(T+A)→I Cross-modal Alignment on Image-Text-Audio
30.76CLIP ScoreOmniFlow
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OmniFlowCategory=Generalists2026.06 | 30.76 | — | |
| FLUX.1Category=Specialists2026.06 | 30.36 | — | |
| MUNICategory=Generalists2026.06 | 29.94 | — | |
| MUNI†Category=Generalists2026.06 | 29.92 | — | |
| UnifiedIO2-LCategory=Generalists2026.06 | 29.73 | — | |
| CoDiCategory=Generalists2026.06 | 29.7 | — | |
| MMVAECategory=Multimodal VAEs2026.06 | 29.68 | — | |
| MoPoECategory=Multimodal VAEs2026.06 | 29.59 | — | |
| FlowBindCategory=Generalists2026.06 | 28.07 | — | |
| MUNI†Category=Generalists, aggregation=Hellinger2026.06 | 26.43 | 90.94 | |
| OmniFlowCategory=Generalists2026.06 | 26.41 | 81.51 | |
| MoPoECategory=Multimodal VAEs2026.06 | 26.25 | 86.25 | |
| MMVAECategory=Multimodal VAEs2026.06 | 25.7 | 88.22 | |
| MUNICategory=Generalists, aggregation=PoE2026.06 | 25.44 | 93.42 | |
| FlowBindCategory=Generalists2026.06 | 25.23 | 86.44 | |
| CoDiCategory=Generalists2026.06 | 24.98 | 85.52 | |
| CoDiCategory=Generalists2026.06 | — | 84.47 | |
| FlowBindCategory=Generalists2026.06 | — | 93.94 | |
| MMVAECategory=Multimodal VAEs2026.06 | — | 95.11 | |
| MoPoECategory=Multimodal VAEs2026.06 | — | 94.2 | |
| MUNICategory=Generalists2026.06 | — | 95.59 | |
| MUNI†Category=Generalists2026.06 | — | 95.61 | |
| OmniFlowCategory=Generalists2026.06 | — | 64.22 | |
| Sound2VisionCategory=Specialists2026.06 | — | 97.4 |