AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering

Dongxing Mao, Alex Jinpeng Wang, Jiahao Tang, Kevin Qinghong Lin, Linjie Li, Zhengyuan Yang, Lijuan Wang, Min Li, Jingru Tan

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 1 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 RDAJanus Pro* 1B text-specific · StyledTextVisionBlendOCR accuracy: 24.52 -> 58.26Improved
add RDAJanus Pro* 1B text-specific · StyledTextSynthOCR accuracy: 12.75 -> 36.81Improved
add RDAJanus Pro 7B general · AnyText-BenchmarkOCR accuracy: 8.85 -> 10.07Improved
add RDAJanus Pro 7B general · Mario-EvalOCR accuracy: 6.75 -> 8.33Improved
add RDALlamaGen-VQ tokenizer · AnyText-Benchmark reconstruction (low resolution)OCR accuracy: 21.26 -> 36.79Improved
add RDALlamaGen-VQ tokenizer · AnyText-Benchmark reconstruction (low resolution)LPIPS: 0.1912 -> 0.1832Improved
add residual perceptual loss (ablation)RDA · AnyText-Benchmark reconstruction (high resolution)OCR accuracy: 58.30 -> 66.48Improved
add Sobel edge loss (ablation)RDA · AnyText-Benchmark reconstruction (high resolution)OCR accuracy: 64.31 -> 66.48Improved
add final-image perceptual loss (ablation)RDA · AnyText-Benchmark reconstruction (high resolution)OCR accuracy: 64.58 -> 66.48Improved
add frequency-domain loss (ablation)RDA · AnyText-Benchmark reconstruction (high resolution)OCR accuracy: 66.13 -> 66.48No clear effect
add residual decoder without hint codebook (ablation)LlamaGen-VQ tokenizer · AnyText-Benchmark reconstruction (high resolution)OCR accuracy: 58.04 -> 64.25Improved
add hint codebook (dim 16) (ablation)RDA residual decoder · AnyText-Benchmark reconstruction (high resolution)OCR accuracy: 64.25 -> 66.48Improved

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