Pith. sign in

REVIEW 12 cited by

Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.01699 v2 pith:DCZW2CXP submitted 2024-10-02 cs.CV

Yao Teng , Han Shi , Xian Liu , Xuefei Ning , Guohao Dai , Yu Wang , Zhenguo Li , Xihui Liu This is my paper · ORCID
classification cs.CV
keywords decodingauto-regressivegenerationtext-to-imagejacobimodelcriteriongenerate
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The current large auto-regressive models can generate high-quality, high-resolution images, but these models require hundreds or even thousands of steps of next-token prediction during inference, resulting in substantial time consumption. In existing studies, Jacobi decoding, an iterative parallel decoding algorithm, has been used to accelerate the auto-regressive generation and can be executed without training. However, the Jacobi decoding relies on a deterministic criterion to determine the convergence of iterations. Thus, it works for greedy decoding but is incompatible with sampling-based decoding which is crucial for visual quality and diversity in the current auto-regressive text-to-image generation. In this paper, we propose a training-free probabilistic parallel decoding algorithm, Speculative Jacobi Decoding (SJD), to accelerate auto-regressive text-to-image generation. By introducing a probabilistic convergence criterion, our SJD accelerates the inference of auto-regressive text-to-image generation while maintaining the randomness in sampling-based token decoding and allowing the model to generate diverse images. Specifically, SJD facilitates the model to predict multiple tokens at each step and accepts tokens based on the probabilistic criterion, enabling the model to generate images with fewer steps than the conventional next-token-prediction paradigm. We also investigate the token initialization strategies that leverage the spatial locality of visual data to further improve the acceleration ratio under specific scenarios. We conduct experiments for our proposed SJD on multiple auto-regressive text-to-image generation models, showing the effectiveness of model acceleration without sacrificing the visual quality. The code of our work is available here: https://github.com/tyshiwo1/Accelerating-T2I-AR-with-SJD/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Token Radius Attention for Efficient Video Generation

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Video diffusion transformers can run ~1.5-2x faster with competitive quality by converting each query's attention entropy into a spatially decayed retention radius instead of dense attention.

  2. SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation

    cs.CV 2026-03 accept novelty 6.0 of 10

    SJD-PAC combines proactive multi-path drafting and adaptive continuation to raise average acceptance length in Speculative Jacobi Decoding, delivering 3.8 imes lossless wall-clock speedup on Lumina-mGPT and Emu3.

  3. HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    HMAR is an image generator that builds each resolution scale from the previous scale and refines it with masked prediction, matching or improving ImageNet FID/IS versus VAR with faster training and inference.

  4. MARch\'e: Fast Masked Autoregressive Image Generation with Cache-Aware Attention

    cs.LG 2025-05 conditional novelty 6.0 of 10

    MARche accelerates masked autoregressive image generation by caching stable token projections and refreshing only attention-selected tokens, reaching up to 1.72x speedup with some loss in FID.

  5. Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Forecasting with a non-causal encoder-only model improves fixed-horizon accuracy when the model is asked to output extra future tokens, an effect the authors call delayed chain-of-thought.

  6. FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge

    cs.CV 2025-05 conditional novelty 6.0 of 10

    FastCar reuses cached MLP outputs from the previous frame for tokens with high temporal attention scores, reducing video generation decoding work by up to 87% at moderate quality loss.

  7. ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality

    cs.CV 2024-12 conditional novelty 6.0 of 10

    ZipAR is a training-free decoding method that uses spatial locality to generate multiple visual tokens per forward pass, cutting autoregressive image generation steps by up to 91%.

  8. Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

    cs.CV 2024-11 conditional novelty 6.0 of 10

    CoDe speeds up Visual Auto-Regressive image generation by using a 2B model for early coarse scales and a 0.3B model for later fine scales, with 1.7x-2.9x speedup and only a small FID increase.

  9. Continuous Speculative Decoding for Autoregressive Image Generation

    cs.CV 2024-11 reject novelty 6.0 of 10

    Continuous speculative decoding accelerates continuous autoregressive image generation by over 2x while approximately maintaining output quality.

  10. Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A set of inference-time design choices improves image quality, memory, and speed of masked generative Transformers, with combined tricks winning about 70% of human-preference comparisons against vanilla sampling.

  11. XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding

    cs.GR 2025-07 conditional novelty 5.0 of 10

    XSpecMesh speeds up auto-regressive mesh generation by about 1.7x using multi-head speculative decoding with cross-attention heads and a probability threshold verification, while keeping output quality close to the ba...

  12. Text-to-Image Synthesis: A Decade Survey

    cs.CV 2024-11 conditional novelty 1.0 of 10

    A decade-spanning survey categorizes over 440 text-to-image papers by architecture, research problem, dataset, and evaluation metric.

Pith tools