暂无评分数据
ICLR 2025
Catastrophic Token Leakage in Convolutional Sequence Modeling and How to Mitigate It
TL;DR
FFT based Convolutional models break causality due to numerical imprecision. Integer based FFTs can be a solution.
摘要
关键词
Convolutional ModelsLLMsLanguage ModelingFast Fourier Transforms
评审与讨论
作者撤稿通知
I have read and agree with the venue's withdrawal policy on behalf of myself and my co-authors.