Imagen de Portada

S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Zihao, Dong, Juncheng, Yang, Haoming, Tarokh, Vahid
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Rethinking Token Prediction: Tree-Structured Diffusion Language Model
por: Wu, Zihao, et al.
Publicado: (2026)

Teleportation With Null Space Gradient Projection for Optimization Acceleration
por: Wu, Zihao, et al.
Publicado: (2025)

Offline Stochastic Optimization of Black-Box Objective Functions
por: Dong, Juncheng, et al.
Publicado: (2024)

Score-Based Metropolis-Hastings Algorithms
por: Aloui, Ahmed, et al.
Publicado: (2024)

Conditional Average Treatment Effect Estimation Under Hidden Confounders
por: Aloui, Ahmed, et al.
Publicado: (2025)

Parabolic Continual Learning
por: Yang, Haoming, et al.
Publicado: (2025)

Perceiver-based CDF Modeling for Time Series Forecasting
por: Le, Cat P., et al.
Publicado: (2023)

Elliptic Loss Regularization
por: Hasan, Ali, et al.
Publicado: (2025)

Neural McKean-Vlasov Processes: Distributional Dependence in Diffusion Processes
por: Yang, Haoming, et al.
Publicado: (2024)

CATE Estimation With Potential Outcome Imputation From Local Regression
por: Aloui, Ahmed, et al.
Publicado: (2023)

In-Context Reinforcement Learning From Suboptimal Historical Data
por: Dong, Juncheng, et al.
Publicado: (2026)

Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers
por: Dong, Juncheng, et al.
Publicado: (2026)

Learn2Mix: Training Neural Networks Using Adaptive Data Integration
por: Venkatasubramanian, Shyam, et al.
Publicado: (2024)

CARE: Turning LLMs Into Causal Reasoning Expert
por: Dong, Juncheng, et al.
Publicado: (2025)

Boosting In-Context Learning in LLMs Through the Lens of Classical Supervised Learning
por: Gundem, Korel, et al.
Publicado: (2025)

Neuro-Logic Lifelong Learning
por: He, Bowen, et al.
Publicado: (2025)

MSHyper: Multi-Scale Hypergraph Transformer for Long-Range Time Series Forecasting
por: Shang, Zongjiang, et al.
Publicado: (2024)

PASTA: A Unified Framework for Offline Assortment Learning
por: Dong, Juncheng, et al.
Publicado: (2025)

Sentinel: Multi-Patch Transformer with Temporal and Channel Attention for Time Series Forecasting
por: Villaboni, Davide, et al.
Publicado: (2025)

Learning Temporal Saliency for Time Series Forecasting with Cross-Scale Attention
por: Delibasoglu, Ibrahim, et al.
Publicado: (2025)

Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
por: Shang, Zongjiang, et al.
Publicado: (2024)

Enhancing Time Series Forecasting with Fuzzy Attention-Integrated Transformers
por: Chakraborty, Sanjay, et al.
Publicado: (2025)

Non-Stationary Time Series Forecasting Based on Fourier Analysis and Cross Attention Mechanism
por: Xiong, Yuqi, et al.
Publicado: (2025)

Frequency-Aware Attention-LSTM for PM$_{2.5}$ Time Series Forecasting
por: Lu, Jiahui, et al.
Publicado: (2025)

Diffusion-Based Hypothesis Testing and Change-Point Detection
por: Moushegian, Sean, et al.
Publicado: (2025)

Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks
por: Venkatasubramanian, Shyam, et al.
Publicado: (2023)

Steinmetz Neural Networks for Complex-Valued Data
por: Venkatasubramanian, Shyam, et al.
Publicado: (2024)

Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series
por: Yu, Guoqi, et al.
Publicado: (2026)

Revisiting Attention for Multivariate Time Series Forecasting
por: Wu, Haixiang
Publicado: (2024)

Why Attention Fails: The Degeneration of Transformers into MLPs in Time Series Forecasting
por: Liang, Zida, et al.
Publicado: (2025)

MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting
por: Cai, Wanlin, et al.
Publicado: (2023)

Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting
por: Chen, Peng, et al.
Publicado: (2024)

Multi-scale Transformer Pyramid Networks for Multivariate Time Series Forecasting
por: Zhang, Yifan, et al.
Publicado: (2023)

SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting
por: Xu, Xiongxiao, et al.
Publicado: (2024)

CC-Time: Cross-Model and Cross-Modality Time Series Forecasting
por: Chen, Peng, et al.
Publicado: (2025)

TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecasting
por: Liu, Zhipeng, et al.
Publicado: (2025)

Metadata Matters for Time Series: Informative Forecasting with Transformers
por: Dong, Jiaxiang, et al.
Publicado: (2024)

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

AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting
por: Zhang, Huanyao, et al.
Publicado: (2025)

CRAFT: Time Series Forecasting with Cross-Future Behavior Awareness
por: Zhang, Yingwei, et al.
Publicado: (2025)