AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching

Run Luo, Xiaobo Xia, Lu Wang, Longze Chen, Renke Shan, Jing Luo, Min Yang, Tat-Seng Chua

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 20 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
replace AR paradigm with DFM (decoupled representation) (ablation)NExT-OMNI baseline · Ablation averageaverage: 41.4 -> 42.6Improved
replace AR with DFM (ablation)NExT-OMNI baseline · VQAv2accuracy: 55.2 -> 52.3Hurt
replace AR with DFM (ablation)NExT-OMNI baseline · GenEvalGenEval: 53.4 -> 59.8Improved
replace AR with DFM (ablation)NExT-OMNI baseline · Spoken QA (S->S)accuracy: 16.4 -> 20.3Improved
use unified instead of decoupled representation (ablation)DFM model · Ablation averageaverage: 42.6 -> 43.0Improved
use unified instead of decoupled representation (ablation)DFM model · InfoSeekTop-5 accuracy: 29.6 -> 32.8Improved
use unified instead of decoupled representation (ablation)DFM model · VQAv2accuracy: 52.3 -> 51.7Hurt
add dynamic generation strategy (DGS) (ablation)DFM unified model · VQAv2accuracy: 51.7 -> 54.3Improved
add dynamic generation strategy (DGS) (ablation)DFM unified model · AudioCapsscore: 59.4 -> 61.9Improved
add dynamic generation strategy (DGS) (ablation)DFM unified model · GenEvalGenEval: 59.2 -> 59.4No clear effect
add modality reconstruction loss (ablation)DFM unified + DGS · GenEvalGenEval: 59.4 -> 62.6Improved
add modality reconstruction loss (ablation)DFM unified + DGS · Ablation averageaverage: 43.9 -> 45.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 6 of 6 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