List your company

Audio-Visual Speaker Identification on AV-Speaker

47.1Original ScoreQwen2.5-Omni
26.61231.93137.2542.569Sep 22, 2025

Evaluation results

MethodLinks
Qwen2.5-OmniLLM=Qwen2.5-7B, Use Audio=✓, Latency (s)=4.122025.0947.150.5
UniMambaMiaLLM=Qwen2-7B, Use Audio=✓, Latency (s)=1.602025.0946.647.3
LLaVA-VideoLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.002025.0943.543
Qwen2-VLLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.632025.0942.643.5
LLaVA-OneVisionLLM=Qwen2-7B, Use Audio=×, Latency (s)=0.972025.0941.839.3
LLaVA-NeXT-Vid.LLM=Vicuna-7B, Use Audio=×, Latency (s)=0.242025.0927.45.6