AI Paper Atlas

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

OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models

Jialv Zou, Bencheng Liao, Qian Zhang, Wenyu Liu, Xinggang Wang

ECCV 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining

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 decoupled (modality-specific) vocabularies instead of a unified vocabulary (ablation)OmniMamba (Mamba-2-370M) · MS-COCO valFID-30K: 19.1 -> 10.3Improved
use decoupled vocabularies instead of unified (ablation)OmniMamba (Mamba-2-370M) · MMEscore: 1036 -> 1100Improved
add task-specific LoRA (ablation)OmniMamba (Mamba-2-370M) · MS-COCO valFID-30K: 14.4 -> 10.3Improved
add task-specific LoRA (ablation)OmniMamba (Mamba-2-370M) · POPEaccuracy: 81.2 -> 81.9Improved
add task-specific LoRA (ablation)OmniMamba (Mamba-2-370M) · MMEscore: 1003 -> 1100Improved
use OmniMamba instead of Show-o on understandingOmniMamba · POPEaccuracy: 80.0 -> 86.3Improved
use OmniMamba instead of JanusFlowOmniMamba · POPE / MME-P / VQAv2score: POPE 88.0 -> 86.3; MME-P 1333.1 -> 1290.6; GQA 60.3 -> 60.8Mixed
use OmniMamba instead of Show-o for generationOmniMamba · MS-COCO valFID-30K: 9.24 -> 5.50Improved
use Mamba-2 backbone instead of Transformer for image generationOmniMamba · generation speedimages/s: 0.81 -> 5.68Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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