List your company

Audio-visual QA on MUSIC-AVQA

84.3Overall AccuracyCAT-7B-FT
47.17256.81166.4576.089May 30, 2026

Evaluation results

MethodLinks
CAT-7B-FTEvaluation Protocol=Task-specific, Model Scale=≥ 7B2026.0584.384.986.183.2
V-LynX-7BEvaluation Protocol=Task-specific, Model Scale=≥ 7B, ∆Params.=195.0M2026.058380.893.578.8
PAVE-7BEvaluation Protocol=Task-specific, Model Scale=≥ 7B, ∆Params.=256.7M2026.0582.379.79378
V-LynX-0.5BEvaluation Protocol=Task-specific, Model Scale=< 7B, ∆Params.=68.7M2026.0581.178.992.276.5
VASTEvaluation Protocol=Task-specific, Model Scale=< 7B2026.0580.7———
PAVE-0.5BEvaluation Protocol=Task-specific, Model Scale=< 7B, ∆Params.=127.6M2026.0578.877.389.874.1
LLaVA-OV-7B-FTEvaluation Protocol=Task-specific, Model Scale=≥ 7B, ∆Params.=161.5M2026.0577.475.489.372.3
LLaVA-OV-0.5B-FTEvaluation Protocol=Task-specific, Model Scale=< 7B, ∆Params.=35.2M2026.0567.669.676.362.8
LLaVA-OV-7BEvaluation Protocol=Zero-shot2026.0560.468.870.652.8
LLaVA-OV-0.5BEvaluation Protocol=Zero-shot2026.0552.86057.148.5
CAT-7BEvaluation Protocol=Zero-shot2026.0548.6———