UMID infers membership in contrastive pre-training data using only text queries by performing latent inversion and comparing similarity and variability signals to synthetic gibberish references via unsupervised anomaly detection.
Clap learning audio concepts from natural language supervision
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
LLMs using in-context learning and fine-tuning on listener experiment data generate equalization settings that align better with population preferences than random sampling or static presets.
AcuLa aligns audio models with medical language models via contrastive and self-supervised objectives on LLM-generated clinical reports, raising mean AUROC from 0.68 to 0.79 across 18 cardio-respiratory tasks.
citing papers explorer
-
Membership Inference for Contrastive Pre-training Models with Text-only PII Queries
UMID infers membership in contrastive pre-training data using only text queries by performing latent inversion and comparing similarity and variability signals to synthetic gibberish references via unsupervised anomaly detection.
-
One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization
LLMs using in-context learning and fine-tuning on listener experiment data generate equalization settings that align better with population preferences than random sampling or static presets.
-
Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding
AcuLa aligns audio models with medical language models via contrastive and self-supervised objectives on LLM-generated clinical reports, raising mean AUROC from 0.68 to 0.79 across 18 cardio-respiratory tasks.