Sarah M. Erfani
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces GRIDS, a framework using Local Intrinsic Dimensionality (LID) to detect anomalies in self-supervised speech model representations, showing that LID elevation correlates with ASR degradation and enables transcript-free monitoring.
The paper introduces TRACER, a novel regularization framework that uses Weighted Moving Average (WMA) distillation to robustly finetune multimodal models, mitigating catastrophic forgetting and improving out-of-distribution performance.
Papers
TRACER: Persistent Regularization for Robust Multimodal Finetuning
The paper introduces TRACER, a novel regularization framework that uses Weighted Moving Average (WMA) distillation to robustly finetune multimodal models, mitigating catastrophic forgetting and improv…