English
Related papers

Related papers: Uni-Perceiver-MoE: Learning Sparse Generalist Mode…

200 papers

Despite the remarkable success of foundation models, their task-specific fine-tuning paradigm makes them inconsistent with the goal of general perception modeling. The key to eliminating this inconsistency is to use generalist models for…

Computer Vision and Pattern Recognition · Computer Science 2022-11-18 Hao Li , Jinguo Zhu , Xiaohu Jiang , Xizhou Zhu , Hongsheng Li , Chun Yuan , Xiaohua Wang , Yu Qiao , Xiaogang Wang , Wenhai Wang , Jifeng Dai

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…

Machine Learning · Computer Science 2026-04-27 Zehua Pei , Ying Zhang , Hui-Ling Zhen , Tao Yuan , Xianzhi Yu , Zhenhua Dong , Sinno Jialin Pan , Mingxuan Yuan , Bei Yu

Mixture of Experts (MoE) models have become central to scaling large language models, yet their mechanistic differences from dense networks remain poorly understood. Previous work has explored how dense models use \textit{superposition} to…

Machine Learning · Computer Science 2025-12-29 Marmik Chaudhari , Jeremi Nuer , Rome Thorstenson

We hypothesize that due to the greedy nature of learning in multi-modal deep neural networks, these models tend to rely on just one modality while under-fitting the other modalities. Such behavior is counter-intuitive and hurts the models'…

Machine Learning · Computer Science 2022-09-20 Nan Wu , Stanisław Jastrzębski , Kyunghyun Cho , Krzysztof J. Geras

Advances in multimodal models have greatly improved how interactions relevant to various tasks are modeled. Today's multimodal models mainly focus on the correspondence between images and text, using this for tasks like image-text matching.…

Computation and Language · Computer Science 2024-09-27 Haofei Yu , Zhengyang Qi , Lawrence Jang , Ruslan Salakhutdinov , Louis-Philippe Morency , Paul Pu Liang

Mixture of Experts (MoE) offers remarkable performance and computational efficiency by selectively activating subsets of model parameters. Traditionally, MoE models use homogeneous experts, each with identical capacity. However, varying…

Computation and Language · Computer Science 2024-08-21 An Wang , Xingwu Sun , Ruobing Xie , Shuaipeng Li , Jiaqi Zhu , Zhen Yang , Pinxue Zhao , J. N. Han , Zhanhui Kang , Di Wang , Naoaki Okazaki , Cheng-zhong Xu

Mixture-of-Experts (MoE) is a flexible framework that combines multiple specialized submodels (``experts''), by assigning covariate-dependent weights (``gating functions'') to each expert, and have been commonly used for analyzing…

Methodology · Statistics 2026-01-06 Qicheng Zhao , Celia M. T. Greenwood , Qihuang Zhang

Learning from multiple domains is a primary factor that influences the generalization of a single unified robot system. In this paper, we aim to learn the trajectory prediction model by using broad out-of-domain data to improve its…

Robotics · Computer Science 2025-04-02 Jiange Yang , Haoyi Zhu , Yating Wang , Gangshan Wu , Tong He , Limin Wang

How sensitive should machine learning models be to input changes? We tackle the question of model smoothness and show that it is a useful inductive bias which aids generalization, adversarial robustness, generative modeling and…

Machine Learning · Statistics 2021-07-08 Mihaela Rosca , Theophane Weber , Arthur Gretton , Shakir Mohamed

Mixture of experts (MoE) models are a class of artificial neural networks that can be used for functional approximation and probabilistic modeling. An important class of MoE models is the class of mixture of linear experts (MoLE) models,…

Methodology · Statistics 2019-05-29 Hien D. Nguyen , Faicel Chamroukhi , Florence Forbes

According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language…

Computation and Language · Computer Science 2024-03-19 Sungjun Han , Sebastian Padó

Sparse Mixture of Experts (SMoE) enables scalable parameter growth in large language models (LLMs) by selectively activating a subset of experts, and its large parameter count necessitates distributed deployment for inference. However,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-07 Yu Han , Lehan Pan , Jie Peng , Ziyang Tao , Hanqi Zhu , Wuyang Zhang , Yanyong Zhang

Adapting Large Language Models (LLMs) to a continuous stream of tasks is a critical yet challenging endeavor. While Parameter-Efficient Fine-Tuning (PEFT) methods have become a standard for this, they face a fundamental dilemma in continual…

Machine Learning · Computer Science 2025-11-11 Haeyong Kang

Mixture-of-Experts (MoE) architectures enable conditional computation by activating only a subset of model parameters for each input. Although sparse routing has been highly effective in language models and has also shown promise in vision,…

Machine Learning · Computer Science 2026-04-07 Vadim Vashkelis , Natalia Trukhina

This work proposes a new data-driven model devised to integrate process knowledge into its structure to increase the human-machine synergy in the process industry. The proposed Contextual Mixture of Experts (cMoE) explicitly uses process…

Machine Learning · Computer Science 2022-11-02 Francisco Souza , Tim Offermans , Ruud Barendse , Geert Postma , Jeroen Jansen

Mixture of Experts (MoE) are rising in popularity as a means to train extremely large-scale models, yet allowing for a reasonable computational cost at inference time. Recent state-of-the-art approaches usually assume a large number of…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Amelie Royer , Ilia Karmanov , Andrii Skliar , Babak Ehteshami Bejnordi , Tijmen Blankevoort

This paper introduces the "Uncertainty-aware Mixture of Experts" (uMoE), a novel solution aimed at addressing aleatoric uncertainty within Neural Network (NN) based predictive models. While existing methodologies primarily concentrate on…

Machine Learning · Statistics 2024-04-26 Lucas Luttner

Multimodal learning leverages the integration of diverse data modalities to enhance performance in complex tasks. Yet, it frequently encounters incomplete or redundant modality data in real-world scenarios. This paper presents a…

Machine Learning · Computer Science 2026-05-05 Richeng Zhou , Xuelin Zhang , Liyuan Liu

Sparse models, including sparse Mixture-of-Experts (MoE) models, have emerged as an effective approach for scaling Transformer models. However, they often suffer from computational inefficiency since a significant number of parameters are…

Machine Learning · Computer Science 2024-05-27 Yuanhang Yang , Shiyi Qi , Wenchao Gu , Chaozheng Wang , Cuiyun Gao , Zenglin Xu

Large language models (LLMs) based on transformers have made significant strides in recent years, the success of which is driven by scaling up their model size. Despite their high algorithmic performance, the computational and memory…

Machine Learning · Computer Science 2024-04-30 Ranggi Hwang , Jianyu Wei , Shijie Cao , Changho Hwang , Xiaohu Tang , Ting Cao , Mao Yang