AI Paper Atlas

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

FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows

Yeonwoo Cha, Semin Kim, Jinhyeon Kwon, Seunghoon Hong

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 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
use learnable shared latent anchor instead of fixed text anchor (ablation)FlowBind w/o I-A · I->T alignmentCLIP: 27.94 -> 30.04Improved
use learnable shared latent anchor instead of fixed text anchor (ablation)FlowBind w/o I-A · A->T alignmentCLAP: 36.72 -> 37.04Improved
use learnable shared latent anchor instead of fixed text anchor (ablation)FlowBind w/o I-A · I->A alignmentAIS: 55.48 -> 61.88Improved
compare shared latent against per-modality latent (ablation)FlowBind · text-audio CKNNACKNNA: 0.1965 -> 0.2872Improved
compare shared latent against per-modality latent (ablation)FlowBind · audio-image CKNNACKNNA: 0.1343 -> 0.3026Improved
FlowBind versus OmniFlow on image-audio generation qualityFlowBind · I->AFAD: 5.67 -> 2.50Improved
FlowBind versus OmniFlow on text-to-image alignmentFlowBind · T->I (MS-COCO)CLIP: 31.52 -> 28.35Hurt
FlowBind versus OmniFlow on audio-to-text alignmentFlowBind · A->TCLAP: 45.08 -> 36.70Hurt
FlowBind versus OmniFlow on (T+I)->A alignmentFlowBind · Many-to-oneCLAP: 7.68 -> 28.13Improved
FlowBind versus OmniFlow on T->(I+A) generationFlowBind · One-to-manyCLAP (T->A): 12.92 -> 29.12Improved
FlowBind versus specialist TangoFlux on text-to-audioFlowBind · T->AFAD: 1.41 -> 4.19Hurt

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