Related papers: Mixture of Sequence: Theme-Aware Mixture-of-Expert…

In sequence to sequence learning, the self-attention mechanism proves to be highly effective, and achieves significant improvements in many tasks. However, the self-attention mechanism is not without its own flaws. Although self-attention…

Mixture-of-Experts (MoE) models promise efficient scaling of large language models (LLMs) by activating only a small subset of experts per token, but their parallelized inference pipelines make elastic serving challenging. Existing…

Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges…

The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts per query. Deploying MoE on consumer-grade edge hardware, however, is constrained by limited…

Mixture-of-Experts (MoE) has emerged as a promising paradigm for efficiently scaling large language models without a proportional increase in computational cost. However, the standard training strategy of Top-K router prevents MoE models…

Finding the optimal configuration of Sparse Mixture-ofExperts (SMoE) that maximizes semantic differentiation among experts is essential for exploiting the full potential of MoE architectures. However, existing SMoE frameworks either heavily…

This paper presents a comprehensive review of the Mixture-of-Experts (MoE) architecture in large language models, highlighting its ability to significantly enhance model performance while maintaining minimal computational overhead. Through…

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…

In recent years, various methods have been proposed for mesh analysis, each offering distinct advantages and often excelling on different object classes. We present a novel Mixture of Experts (MoE) framework designed to harness the…

Large-scale industrial recommendation systems typically employ a two-stage paradigm of retrieval and ranking to handle huge amounts of information. Recent research focuses on improving the performance of retrieval model. A promising way is…

This paper proposes Medley of Sub-Attention Networks (MoSAN), a new novel neural architecture for the group recommendation task. Group-level recommendation is known to be a challenging task, in which intricate group dynamics have to be…

Mixture of Experts (MoE) has emerged as a promising paradigm for scaling model capacity while preserving computational efficiency, particularly in large-scale machine learning architectures such as large language models (LLMs). Recent…

Mixture-of-Experts (MoE) models achieve efficient scaling through sparse expert activation, but often suffer from suboptimal routing decisions due to distribution shifts in deployment. While existing test-time adaptation methods could…

Mixture-of-Experts (MoE) models scale capacity by combining specialized experts, but most existing approaches assume centralized access to training data. In practice, data are distributed across clients and cannot be shared due to privacy…

As the training of giant dense models hits the boundary on the availability and capability of the hardware resources today, Mixture-of-Experts (MoE) models become one of the most promising model architectures due to their significant…

Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE models require batch inference to optimize hardware…

We propose HyMoERec, a novel sequential recommendation framework that addresses the limitations of uniform Position-wise Feed-Forward Networks in existing models. Current approaches treat all user interactions and items equally, overlooking…

Sequential recommendations have drawn significant attention in modeling the user's historical behaviors to predict the next item. With the booming development of multimodal data (e.g., image, text) on internet platforms, sequential…

The modeling of users' behaviors is crucial in modern recommendation systems. A lot of research focuses on modeling users' lifelong sequences, which can be extremely long and sometimes exceed thousands of items. These models use the target…

Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods typically employ a single window length across all attention…