List your company

Audio-Visual Question Answering on Music-AVQA 30 (test)

84.3Overall AccuracyCAT-7B-FT
47.17256.81166.4576.089Mar 25, 2025

Evaluation results

MethodLinks
CAT-7B-FTEvaluation Protocol=Task-specific fine-tuning2025.0384.384.986.183.2
PAVE-7B (w/ audio)Evaluation Protocol=Task-specific fine-tuning, TFLOPS=98.63, Total/Trainable Params=8.2B / 170.5M2025.0382.379.79378
VASTEvaluation Protocol=Task-specific fine-tuning2025.0380.7———
VALOREvaluation Protocol=Task-specific fine-tuning2025.0378.9———
LLaVA-OV-7B-FTEvaluation Protocol=Task-specific fine-tuning, TFLOPS=98.53, Total/Trainable Params=8.2B / 161.5M2025.0377.475.489.372.3
LLaVA-OV-7BEvaluation Protocol=Zero-shot, TFLOPS=98.53, Total/Trainable Params=8.2B / -2025.0360.468.870.652.8
CAT-7BEvaluation Protocol=Zero-shot2025.0348.6———