相关论文: M3oE: Multi-Domain Multi-Task Mixture-of Experts R…

Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost of training and evaluating models. Efficient Pareto front…

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…

The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE…

Model editing aims to efficiently alter the behavior of Large Language Models (LLMs) within a desired scope, while ensuring no adverse impact on other inputs. Recent years have witnessed various model editing methods been proposed. However,…

In today's digital landscape, Deep Recommender Systems (DRS) play a crucial role in navigating and customizing online content for individual preferences. However, conventional methods, which mainly depend on single recommendation task,…

Low-Rank Adaptation (LoRA) is widely used for adapting large language models (LLMs) to specific domains due to its efficiency and modularity. Meanwhile, vanilla LoRA struggles with task conflicts in multi-task scenarios. Recent works adopt…

Despite over a decade of development, autonomous driving trajectory planning in complex urban environments continues to encounter significant challenges. These challenges include the difficulty in accommodating the multi-modal nature of…

Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning. Mixture-of-experts (MoE) provides a promising solution with a dynamic architecture, enabling effective task decoupling. However,…

Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely, minimizing computational overhead. To mitigate the prohibitive cost of training MoEs from scratch, recent work employs upcycling,…

Remote sensing data analysis and interpretation present unique challenges due to the diversity in sensor modalities and spatiotemporal dynamics of Earth observation data. Mixture-of-Experts (MoE) model has emerged as a powerful paradigm…

Underwater acoustic target recognition is a difficult task owing to the intricate nature of underwater acoustic signals. The complex underwater environments, unpredictable transmission channels, and dynamic motion states greatly impact the…

Mixture-of-Experts (MoE) models increase representational capacity with modest computational cost, but their effectiveness in specialized domains such as medicine is limited by small datasets. In contrast, clinical practice offers rich…

Many data have an underlying dependence on spatial location; it may be weather on the Earth, a simulation on a mesh, or a registered image. Yet this feature is rarely taken advantage of, and violates common assumptions made by many neural…

Healthcare systems generate diverse multimodal data, including Electronic Health Records (EHR), clinical notes, and medical images. Effectively leveraging this data for clinical prediction is challenging, particularly as real-world samples…

Recently, Mixture-of-Experts (short as MoE) architecture has achieved remarkable success in increasing the model capacity of large-scale language models. However, MoE requires incorporating significantly more parameters than the base model…

Multi-task learning (MTL) enables the efficient transfer of extra knowledge acquired from other tasks. The high correlation between multimodal sentiment analysis (MSA) and multimodal emotion recognition (MER) supports their joint training.…

Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead. We introduce a unified framework based on dynamic expert clustering and structured compression to…

In this report, we describe the technical details of our submission to the 2021 EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition. Leveraging multiple modalities has been proved to benefit the Unsupervised…

Mixture-of-Experts (MoE) enhances model performance while maintaining computational efficiency, making it well-suited for large-scale applications. Conventional mixture-of-experts (MoE) architectures suffer from suboptimal coordination…

Training AI models that generalize across tasks and domains has long been among the open problems driving AI research. The emergence of Foundation Models made it easier to obtain expert models for a given task, but the heterogeneity of data…