ZEBRA: Zero-Shot Entropy-Regularized Prompt Learning for Base-to-Novel Generalization in Audio-Language Models
Audio-Language Models (ALMs) achieve strong zero-shot performance by aligning audio with textual class descriptions. Although prompt learning improves accuracy on base classes through few-shot supervised adaptation, we observe a critical trade-off: it often degrades performance on novel classes, sometimes falling below zero-shot accuracy. This exposes a base-to-novel generalization gap in prompt learning for ALMs. To address this issue, we propose \textbf{ZEBRA} (Zero-shot Entropy-Regularized Prompt Learning for Base-to-Novel Generalization), a plug-and-play framework that fuses zero-shot logi
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “ZEBRA: Zero-Shot Entropy-Regularized Prompt Learning for Bas” ≈ “aymericdamien/TopDeepLearning””
- FuzzySimilar title/name (fuzzy) · 59%NirDiamant/Prompt_Engineering →
“Fuzzy title match (0.73): “ZEBRA: Zero-Shot Entropy-Regularized Prompt Learning for Bas” ≈ “NirDiamant/Prompt_Engineering””
- FuzzySimilar title/name (fuzzy) · 59%linshenkx/prompt-optimizer →
“Fuzzy title match (0.73): “ZEBRA: Zero-Shot Entropy-Regularized Prompt Learning for Bas” ≈ “linshenkx/prompt-optimizer””