AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping

Haotian Dong, Ye Li, Rongwei Lu, Chen Tang, Shu-Tao Xia, Zhi Wang

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Accelerating autoregressive image generation · 5 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add partial verification skipping (VVS-U i=2) to relaxed-acceptance SDLlamaGen-XL Stage II · MS-COCO 2017TPF: 1.83 -> 2.86Improved
add verification skipping vs LANTERN (Stage II)LlamaGen-XL Stage II · MS-COCO 2017Recall: 0.5360 -> 0.4588Hurt
add verification skipping vs LANTERN (Stage I)LlamaGen-XL Stage I · MS-COCO 2017wall-clock speedup: 1.45x -> 1.63xImproved
sample the token path uniformly instead of picking the highest confidence (ablation)VVS · MS-COCO (delta=0.1)FID: 24.71 -> 23.88Improved
add dynamic truncation of selected token path (ablation)VVS (confidence selection) · MS-COCO (delta=0.1)FID: 26.24 -> 24.71Improved
add dynamic truncation of selected token path (ablation)VVS (confidence selection) · MS-COCO (delta=0.2)FID: 27.41 -> 26.20Improved
blend fresh features with most recently cached features instead of only stale features (ablation)VVS · MS-COCO (delta=0.2)FID: 32.63 -> 27.69Improved
blend fresh with most recent (s2=0) rather than staler (s2=3) features (ablation)VVS · MS-COCO (delta=0.2)TPF: 2.27 -> 2.31Improved
similarity-based dynamic skipping instead of uniform skipping (ablation)VVS · MS-COCO FID-TPF trade-offFID vs TPFImproved
EAGLE-2 style SD without relaxation on visual ARLlamaGen-XL Stage I · MS-COCO 2017wall-clock speedup: 1.00x -> 0.87xHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy