Related papers: Adversarial Mixture Of Experts with Category Hiera…

While Dense Retrieval Models (DRMs) have advanced Information Retrieval (IR), one limitation of these neural models is their narrow generalizability and robustness. To cope with this issue, one can leverage the Mixture-of-Experts (MoE)…

The softmax gating function is arguably the most popular choice in mixture of experts modeling. Despite its widespread use in practice, the softmax gating may lead to unnecessary competition among experts, potentially causing the…

Standard Mixture-of-Experts (MoE) models rely on centralized routing mechanisms that introduce rigid inductive biases. We propose Routing-Free MoE which eliminates any hard-coded centralized designs including external routers, Softmax,…

Hard-parameter sharing is a common strategy to train a single model jointly across diverse tasks. However, this often leads to task interference, impeding overall model performance. To address the issue, we propose a simple yet effective…

Sparsely activated Mixture-of-Experts (SMoE) has shown promise in scaling up the learning capacity of neural networks. However, vanilla SMoEs have issues such as expert redundancy and heavy memory requirements, making them inefficient and…

Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of \emph{expert paths} -- the sequence of expert selections a token…

Covariance matrices arise naturally in different scientific fields, including finance, genomics, and neuroscience, where they encode dependence structures and reveal essential features of complex multivariate systems. In this work, we…

Standard Operating Procedures (SOPs) are essential for ensuring operational safety and consistency in industrial environments. However, retrieving and following these procedures presents unique challenges, such as rigid proprietary…

Due to the inherent difficulty in modeling phonetic similarities across different languages, code-switching speech recognition presents a formidable challenge. This study proposes a Collaborative-MoE, a Mixture of Experts (MoE) model that…

Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multiple domains. In this paper, we integrate the MoE structure…

This work describes and validates an approach for autonomously bifurcating turbulent combustion manifolds to divide regression tasks amongst specialized artificial neural networks (ANNs). This approach relies on the mixture of experts (MoE)…

In e-commerce system, category prediction is to automatically predict categories of given texts. Different from traditional classification where there are no relations between classes, category prediction is reckoned as a standard…

Accurate precipitation forecasting is indispensable in agriculture, disaster management, and sustainable strategies. However, predicting rainfall has been challenging due to the complexity of climate systems and the heterogeneous nature of…

The computational cost associated with high-fidelity CFD simulations remains a significant bottleneck in the automotive design and optimization cycle. While ML-based surrogate models have emerged as a promising alternative to accelerate…

Sparse Mixture-of-Experts (MoE) architectures are increasingly popular for frontier large language models (LLM) but they introduce training challenges due to routing complexity. Fully leveraging parameters of an MoE model requires all…

A long-cherished vision in robotics is to equip robots with skills that match the versatility and precision of humans. For example, when playing table tennis, a robot should be capable of returning the ball in various ways while precisely…

Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model's parameters is used during each inference. However, to translate this sparsity into practical performance, an expert caching mechanism…

Sparse Mixture of Experts (SMoE) has emerged as a key to achieving unprecedented scalability in deep learning. By activating only a small subset of parameters per sample, SMoE achieves an exponential increase in parameter counts while…

This project addresses the challenge of human motion prediction, a critical area for applications such as au- tonomous vehicle movement detection. Previous works have emphasized the need for low inference times to provide real time…

Mixture-of-Experts (MoE) architectures scale Large Language Models via expert specialization induced by conditional computation. In practice, however, expert specialization often fails: some experts become functionally similar, while others…