Co-occurring keywords · papers mentioning both
Papers
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
NeurIPS 2024
Learning better with Dale’s Law: A Spectral Perspective
NeurIPS 2023
Improving Neural Language Generation with Spectrum Control
ICLR 2020
Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice
NeurIPS 2017