List your company

Audio-Visual Captioning on VGGSound All (with ALOHa)

38.8ALOHaASD
32.24833.94935.6537.351May 11, 2026

Evaluation results

MethodLinks
ASDBase Model=Qwen2.5-Omni(7B)2026.0538.829.621.755.8
VanillaBase Model=Qwen2.5-Omni(7B)2026.053530.720.658.6
AVCDBase Model=Qwen2.5-Omni(7B)2026.0532.833.524.455.7
FMDBase Model=Qwen2.5-Omni(7B)2026.0532.537.925.957.3