Audio-Visual Question Answering on AVQA 69 (test)
93.8AccuracyPAVE-7B (w/ audio)
Evaluation Results
| Method | Links | |
|---|---|---|
| PAVE-7B (w/ audio)Evaluation Protocol=Task-specific fine-tuning, TFLOPS=98.63, Total/Trainable Params=8.2B / 170.5M2025.03 | 93.8 | |
| CAT-7B-FTEvaluation Protocol=Task-specific fine-tuning2025.03 | 92 | |
| LLaVA-OV-7B-FTEvaluation Protocol=Task-specific fine-tuning, TFLOPS=98.53, Total/Trainable Params=8.2B / 161.5M2025.03 | 90.8 | |
| PSTP-NetEvaluation Protocol=Task-specific fine-tuning2025.03 | 90.2 | |
| LLaVA-OV-7BEvaluation Protocol=Zero-shot, TFLOPS=98.53, Total/Trainable Params=8.2B / -2025.03 | 85.6 |