AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

FastHybrid: Accelerating Hybrid Autoregressive Image Generation with Lookahead and Guided Decoding

Zhengguo Jiang, Fang Zhang, Yongxiang Hua, Bocheng Li, Wentao Zhang, Linli Xu

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images

Read the paperCheck your idea against 137,217 papers

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
use FastHybrid instead of halving AR steps (64 to 32)MAR-L · ImageNet 256x256FID: 2.05 -> 1.90 at similar speedup (1.97x vs 1.92x)Improved
use FastHybrid instead of halving AR stepsMAR-H · ImageNet 256x256FID: 1.92 -> 1.70Improved
apply FastHybrid to MAR-BMAR-B · ImageNet 256x256FID: 2.32 -> 2.43Hurt
apply FastHybrid to MAR-HMAR-H · ImageNet 256x256running time (s): 35.7 -> 21.0Improved
add guided diffusion sampling after rejection filtering (RG-0.8 vs R-0.8) (ablation)FastHybrid · ImageNet (10k, MAR-B)FID: 4.94 -> 4.84Improved
raise semantic similarity rejection threshold from 0.0 to 0.8 (ablation)FastHybrid · ImageNet (10k, MAR-B)FID: 5.60 -> 4.84Improved
raise rejection threshold (cost) (ablation)FastHybrid · ImageNet (10k, MAR-B)time (s): 7.47 -> 10.02Hurt
reduce diffusion steps from 50 to 30 without guidance (ablation)MAR-D50 · ImageNet (10k)FID: 4.75 -> 5.04Hurt
use add-noise-then-denoise (inverse) instead of guided sampling (ablation)FastHybrid · ImageNet (10k)FID: 4.84 -> 4.87 / 5.13Hurt
use decreasing (cosine) guidance weight instead of increasing (Linear-up) (ablation)FastHybrid · ImageNet (10k)FID: 5.13 -> 4.84Improved
use cosine schedule instead of linear-down or square schedule (ablation)FastHybrid · ImageNet (10k)FID: 4.99 / 5.09 -> 4.84Improved

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