Poster "low-rank compression" Papers
3 papers found
FlashBias: Fast Computation of Attention with Bias
Haixu Wu, Minghao Guo, Yuezhou Ma et al.
NeurIPS 2025posterarXiv:2505.12044
1
citations
Error Feedback Can Accurately Compress Preconditioners
Ionut-Vlad Modoranu, Aleksei Kalinov, Eldar Kurtic et al.
ICML 2024poster
Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
Samuel Horváth, Stefanos Laskaridis, Shashank Rajput et al.
ICML 2024poster