Audio-to-Text Generation on Image-Text-Audio
54.41CIDErFlowBind
Evaluation Results
| Method | Links | |
|---|---|---|
| FlowBindCategory=Generalists2026.06 | 54.41 | |
| MoPoECategory=Multimodal VAEs, Backbone=same as MUNI, Compute=same as MUNI2026.06 | 50.34 | |
| MMVAECategory=Multimodal VAEs, Backbone=same as MUNI, Compute=same as MUNI2026.06 | 47.43 | |
| MUNI†Category=Generalists2026.06 | 47.38 | |
| MUNICategory=Generalists2026.06 | 43.72 | |
| OmniFlowCategory=Generalists2026.06 | 31.42 | |
| Qwen2-AudioCategory=Specialists2026.06 | 21.39 | |
| UnifiedIO2-LCategory=Generalists2026.06 | 15.18 | |
| CoDiCategory=Generalists2026.06 | 7.7 |