Related papers: Learning How Much to Think: Difficulty-Aware Dynam…

Mixture-of-Experts (MoE) models improve transformer efficiency but lack a unified theoretical explanation, especially when both feed-forward and attention layers are allowed to specialize. To this end, we study the Mixture-of-Transformers…

Mixture-of-Experts (MoE) models offer immense capacity via sparsely gated expert subnetworks, yet adapting them to multiple domains without catastrophic forgetting remains an open challenge. Existing approaches either incur prohibitive…

Learning a graph topology to reveal the underlying relationship between data entities plays an important role in various machine learning and data analysis tasks. Under the assumption that structured data vary smoothly over a graph, the…

Mixture-of-Experts (MoE) model architectures can significantly reduce the number of activated parameters per token, enabling computationally efficient training and inference. However, their large overall parameter counts and model sizes…

Modern applications increasingly involve many heterogeneous input streams, such as clinical sensors, wearable device data, imaging, and text, each with distinct measurement models, sampling rates, and noise characteristics. We define this…

In a distributed mixture-of-experts (MoE) system, a server collaborates with multiple specialized expert clients to perform inference. The server extracts features from input data and dynamically selects experts based on their areas of…

In the quest to improve efficiency, interdependence and complexity are becoming defining characteristics of modern complex networks representing engineered and natural systems. Graph theory is a widely used framework for modeling such…

\emph{Over-fitting} and \emph{over-smoothing} are two main obstacles of developing deep Graph Convolutional Networks (GCNs) for node classification. In particular, over-fitting weakens the generalization ability on small dataset, while…

Mixture-of-Experts (MoE) layers have emerged as an important tool in scaling up modern neural networks by decoupling total trainable parameters from activated parameters in the forward pass for each token. However, sparse MoEs add…

Preference-based reinforcement learning offers a scalable alternative to manual reward engineering by learning reward structures from comparative feedback. However, large-scale preference datasets, whether collected from crowdsourced…

Graph neural networks (GNN) have been ubiquitous in graph node classification tasks. Most of GNN methods update the node embedding iteratively by aggregating its neighbors' information. However, they often suffer from negative disturbance,…

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer from two critical limitations: (1) inefficient token-to-expert…

Mixture-of-Experts (MoE) models mostly use a router to assign tokens to specific expert modules, activating only partial parameters and often outperforming dense models. We argue that the separation between the router's decision-making and…

We propose Tensor-Trained Low-Rank Adaptation Mixture of Experts (TT-LoRA MoE), a novel computational framework integrating Parameter-Efficient Fine-Tuning (PEFT) with sparse MoE routing to address scalability challenges in large model…

Multimodal Mixture-of-Experts (MoE) models offer a promising path toward scalable and efficient large vision-language systems. However, existing approaches rely on rigid routing strategies (typically activating a fixed number of experts per…

Mixture-of-Experts (MoE) models offer dynamic computation, but are typically deployed as static full-capacity models, missing opportunities for deployment-specific specialization. We introduce PreMoE, a training-free framework that…

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) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…

The Mixture of Experts (MoE) architecture enables the scaling of Large Language Models (LLMs) to trillions of parameters by activating a sparse subset of weights for each input, maintaining constant computational cost during inference.…

The Mixture-of-Experts (MoE) architecture has become a predominant paradigm for scaling large language models (LLMs). Despite offering strong performance and computational efficiency, large MoE-based LLMs like DeepSeek-V3-0324 and…