Pith. sign in

REVIEW 5 cited by

ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality

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 2412.04062 v3 pith:VY5A7LIY submitted 2024-12-05 cs.CV cs.AI

Yefei He , Feng Chen , Yuanyu He , Shaoxuan He , Hong Zhou , Kaipeng Zhang , Bohan Zhuang This is my paper · ORCID
classification cs.CVcs.AI
keywords ziparforwardgenerationparalleltokensauto-regressivedecodeddecoding
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we propose ZipAR, a training-free, plug-and-play parallel decoding framework for accelerating auto-regressive (AR) visual generation. The motivation stems from the observation that images exhibit local structures, and spatially distant regions tend to have minimal interdependence. Given a partially decoded set of visual tokens, in addition to the original next-token prediction scheme in the row dimension, the tokens corresponding to spatially adjacent regions in the column dimension can be decoded in parallel, enabling the ``next-set prediction'' paradigm. By decoding multiple tokens simultaneously in a single forward pass, the number of forward passes required to generate an image is significantly reduced, resulting in a substantial improvement in generation efficiency. Experiments demonstrate that ZipAR can reduce the number of model forward passes by up to 91% on the Emu3-Gen model without requiring any additional retraining. Code is available here: https://github.com/ThisisBillhe/ZipAR.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Dynamic Execution Commitment of Vision-Language-Action Models

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    A3 reframes dynamic action chunk commitment in VLA models as self-speculative prefix verification, accepting the longest continuous sequence of actions that satisfies consensus-ordered conditional invariance and prefi...

  2. Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    p-less cluster decoding, which truncates and samples over K-means clusters of visual tokens rather than individual tokens, yields higher per-prompt sample diversity than default or dynamic-temperature baselines on mos...

  3. Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective

    cs.CV 2025-07 reject novelty 6.0 of 10

    A new linear attention with spatial-aware decay at row boundaries lowers FID for autoregressive image generation on ImageNet relative to the softmax LlamaGen baseline, but the description of the core mask is internall...

  4. Next Patch Prediction for Autoregressive Visual Generation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Averaging neighboring image tokens into patches during training lets autoregressive image models train faster and generate higher-quality images, with inference unchanged.

  5. Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model

    cs.CV 2025-01 reject novelty 4.0 of 10

    A new 10.5M-pair remote sensing dataset and a 1.3B diffusion model generate resolution-controlled satellite imagery from text, with large reported gains on the RSICD benchmark.

Pith tools