Pith. sign in

REVIEW 9 cited by

ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality

Not yet reviewed by Pith; the record is open.

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

ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality

classification cs.CV cs.AI
keywords ziparforwardgenerationparalleltokensauto-regressivedecodeddecoding
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
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)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

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

  1. Parallel Jacobi Decoding for Fast Autoregressive Image Generation

    cs.CV 2026-06 conditional novelty 7.0

    Parallel Jacobi Decoding accelerates autoregressive image models 4.8x-6.4x by using 2D spatial draft expansion and adjusted attention masks while keeping generation quality competitive.

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

    cs.CV 2026-05 unverdicted novelty 7.0

    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...

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

    cs.CV 2026-05 unverdicted novelty 7.0

    A3 determines the execution horizon in VLA models as the longest prefix of actions that passes consensus-based verification and sequential consistency checks.

  4. FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling

    cs.CV 2025-09 unverdicted novelty 7.0

    Phoneme-guided autoregressive framework for talking-head animation that reduces inter-frame flicker via causal keyframe generation and timestamp-aware interpolation, outperforming diffusion baselines on FVD and a new ...

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

    cs.CV 2026-07 conditional novelty 6.0

    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...

  6. Knowledge Distillation for Visual Autoregressive Models

    cs.CV 2026-06 unverdicted novelty 6.0

    VarKD is a distillation framework for visual AR models that uses student samples and selective teacher supervision to reduce token ambiguity, outperforming prior baselines on ImageNet.

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

    cs.CV 2026-05 conditional novelty 6.0

    A3 adaptively sets a VLA model's execution horizon to the longest action prefix the model re-confirms under conditional and sequential re-decoding, matching or improving task success without manual tuning.

  8. CASCADE: Context-Aware Relaxation for Speculative Image Decoding

    cs.CV 2026-05 unverdicted novelty 6.0

    CASCADE formalizes semantic interchangeability and convergence in target model representations to enable context-aware acceptance relaxation in tree-based speculative decoding, delivering up to 3.6x speedup on text-to...

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

    cs.CV 2026-05 unverdicted novelty 5.0

    A3 adaptively selects verifiable action prefixes in VLA models using group-sampled consensus and conditional re-decoding to balance robustness and speed without manual horizon tuning.