TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition 事件

TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition arXiv:2605.27808v1 Announce Type: new Abstract: Data-aware post-training quantization (PTQ) minimizes a per-token reconstruction loss on a small calibration corpus, implicitly weighting positions by their empirical frequency. For \textbf{A}utomatic \textbf{S}peech \textbf{R}ecognition (ASR), this misaligns with tail-sensitive risk: names, numerals, and domain-specific words receive proportionally litt