Imagen de Portada

Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Guoqi, Wang, Juncheng, Yang, Chen, Qin, Jing, Aviles-Rivero, Angelica I., Wang, Shujun
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecasting
por: Yu, Guoqi, et al.
Publicado: (2025)

Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling
por: Yu, Guoqi, et al.
Publicado: (2024)

Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classification
por: Yu, Guoqi, et al.
Publicado: (2026)

NeuTSFlow: Modeling Continuous Functions Behind Time Series Forecasting
por: Xu, Huibo, et al.
Publicado: (2025)

CATO: Charted Attention for Neural PDE Operators
por: Cheng, Chun-Wun, et al.
Publicado: (2026)

Why Do Transformers Fail to Forecast Time Series In-Context?
por: Zhou, Yufa, et al.
Publicado: (2025)

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
por: Ke, Yekun, et al.
Publicado: (2024)

Product Interaction: An Algebraic Formalism for Deep Learning Architectures
por: Dong, Haonan, et al.
Publicado: (2026)

Test of Time: Rethinking Temporal Signal of Benchmark Contamination
por: Zhang, Terry Jingchen, et al.
Publicado: (2025)

PSformer: Parameter-efficient Transformer with Segment Attention for Time Series Forecasting
por: Wang, Yanlong, et al.
Publicado: (2024)

XicorAttention: Time Series Transformer Using Attention with Nonlinear Correlation
por: Kimura, Daichi, et al.
Publicado: (2025)

AlphaFace: High Fidelity and Real-time Face Swapper Robust to Facial Pose
por: Yu, Jongmin, et al.
Publicado: (2026)

TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
por: Wang, Yuxuan, et al.
Publicado: (2024)

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
por: Qiu, Haiquan, et al.
Publicado: (2025)

UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting
por: Liu, Juncheng, et al.
Publicado: (2024)

Correlation-Aware Select and Merge Attention for Efficient Fine-Tuning and Context Length Extension
por: Wang, Ning, et al.
Publicado: (2024)

CAPS: Unifying Attention, Recurrence, and Alignment in Transformer-based Time Series Forecasting
por: Pati, Viresh, et al.
Publicado: (2026)

Frequency Matters: When Time Series Foundation Models Fail Under Spectral Shift
por: Wang, Tianze, et al.
Publicado: (2025)

MediHive: A Decentralized Agent Collective for Medical Reasoning
por: Wang, Xiaoyang, et al.
Publicado: (2026)

Capture Timing-Attention of Events in Clinical Time Series
por: Li, Jia, et al.
Publicado: (2026)

Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification
por: Wang, Yihe, et al.
Publicado: (2024)

When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
por: Park, Min-Yeong, et al.
Publicado: (2025)

HTMformer: Hybrid Time and Multivariate Transformer for Time Series Forecasting
por: Wang, Tan, et al.
Publicado: (2025)

Labels Matter More Than Models: Rethinking the Unsupervised Paradigm in Time Series Anomaly Detection
por: Zhong, Zhijie, et al.
Publicado: (2025)

Attention as Robust Representation for Time Series Forecasting
por: Niu, PeiSong, et al.
Publicado: (2024)

PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting
por: Sun, Tian, et al.
Publicado: (2025)

Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting
por: Wang, Muyao, et al.
Publicado: (2024)

CorBenchX: Large-Scale Chest X-Ray Error Dataset and Vision-Language Model Benchmark for Report Error Correction
por: Zou, Jing, et al.
Publicado: (2025)

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling
por: Chen, Yuqi, et al.
Publicado: (2024)

FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation
por: Li, Runze, et al.
Publicado: (2025)

Efficient Linear Attention for Multivariate Time Series Modeling via Entropy Equality
por: Zhang, Mingtao, et al.
Publicado: (2025)

AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
por: Yang, Pei, et al.
Publicado: (2026)

RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals
por: Heo, Jaemu, et al.
Publicado: (2025)

Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluation
por: Kong, Yaxuan, et al.
Publicado: (2025)

Rethinking Time Encoding via Learnable Transformation Functions
por: Chen, Xi, et al.
Publicado: (2025)

Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
por: Wang, Hao, et al.
Publicado: (2025)

Toward Reasoning-Centric Time-Series Analysis
por: Wang, Xinlei, et al.
Publicado: (2025)

Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting
por: Nagrath, Saurish, et al.
Publicado: (2026)

DCMM-Transformer: Degree-Corrected Mixed-Membership Attention for Medical Imaging
por: Cheng, Huimin, et al.
Publicado: (2025)

Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
por: Zhang, Yang, et al.
Publicado: (2024)