Audio-visual QA on AVSD
163CIDErV-LynX-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| V-LynX-7BEvaluation Protocol=Task-specific, Model Scale=≥ 7B, ∆Params.=195.0M2026.05 | 163 | |
| PAVE-7BEvaluation Protocol=Task-specific, Model Scale=≥ 7B, ∆Params.=256.7M2026.05 | 152.9 | |
| V-LynX-0.5BEvaluation Protocol=Task-specific, Model Scale=< 7B, ∆Params.=68.7M2026.05 | 145.7 | |
| PAVE-0.5BEvaluation Protocol=Task-specific, Model Scale=< 7B, ∆Params.=127.6M2026.05 | 134.5 | |
| LLaVA-OV-7B-FTEvaluation Protocol=Task-specific, Model Scale=≥ 7B, ∆Params.=161.5M2026.05 | 124.9 | |
| LLaVA-OV-0.5B-FTEvaluation Protocol=Task-specific, Model Scale=< 7B, ∆Params.=35.2M2026.05 | 117.6 | |
| COSTEvaluation Protocol=Task-specific, Model Scale=< 7B2026.05 | 108.5 | |
| CAT-7BEvaluation Protocol=Zero-shot2026.05 | 79 | |
| LLaVA-OV-7BEvaluation Protocol=Zero-shot2026.05 | 70.6 | |
| LLaVA-OV-0.5BEvaluation Protocol=Zero-shot2026.05 | 65.1 |