Zenia Kellyann

Mamba Iclr 2024. In this paper, we present blackmamba, a novel architecture that combines the mamba ssm with moe to obtain the benefits of both. Relaxing the accurate imputation assumption in doubly robust learning for debiased collaborative.

Our results demonstrate that, across both categories of tasks, mamba closely matches the performance of transformer models for icl. Mamba will not be the first and not the last paper to be refused at iclr.