List your company

Audio-Visual Question Answering on AVQA 69 (test)

93.8AccuracyPAVE-7B (w/ audio)
85.27287.48689.791.914Mar 25, 2025

Evaluation results

MethodLinks
PAVE-7B (w/ audio)Evaluation Protocol=Task-specific fine-tuning, TFLOPS=98.63, Total/Trainable Params=8.2B / 170.5M2025.0393.8
CAT-7B-FTEvaluation Protocol=Task-specific fine-tuning2025.0392
LLaVA-OV-7B-FTEvaluation Protocol=Task-specific fine-tuning, TFLOPS=98.53, Total/Trainable Params=8.2B / 161.5M2025.0390.8
PSTP-NetEvaluation Protocol=Task-specific fine-tuning2025.0390.2
LLaVA-OV-7BEvaluation Protocol=Zero-shot, TFLOPS=98.53, Total/Trainable Params=8.2B / -2025.0385.6