Image de couverture de livre

Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Semantic Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Yanru, Eldele, Emadeldeen, Xie, Zongxia, Wang, Yucheng, Niu, Wenzhe, Hu, Qinghua, Kwoh, Chee Keong, Wu, Min
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Hierarchical Classification Auxiliary Network for Time Series Forecasting
par: Sun, Yanru, et autres
Publié: (2024)

Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
par: Sun, Yanru, et autres
Publié: (2024)

Label-efficient Time Series Representation Learning: A Review
par: Eldele, Emadeldeen, et autres
Publié: (2023)

PPGF: Probability Pattern-Guided Time Series Forecasting
par: Sun, Yanru, et autres
Publié: (2025)

Patch-wise Structural Loss for Time Series Forecasting
par: Kudrat, Dilfira, et autres
Publié: (2025)

LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
par: Niu, Wenzhe, et autres
Publié: (2025)

Lightweight Channel-wise Dynamic Fusion Model: Non-stationary Time Series Forecasting via Entropy Analysis
par: Jia, Tianyu, et autres
Publié: (2025)

SEED: Spectral Entropy-Guided Evaluation of SpatialTemporal Dependencies for Multivariate Time Series Forecasting
par: Xiong, Feng, et autres
Publié: (2025)

TSLANet: Rethinking Transformers for Time Series Representation Learning
par: Eldele, Emadeldeen, et autres
Publié: (2024)

A Unified Shape-Aware Foundation Model for Time Series Classification
par: Liu, Zhen, et autres
Publié: (2026)

Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
par: Abeywickrama, Sachith, et autres
Publié: (2025)

Time Series Domain Adaptation via Latent Invariant Causal Mechanism
par: Cai, Ruichu, et autres
Publié: (2025)

MSA-CNN: A Lightweight Multi-Scale CNN with Attention for Sleep Stage Classification
par: Goerttler, Stephan, et autres
Publié: (2025)

Learning Soft Sparse Shapes for Efficient Time-Series Classification
par: Liu, Zhen, et autres
Publié: (2025)

Target-specific Adaptation and Consistent Degradation Alignment for Cross-Domain Remaining Useful Life Prediction
par: Hou, Yubo, et autres
Publié: (2025)

Bridging Distribution Gaps in Time Series Foundation Model Pretraining with Prototype-Guided Normalization
par: Gong, Peiliang, et autres
Publié: (2025)

Evidentially Calibrated Source-Free Time-Series Domain Adaptation with Temporal Imputation
par: Ragab, Mohamed, et autres
Publié: (2024)

Evidential Domain Adaptation for Remaining Useful Life Prediction with Incomplete Degradation
par: Hou, Yubo, et autres
Publié: (2026)

Enhancing Time Series Forecasting via Multi-Level Text Alignment with LLMs
par: Zhao, Taibiao, et autres
Publié: (2025)

Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning
par: Wang, Hanxuan, et autres
Publié: (2025)

Enhancing LLMs for Time Series Forecasting via Structure-Guided Cross-Modal Alignment
par: Sun, Siming, et autres
Publié: (2025)

FOCUS: Frequency-Optimized Conditioning of DiffUSion Models for mitigating catastrophic forgetting during Test-Time Adaptation
par: Tjio, Gabriel, et autres
Publié: (2025)

TimeCatcher: A Variational Framework for Volatility-Aware Forecasting of Non-Stationary Time Series
par: Chen, Zhiyu, et autres
Publié: (2026)

UniFault: A Fault Diagnosis Foundation Model from Bearing Data
par: Eldele, Emadeldeen, et autres
Publié: (2025)

Enhancing Zero-Shot Time Series Forecasting in Off-the-Shelf LLMs via Noise Injection
par: Yin, Xingyou, et autres
Publié: (2025)

Physics-Informed Neural Networks in Electromagnetic and Nanophotonic Design
par: Abdelraouf, Omar A. M., et autres
Publié: (2025)

Time-Prompt: Integrated Heterogeneous Prompts for Unlocking LLMs in Time Series Forecasting
par: Wang, Zesen, et autres
Publié: (2025)

Graph Generation Powered with LLMs for Boosting Multivariate Time-Series Representation Learning
par: Wang, Yucheng, et autres
Publié: (2024)

Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data
par: Wang, Yucheng, et autres
Publié: (2023)

Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation
par: Wang, Yucheng, et autres
Publié: (2024)

Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach
par: Liu, Qingxiang, et autres
Publié: (2024)

Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
par: Hu, Yifan, et autres
Publié: (2025)

Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adapt
par: Zhang, YiFan, et autres
Publié: (2024)

Rethinking the Role of LLMs in Time Series Forecasting
par: Qiu, Xin, et autres
Publié: (2026)

TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding
par: Ding, Kuiye, et autres
Publié: (2025)

Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift
par: Chen, Mouxiang, et autres
Publié: (2023)

From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning
par: Niu, Wenzhe, et autres
Publié: (2026)

Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
par: Tao, Xiaoyu, et autres
Publié: (2024)

Attention as Robust Representation for Time Series Forecasting
par: Niu, PeiSong, et autres
Publié: (2024)

CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Network
par: Li, Chenglin, et autres
Publié: (2024)