of its 64 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

56 of 64 references.

References · 56

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2023GPT-4 Technical Reportcited by 18,396
  7. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  8. 2024The Llama 3 Herd of Modelscited by 14,715
  9. 2020Denoising Diffusion Implicit Modelscited by 9,781
  10. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  11. 2025Qwen3 Technical Reportcited by 8,820
  12. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
38 more
  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2017Neural Discrete Representation Learningcited by 4,712
  3. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  5. 2016Improved Techniques for Training GANscited by 2,970
  6. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  7. 2023Consistency Modelscited by 1,822
  8. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  9. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  10. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  11. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 1,006
  12. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  13. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  14. 2024SnapKV: LLM Knows What You are Looking for Before Generationcited by 880
  15. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  16. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  17. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 843
  18. 2023H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Modelscited by 832
  19. 2016Pixel Recurrent Neural Networkscited by 816
  20. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  21. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  22. 2023Adversarial Diffusion Distillationcited by 759
  23. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 665
  24. 2024KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cachecited by 637
  25. 2024EAGLE: Speculative Sampling Requires Rethinking Feature Uncertaintycited by 578
  26. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 474
  27. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 428
  28. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 417
  29. 2018Blockwise Parallel Decoding for Deep Autoregressive Modelscited by 323
  30. 2024Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretrainingcited by 150
  31. 2017PixelSNAIL: An Improved Autoregressive Generative Modelcited by 137
  32. 2023Accelerating Transformer Inference for Translation via Parallel Decodingcited by 124
  33. 2024ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generationcited by 114
  34. 2024CLLMs: Consistency Large Language Modelscited by 72
  35. 2024Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decodingcited by 66
  36. 2024Parallelized Autoregressive Visual Generationcited by 60
  37. 2020Accelerating Feedforward Computation via Parallel Nonlinear Equation Solvingcited by 52
  38. 2024LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decodingcited by 47

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generationcited by 2
  2. 2026Accelerating Visual On-Policy Distillation with Batched Speculative Jacobi Rolloutscited by 0