AI Paper Atlas

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

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Zhiheng Liu, Weiming Ren, Haozhe Liu, Zijian Zhou, Shoufa Chen, Haonan Qiu, Xiaoke Huang, Zhaochong An, Fanny Yang, Aditya Patel, Viktar Atliha, Tony Ng and 13 more

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 36 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 unified VAE+SigLIP2 representation instead of decoupled SigLIP2/VAE representations (ablation)TUNA 1.5B ablation · understanding and generation benchmarksSEED / GenEval: SEED 61.4 -> 66.5, GenEval 78.3 -> 79.4Improved
use TUNA unified representation instead of Show-o2 late-fusion (ablation)TUNA 1.5B ablation · Und & Gen trainingGenEval: 75.9 -> 79.4Improved
use SigLIP 2 instead of SigLIP as representation encoder (ablation)TUNA 1.5B ablation · Und & Gen trainingSEED / GenEval: SEED 64.6 -> 66.5, GenEval 76.9 -> 79.4Improved
use DINOv3 instead of SigLIP 2 as encoder (ablation)TUNA 1.5B ablation · Und & Gen trainingGenEval: 79.4 -> 78.9 (MME-p 1361 -> 1396)No clear effect
add generation data to understanding training (ablation)TUNA (SigLIP 2) 1.5B · understanding benchmarksMMMU / SEED / GQA: MMMU 37.6 -> 38.1, SEED 62.9 -> 66.5Improved
add understanding data to generation training (ablation)TUNA (SigLIP 2) 1.5B · generation benchmarksGenEval: 77.8 -> 79.4Improved
add generation data to understanding training on MME-p (ablation)TUNA (SigLIP 2) 1.5B · MME perceptionscore: 1386 -> 1361Hurt

Later papers that compared with this method

4 later accepted papers report Tuna as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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