← Search

Rahim Tafazolli

2 accepted papers

2025

FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training

NeurIPS 2025poster

The parameter size of modern large language models (LLMs) can be scaled up to the trillion-level via the sparsely-activated Mixture-of-Experts (MoE) technique to avoid excessive increase of the computational costs. To further improve training efficiency, pipelining computation and communication has…

Cited by 0SourceScholar
2016

Uniform expected likelihood solution for interference rejection combining regularization

ICASSP 2016accepted

A well known problem of regularization (diagonal loading) of the interference rejection combining (IRC) and IRC / maximum ratio combining (MRC) switching is addressed. Different empirical loading factor selection rules adjusted to specific scenarios have been introduced in the literature. It is expe…

Cited by 0SourceScholar