English
Related papers

Related papers: Switch-Hurdle: A MoE Encoder with AR Hurdle Decode…

200 papers

Wearable sensors provide abundant physiological time series, yet the principles governing their predictive utility remain unclear. We hypothesize that temporal resolution is a fundamental axis of representation learning, with different…

Neural shape representation generally refers to representing 3D geometry using neural networks, e.g., computing a signed distance or occupancy value at a specific spatial position. In this paper we present a neural-network architecture…

Machine Learning · Computer Science 2024-08-22 Stefan Rhys Jeske , Jonathan Klein , Dominik L. Michels , Jan Bender

This study proposes an Ensemble Differential Evolution with Simula-tion-Based Hybridization and Self-Adaptation (EDESH-SA) approach for inven-tory management (IM) under uncertainty. In this study, DE with multiple runs is combined with a…

Optimization and Control · Mathematics 2023-10-16 Sarit Maitra , Vivek Mishra , Sukanya Kundu

Most unsupervised anomaly detection methods based on representations of normal samples to distinguish anomalies have recently made remarkable progress. However, existing methods only learn a single decision boundary for distinguishing the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Tianwu Lei , Silin Chen , Bohan Wang , Zhengkai Jiang , Ningmu Zou

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…

Machine Learning · Computer Science 2025-09-24 Yujiao Yang , Jing Lian , Linhui Li

Zero-shot forecasting aims to predict outcomes for previously unseen conditions without direct historical data, posing a significant challenge for traditional forecasting methods. We introduce a Resolution-Aware Retrieval-Augmented…

Machine Learning · Computer Science 2025-10-21 Iman Deznabi , Peeyush Kumar , Madalina Fiterau

Despite many recent works on Mixture of Experts (MoEs) for resource-efficient Transformer language models, existing methods mostly focus on MoEs for feedforward layers. Previous attempts at extending MoE to the self-attention layer fail to…

Machine Learning · Computer Science 2024-10-02 Róbert Csordás , Piotr Piękos , Kazuki Irie , Jürgen Schmidhuber

Encoder-decoder-based recurrent neural network (RNN) has made significant progress in sequence-to-sequence learning tasks such as machine translation and conversational models. Recent works have shown the advantage of this type of network…

Machine Learning · Computer Science 2023-05-10 Jing Xiong , Pengyang Zhou , Alan Chen , Yu Zhang

As foundational models reshape scientific discovery, a bottleneck persists in dynamical system reconstruction (DSR): the ability to learn across system hierarchies. Many meta-learning approaches have been applied successfully to single…

Machine Learning · Computer Science 2025-06-12 Roussel Desmond Nzoyem , Grant Stevens , Amarpal Sahota , David A. W. Barton , Tom Deakin

Seismic acoustic impedance inversion is a challenging problem in geophysical exploration, primarily due to the scarcity of well-logging data and the inherent nonlinearity of the task. Most existing inversion methods, including…

Geophysics · Physics 2025-11-25 Junheng Peng , Yingtian Liu , Xiaowen Wang , Yong Li , Mingwei Wang

Learning an effective similarity measure between image representations is key to the success of recent advances in visual search tasks (e.g. verification or zero-shot learning). Although the metric learning part is well addressed, this…

Computer Vision and Pattern Recognition · Computer Science 2019-08-08 Pierre Jacob , David Picard , Aymeric Histace , Edouard Klein

Time series forecasting is an important task in many fields ranging from supply chain management to weather forecasting. Recently, Transformer neural network architectures have shown promising results in forecasting on common time series…

Machine Learning · Computer Science 2024-08-08 Rares Cristian , Pavithra Harsha , Clemente Ocejo , Georgia Perakis , Brian Quanz , Ioannis Spantidakis , Hamza Zerhouni

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…

Machine Learning · Computer Science 2026-03-03 Xing Han , Hsing-Huan Chung , Joydeep Ghosh , Paul Pu Liang , Suchi Saria

Item Price Elasticity is used to quantify the responsiveness of consumer demand to changes in item prices, enabling businesses to create pricing strategies and optimize revenue management. Sectors such as store retail, e-commerce, and…

Machine Learning · Computer Science 2026-05-12 Lakshya Garg , Sai Yaswanth , Deep Narayan Mishra , Karthik Kumaran , Anupriya Sharma , Mayank Uniyal

Sparsely-gated mixture-of-experts (MoE) has been widely adopted to scale deep learning models to trillion-plus parameters with fixed computational cost. The algorithmic performance of MoE relies on its token routing mechanism that forwards…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-06-06 Changho Hwang , Wei Cui , Yifan Xiong , Ziyue Yang , Ze Liu , Han Hu , Zilong Wang , Rafael Salas , Jithin Jose , Prabhat Ram , Joe Chau , Peng Cheng , Fan Yang , Mao Yang , Yongqiang Xiong

Recently, Mixture of Experts (MoE) based Transformer has shown promising results in many domains. This is largely due to the following advantages of this architecture: firstly, MoE based Transformer can increase model capacity without…

Sound · Computer Science 2021-05-10 Zhao You , Shulin Feng , Dan Su , Dong Yu

Residual networks, as discrete approximations of Ordinary Differential Equations (ODEs), have inspired significant advancements in neural network design, including multistep methods, high-order methods, and multi-particle dynamical systems.…

Computation and Language · Computer Science 2024-11-06 Bei Li , Tong Zheng , Rui Wang , Jiahao Liu , Qingyan Guo , Junliang Guo , Xu Tan , Tong Xiao , Jingbo Zhu , Jingang Wang , Xunliang Cai

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling neural networks while maintaining computational efficiency. However, standard MoE implementations rely on two rigid design assumptions: (1) fixed Top-K…

Machine Learning · Computer Science 2026-03-03 Gökdeniz Gülmez

Standard decoding approaches rely on model-based channel estimation methods to compensate for varying channel effects, which degrade in performance whenever there is a model mismatch. Recently proposed Deep learning based neural decoders…

Signal Processing · Electrical Eng. & Systems 2019-03-07 Yihan Jiang , Hyeji Kim , Himanshu Asnani , Sreeram Kannan

This project addresses the challenge of human motion prediction, a critical area for applications such as au- tonomous vehicle movement detection. Previous works have emphasized the need for low inference times to provide real time…

Computer Vision and Pattern Recognition · Computer Science 2024-05-13 Edmund Shieh , Joshua Lee Franco , Kang Min Bae , Tej Lalvani