Mixture of Experts

Also known as MoE

Follow this topic Ask about this topic

Latest papers 216

37 papers in the last four weeks, up 32% on the four weeks before. 0.2% of all new papers.

All topics

DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE
Feb 20, 2026Yujie Jin, Wenxin Zhang, Jingjing Wang +1Video Understanding Mixture of Experts
School of Computer Science and Technology, Soochow University, Suzhou, China
A Theoretical Framework for Modular Learning of Robust Generative Models
Feb 19, 2026Corinna Cortes, Mehryar Mohri, Yutao ZhongGenerative Modeling Modular Neural Networks
Google Research, New York, NY · Courant Institute of Mathematical Sciences, New York, NY
ClusIR: Towards Cluster-Guided All-in-One Image Restoration
Dec 11, 2025Shengkai Hu, Jiaqi Ma, Xu Zhang +3Mixture of Experts All-in-One Image Restoration
Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates · Nanyang Technological University Singapore, Singapore
UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking
Nov 30, 2025Lingling Fu, Yongfu XueReward Modeling Reward Hacking
Guangxi University
MEGO: Learning Mixture-of-Experts for General-Purpose Binary Optimization
May 29, 2024Shengcai Liu, Zhiyuan Wang, Yew-Soon Ong +2Black-Box Optimization Mixture of Experts
Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China · College of Computing & Data Science, Nanyang Technological University, Singapore 639798 · School of Data Science, Lingnan University, Hong Kong, China
Regularized Estimation and Feature Selection in Mixtures of Generalized Linear Experts
Jul 14, 2019Thin Nguyen-Van, Faicel Chamroukhi, Ha Hoang Van +1Mixture of Experts Sparse Mixture-of-Experts
Faculty of Mathematics and Computer Science, University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam · IRT SystemX, 91120 Palaiseau, France +1

Feb 20, 2026J/K move · Enter open · S save

DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE

Yujie Jin, Wenxin Zhang, Jingjing Wang, Guodong Zhou

School of Computer Science and Technology, Soochow University, Suzhou, China

Video Understanding Mixture of Experts Physical Reasoning in Video Temporal Video Understanding

Open paper AskPDF arXiv

In the literature, prior research on Security-oriented Video Understanding (SVU) has predominantly focused on detecting and localize the threats (e.g., shootings, robberies) in videos, while largely lacking the effective capability to generate and evaluate the threat causes. Motivated by these gaps, this paper introduces a new chat paradigm SVU task, i.e., In-depth Security-oriented Video Understanding (DeepSVU), which aims to not only identify and locate the threats but also attribute and evaluate the causes threatening segments. Furthermore, this paper reveals two key challenges in the proposed task: 1) how to effectively model the coarse-to-fine physical-world information (e.g., human behavior, object interactions and background context) to boost the DeepSVU task; and 2) how to adaptively trade off these factors. To tackle these challenges, this paper proposes a new Unified Physical-world Regularized MoE (UPRM) approach. Specifically, UPRM incorporates two key components: the Unified Physical-world Enhanced MoE (UPE) Block and the Physical-world Trade-off Regularizer (PTR), to address the above two challenges, respectively. Extensive experiments conduct on our DeepSVU instructions datasets (i.e., UCF-C instructions and CUVA instructions) demonstrate that UPRM outperforms several advanced Video-LLMs as well as non-VLM approaches. Such information.These justify the importance of the coarse-to-fine physical-world information in the DeepSVU task and demonstrate the effectiveness of our UPRM in capturing such information.

Latest papers 216

DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE

A Theoretical Framework for Modular Learning of Robust Generative Models

ClusIR: Towards Cluster-Guided All-in-One Image Restoration

UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking

MEGO: Learning Mixture-of-Experts for General-Purpose Binary Optimization

Regularized Estimation and Feature Selection in Mixtures of Generalized Linear Experts