Related papers: MoH: Multi-Head Attention as Mixture-of-Head Atten…

Larger transformer models always perform better on various tasks but require more costs to scale up the model size. To efficiently enlarge models, the mixture-of-experts (MoE) architecture is widely adopted, which consists of a gate network…

Mixture-of-Experts large language models (MoE-LLMs) marks a significant step forward of language models, however, they encounter two critical challenges in practice: 1) expert parameters lead to considerable memory consumption and loading…

Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic…

The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference costs. However, deploying MoE-based LLMs on…

Continual learning (CL) has garnered significant attention because of its ability to adapt to new tasks that arrive over time. Catastrophic forgetting (of old tasks) has been identified as a major issue in CL, as the model adapts to new…

We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike state-of-the-art Long Short-Term Memory (LSTM)…

While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades…

Self-attention has greatly contributed to the success of the widely used Transformer architecture by enabling learning from data with long-range dependencies. In an effort to improve performance, a gated attention model that leverages a…

Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a…

Simultaneous machine translation models start generating a target sequence before they have encoded or read the source sequence. Recent approaches for this task either apply a fixed policy on a state-of-the art Transformer model, or a…

Transformer-based methods have demonstrated excellent performance on super-resolution visual tasks, surpassing conventional convolutional neural networks. However, existing work typically restricts self-attention computation to…

Vision-language-action (VLA) models have shown remarkable capabilities in robotic manipulation, but their performance is sensitive to the $\textbf{action chunk length}$ used during training, termed $\textbf{horizon}$. Our empirical study…

Large language models (LLMs) increasingly support multilingual understanding and generation. Meanwhile, efforts to interpret their internal mechanisms have emerged, offering insights to enhance multilingual performance. While multi-head…

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…

Mixture of Experts (MoE) has become a key architectural paradigm for efficiently scaling Large Language Models (LLMs) by selectively activating a subset of parameters for each input token. However, standard MoE architectures face…

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

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…

Recent attempts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for multi-task adaptation of Large Language Models (LLMs) often replace whole attention/FFN layers with switch experts or append parallel expert branches,…

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…

Large language models (LLMs) have emerged due to their capability to generate high-quality content across diverse contexts. To reduce their explosively increasing demands for computing resources, a mixture of experts (MoE) has emerged. The…