AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Unified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to Unification

Wujian Peng, Lingchen Meng, Yuxuan Cai, Xianwei Zhuang, Yuhuan Yang, Rongyao Fang, Chenfei Wu, Junyang Lin, Zuxuan Wu, Shuai Bai

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 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
add reinforcement learning at 512 px (500 steps) (ablation)UniAR · OneIG-ENscore: 71.1 to 84.0Improved
add 100 more RL steps at 960 px (ablation)UniAR · OneIG-ENscore: 84.0 to 87.3Improved
add random bitwise visual index flipping during pretraining (ablation)UniAR · image generation at higher temperaturessample stabilityImproved
condition decoder on multi-level features instead of single layer (ablation)visual decoder · image reconstructionreconstruction qualityImproved
use discrete visual tokens instead of continuousUniAR · pre-trainingtime per iteration (s): 35.4 -> 24.5Improved
add decoder upsampling (x64 downsample, 256 tokens) (ablation)UniAR (8B) · 1024px generationtime (s): 53.5 -> 13.0Improved
use UniAR tokenizer instead of COMP-SigLIP as vision encoderLLM with Llama 3.0-8B · DocVQAaccuracy: 34.0 -> 38.0Improved
UniAR tokenizer versus COMP-SigLIPLLM with Llama 3.0-8B · InfoVQAaccuracy: 26.0 -> 23.8Hurt
prompt rewritingUniAR · GenEvaloverall: 0.85 -> 0.86Improved

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