2 papers
cs.LG2026
Logit Distillation on Manifolds: Mapping by Learning
Yiru Yang, Junling Wang, Nishant Kumar Singh +2
A simple way to improve the performance of almost any machine learning model is not to train a single but several models with diverse algorithms which will make slightly distinct k…
cs.SD2025
DQLoRA: A Lightweight Domain-Aware Denoising ASR via Adapter-guided Distillation
Yiru Yang
We present a demo of DQLoRA, an Adapter-Guided Distillation framework for robust speech recognition under low-resource and noisy conditions. Our method employs a frozen Whisper mod…