AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer

Yecheng Wu, Han Cai, Junyu Chen, Zhuoyang Zhang, Enze Xie, Jincheng Yu, Junsong Chen, Jinyi Hu, Yao Lu, Song Han

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Accelerating autoregressive image generation · 10 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
add continuous residual tokens and diffusion head to discrete-only model (ablation)DC-AR · MJHQ-30KgFID: 6.71 -> 5.50Improved
add continuous residual tokens and diffusion head to discrete-only model (ablation)DC-AR · GenEvaloverall score: 0.66 -> 0.69Improved
add continuous residual tokens and diffusion head to discrete-only model (ablation)DC-AR tokenizer · ImageNet 256rFID: 5.13 -> 1.60Improved
add continuous residual tokens and diffusion head to discrete-only model (ablation)DC-AR · MJHQ-30Kthroughput (images/s): 11.4 -> 10.3Hurt
add continuous warm-up stage before alternate fine-tuning (ablation)DC-HT tokenizer · ImageNetrFID: 1.76 -> 1.60Improved
freeze latent space in alternate fine-tuning instead of training all components (ablation)DC-HT tokenizer · ImageNetrFID: 1.92 -> 1.60Improved
pre-train at 256 then fine-tune at 512 instead of training from scratch at 512 (ablation)DC-AR · MJHQ-30KgFID: 6.64 -> 5.50Improved
pre-train at 256 then fine-tune at 512 instead of training from scratch at 512 (ablation)DC-AR · MJHQ-30KGPU hours: 1440 -> 760Improved
use discrete-token transformer with 12 sampling steps instead of continuous MAR needing 64DC-AR · MJHQ-30Ksampling steps: 64 -> 12Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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