Audio-Visual Question Answering on Music-AVQA (Original and Filtered Scores)
79.5Original ScoreUniMambaMia
Evaluation results
| Method | Links | ||
|---|---|---|---|
| UniMambaMiaLLM=Qwen2-7B, Use Audio=✓, Latency (s)=1.602025.09 | 79.5 | 69.2 | |
| LLaVA-OneVisionLLM=Qwen2-7B, Use Audio=×, Latency (s)=0.972025.09 | 60.4 | 48.7 | |
| Qwen2-VLLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.632025.09 | 60.3 | 45.4 | |
| LLaVA-VideoLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.002025.09 | 60.2 | 45.2 | |
| LLaVA-NeXT-Vid.LLM=Vicuna-7B, Use Audio=×, Latency (s)=0.242025.09 | 54.6 | 47 | |
| Qwen2.5-OmniLLM=Qwen2.5-7B, Use Audio=✓, Latency (s)=4.122025.09 | 45.7 | 32.4 |