Binary Audio Classification on RAVDESS (test)
68.55Mean AccuracyAdaptive Attribute Discovery with MLLMs
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Adaptive Attribute Discovery with MLLMsMethod Type=Proposed, Backbone=gemini-3-f-p, Trials=10, Sampling Temperature=1.0, q=10, T=10, k=10, Weak Classifier=decision stump2026.03 | 68.55 | 2.57 | 1.95 | |
| MLLM PredictionMethod Type=Baseline, Backbone=gemini-3-f-p, Trials=10, Sampling Temperature=1.0, Evaluation Protocol=direct zero-shot prediction2026.03 | 66.6 | 1.82 | — | |
| LRMethod Type=Baseline, Features=CLAP [18], Solver=L-BFGS2026.03 | 54 | — | — |