AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation

Yi Liu, Shengqian Li, Zuzeng Lin, Feng Wang, Si Liu

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 0 citations (OpenAlex)

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 parallel one-step generation instead of serial multi-step (ablation)CycleVAR (VAR-310M) · Horse to ZebraFID: 82.05 -> 47.82Improved
use parallel one-step generation instead of serial multi-step (ablation)CycleVAR (VAR-310M) · Zebra to HorseFID: 189.80 -> 124.10Improved
use parallel one-step generation instead of serial multi-step (ablation)CycleVAR (VAR-310M) · Horse to Zebrainference time (s): 0.22 -> 0.08Improved
use parallel one-step generation instead of serial multi-step (ablation)CycleVAR (VAR-310M) · Horse to ZebraDINO Structure: 1.90 -> 1.77No clear effect
add multi-scale output to multi-scale context (ablation)CycleVAR (VAR-310M) · Horse to ZebraFID: 58.70 -> 47.82Improved
add multi-scale context and output (ablation)CycleVAR (VAR-310M) · Horse to ZebraFID: 268.70 -> 47.82Improved
add multi-scale context and output (ablation)CycleVAR (VAR-310M) · Zebra to HorseFID: 260.00 -> 124.10Improved
raise SRQ temperature from 0.01 to 2.00 (ablation)CycleVAR (VAR-310M) · Horse to ZebraFID: 228.20 -> 47.82Improved
raise SRQ temperature to 10000 (ablation)CycleVAR (VAR-310M) · Horse to ZebraFID: 47.82 -> 457.90Hurt
raise SRQ temperature from 2.00 to 10.00 (ablation)CycleVAR (VAR-310M) · Horse to ZebraFID / DINO Structure: FID 47.82 -> 47.11; DINO 1.77 -> 1.88Mixed
remove gumbel noise at temperature 0.70 (ablation)CycleVAR (VAR-310M) · Horse to ZebraFID: 48.59 -> 48.58No clear effect
use CycleVAR w/ Infinity instead of CycleGAN-TurboCycleVAR · Night to DayFID: 45.2 -> 43.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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