Copertina

TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lin, Jiafeng, Wang, Yuxuan, Luo, Huakun, Pei, Zhongyi, Wang, Jianmin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Thoth: Mid-Training Bridges LLMs to Time Series Understanding
di: Lin, Jiafeng, et al.
Pubblicazione: (2026)

Aura: Universal Multi-dimensional Exogenous Integration for Aviation Time Series
di: Lin, Jiafeng, et al.
Pubblicazione: (2026)

Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models
di: Qiu, Yunzhong, et al.
Pubblicazione: (2026)

DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters
di: Zhang, Haoran, et al.
Pubblicazione: (2026)

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

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
di: Liu, Xu, et al.
Pubblicazione: (2024)

Transolver: A Fast Transformer Solver for PDEs on General Geometries
di: Wu, Haixu, et al.
Pubblicazione: (2024)

TimesBERT: A BERT-Style Foundation Model for Time Series Understanding
di: Zhang, Haoran, et al.
Pubblicazione: (2025)

DualWeaver: Synergistic Feature Weaving Surrogates for Multivariate Forecasting with Univariate Time Series Foundation Models
di: Li, Jinpeng, et al.
Pubblicazione: (2026)

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

Mixture-of-Linear-Experts for Long-term Time Series Forecasting
di: Ni, Ronghao, et al.
Pubblicazione: (2023)

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

RoPINN: Region Optimized Physics-Informed Neural Networks
di: Wu, Haixu, et al.
Pubblicazione: (2024)

Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
di: Chen, Peng, et al.
Pubblicazione: (2026)

Deep Time Series Models: A Comprehensive Survey and Benchmark
di: Wang, Yuxuan, et al.
Pubblicazione: (2024)

TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling
di: Dong, Jiaxiang, et al.
Pubblicazione: (2024)

Task-Aware Mixture-of-Experts for Time Series Analysis
di: Wu, Xingjian, et al.
Pubblicazione: (2025)

AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
di: Wang, Rui, et al.
Pubblicazione: (2026)

Wavelet Mixture of Experts for Time Series Forecasting
di: Zhou, Zheng, et al.
Pubblicazione: (2025)

Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
di: Liu, Yong, et al.
Pubblicazione: (2024)

Mixture of Online and Offline Experts for Non-stationary Time Series
di: Zhao, Zhilin, et al.
Pubblicazione: (2022)

Timer: Generative Pre-trained Transformers Are Large Time Series Models
di: Liu, Yong, et al.
Pubblicazione: (2024)

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
di: Shi, Xiaoming, et al.
Pubblicazione: (2024)

TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
di: Wang, Shiyu, et al.
Pubblicazione: (2024)

MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models
di: Liu, Yiwen, et al.
Pubblicazione: (2025)

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

Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration
di: Mahtout, Btissame El, et al.
Pubblicazione: (2026)

Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
di: Liu, Qingxiang, et al.
Pubblicazione: (2024)

AnyExperts: On-Demand Expert Allocation for Multimodal Language Models with Mixture of Expert
di: Gao, Yuting, et al.
Pubblicazione: (2025)

Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometries
di: Luo, Huakun, et al.
Pubblicazione: (2025)

Seg-MoE: Multi-Resolution Segment-wise Mixture-of-Experts for Time Series Forecasting Transformers
di: Ortigossa, Evandro S., et al.
Pubblicazione: (2026)

MoTE: Mixture of Ternary Experts for Memory-efficient Large Multimodal Models
di: Wang, Hongyu, et al.
Pubblicazione: (2025)

R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts
di: Li, Zhongyang, et al.
Pubblicazione: (2025)

Multi-Modal Time Series Prediction via Mixture of Modulated Experts
di: Zhang, Lige, et al.
Pubblicazione: (2026)

Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
di: Nochumsohn, Liran, et al.
Pubblicazione: (2025)

UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting
di: Liu, Xu, et al.
Pubblicazione: (2023)

Exploring Accuracy Law for Deep Time Series Forecasters: An Empirical Study
di: Wang, Yuxuan, et al.
Pubblicazione: (2025)

ViTs: Teaching Machines to See Time Series Anomalies Like Human Experts
di: Wang, Zexin, et al.
Pubblicazione: (2025)

Time Tracker: Mixture-of-Experts-Enhanced Foundation Time Series Forecasting Model with Decoupled Training Pipelines
di: Liang, Aobo, et al.
Pubblicazione: (2025)

Mixture Experts with Test-Time Self-Supervised Aggregation for Tabular Imbalanced Regression
di: Wang, Yung-Chien, et al.
Pubblicazione: (2025)