Cross-modal Alignment ((T+I)→A) on Image-Text-Audio
46.96CLAP ScoreTangoFlux
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TangoFluxCategory=Specialists2026.06 | 46.96 | — | |
| MUNI†Category=Generalists2026.06 | 31.81 | — | |
| MUNICategory=Generalists2026.06 | 31.45 | — | |
| MoPoECategory=Multimodal VAEs2026.06 | 31.43 | — | |
| MoPoECategory=Multimodal VAEs2026.06 | 30.96 | 84.07 | |
| MUNI†Category=Generalists, aggregation=Hellinger2026.06 | 30.16 | 86.89 | |
| MMVAECategory=Multimodal VAEs2026.06 | 30.09 | — | |
| OmniFlowCategory=Generalists2026.06 | 30.07 | — | |
| FlowBindCategory=Generalists2026.06 | 27.13 | — | |
| MUNICategory=Generalists, aggregation=PoE2026.06 | 26.88 | 87.29 | |
| FlowBindCategory=Generalists2026.06 | 26.83 | 80.15 | |
| MMVAECategory=Multimodal VAEs2026.06 | 25.33 | 82.49 | |
| CoDiCategory=Generalists2026.06 | 16.72 | — | |
| UnifiedIO2-LCategory=Generalists2026.06 | 15.22 | — | |
| OmniFlowCategory=Generalists2026.06 | 13.5 | 63.55 | |
| CoDiCategory=Generalists2026.06 | 11.06 | 65.31 | |
| CoDiCategory=Generalists2026.06 | — | 59.45 | |
| FlowBindCategory=Generalists2026.06 | — | 89.23 | |
| MMVAECategory=Multimodal VAEs2026.06 | — | 90.05 | |
| MoPoECategory=Multimodal VAEs2026.06 | — | 90.82 | |
| MUNICategory=Generalists2026.06 | — | 89.92 | |
| MUNI†Category=Generalists2026.06 | — | 90.11 | |
| OmniFlowCategory=Generalists2026.06 | — | 76.52 | |
| Seeing & HearingCategory=Specialists2026.06 | — | 51.96 |