ResearchBenchmarksAudio-Visual Captioning on Audioset (ALOHa)Follow63.7ALOHa ScoreFMD37.1844.06550.9557.835May 11, 2026Evaluation ResultsMethodMethodLinksALOHa ScoreCs (Context Score)Ci (Informativeness Score)F1 ScoreFMDBase Model=Qwen2.5-Omn...Base Model=Qwen2.5-Omni(7B)2026.0563.713.613.571.2AVCDBase Model=Qwen2.5-Omn...Base Model=Qwen2.5-Omni(7B)2026.0559.310.812.169.2VanillaBase Model=Qwen2.5-Omn...Base Model=Qwen2.5-Omni(7B)2026.0538.28.910.969.7ASDBase Model=Qwen2.5-Omn...Base Model=Qwen2.5-Omni(7B)2026.0538.28.510.272.9