Pith. sign in

REVIEW 4 cited by

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

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 2503.23367 v3 pith:YMHW6TKS submitted 2025-03-30 cs.CV

Hang Guo , Yawei Li , Taolin Zhang , Jiangshan Wang , Tao Dai , Shu-Tao Xia , Luca Benini This is my paper · ORCID
classification cs.CV
keywords fastvartokenscachedmodelingresolutiontokenautoregressivefurther
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale step, leading to the complexity and runtime scaling dramatically with image resolution. To address this challenge, we propose FastVAR, a post-training acceleration method for efficient resolution scaling with VARs. Our key finding is that the majority of latency arises from the large-scale step where most tokens have already converged. Leveraging this observation, we develop the cached token pruning strategy that only forwards pivotal tokens for scale-specific modeling while using cached tokens from previous scale steps to restore the pruned slots. This significantly reduces the number of forwarded tokens and improves the efficiency at larger resolutions. Experiments show the proposed FastVAR can further speedup FlashAttention-accelerated VAR by 2.7$\times$ with negligible performance drop of <1%. We further extend FastVAR to zero-shot generation of higher resolution images. In particular, FastVAR can generate one 2K image with 15GB memory footprints in 1.5s on a single NVIDIA 3090 GPU. Code is available at https://github.com/csguoh/FastVAR.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 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. Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis

    cs.CV 2026-02 conditional novelty 5.0 of 10

    A training-free entropy-guided token-pruning framework accelerates VAR image generation up to 2.9× with negligible benchmark loss by activating pruning at an adaptive entropy-growth inflection point and adjusting rati...

  3. Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

    cs.LG 2025-05 conditional novelty 5.0 of 10

    ScaleKV cuts KV cache memory for Visual Autoregressive text-to-image generation to 10% by classifying layers as drafters or refiners per scale and pruning low-attention tokens while keeping benchmark scores nearly unchanged.

  4. SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping

    cs.CV 2025-06 conditional novelty 4.0 of 10

    SkipVAR selects, per sample, between step skipping and unconditional branch replacement using handcrafted frequency features and a trained logistic regression, to accelerate visual autoregressive generation.

Pith tools