Imagen de Portada

In-context Pre-trained Time-Series Foundation Models adapt to Unseen Tasks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Shangqing, Kamarthi, Harshavardhan, Liu, Haoxin, Prakash, B. Aditya
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Large Pre-trained time series models for cross-domain Time series analysis tasks
por: Kamarthi, Harshavardhan, et al.
Publicado: (2023)

Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning
por: Liu, Haoxin, et al.
Publicado: (2024)

How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook
por: Liu, Haoxin, et al.
Publicado: (2025)

Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis
por: Liu, Haoxin, et al.
Publicado: (2024)

Seeking Universal Shot Language Understanding Solutions
por: Liu, Haoxin, et al.
Publicado: (2026)

Hierarchical Industrial Demand Forecasting with Temporal and Uncertainty Explanations
por: Kamarthi, Harshavardhan, et al.
Publicado: (2026)

Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity
por: Kamarthi, Harshavardhan, et al.
Publicado: (2024)

TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
por: Zhao, Zhiyuan, et al.
Publicado: (2025)

Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting
por: Kamarthi, Harshavardhan, et al.
Publicado: (2024)

LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting
por: Liu, Haoxin, et al.
Publicado: (2024)

Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
por: Zhao, Zhiyuan, et al.
Publicado: (2025)

Performative Time-Series Forecasting
por: Zhao, Zhiyuan, et al.
Publicado: (2023)

A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization
por: Liu, Haoxin, et al.
Publicado: (2024)

Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
por: Liu, Haoxin, et al.
Publicado: (2026)

Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights
por: Liu, Haoxin, et al.
Publicado: (2025)

Finding Foundation Models for Time Series Classification with a PreText Task
por: Ismail-Fawaz, Ali, et al.
Publicado: (2023)

VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones
por: Shen, Lefei, et al.
Publicado: (2025)

Measuring Pre-training Data Quality without Labels for Time Series Foundation Models
por: Wen, Songkang, et al.
Publicado: (2024)

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

Cross-Domain Pre-training with Language Models for Transferable Time Series Representations
por: Cheng, Mingyue, et al.
Publicado: (2024)

Pre-training Epidemic Time Series Forecasters with Compartmental Prototypes
por: Liu, Zewen, et al.
Publicado: (2025)

Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs
por: Harshavardhan
Publicado: (2026)

Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models
por: Major, Noam, et al.
Publicado: (2026)

OSF: On Pre-training and Scaling of Sleep Foundation Models
por: Shuai, Zitao, et al.
Publicado: (2026)

LENS: Large Pre-trained Transformer for Exploring Financial Time Series Regularities
por: Xu, Yuanjian, et al.
Publicado: (2024)

A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks
por: Saha, Anish, et al.
Publicado: (2026)

QKCV Attention: Enhancing Time Series Forecasting with Static Categorical Embeddings for Both Lightweight and Pre-trained Foundation Models
por: Wang, Hao, et al.
Publicado: (2025)

TSI-Bench: Benchmarking Time Series Imputation
por: Du, Wenjie, et al.
Publicado: (2024)

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

Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification
por: Auer, Andreas, et al.
Publicado: (2025)

Using Pre-trained LLMs for Multivariate Time Series Forecasting
por: Wolff, Malcolm L., et al.
Publicado: (2025)

OATS: Online Data Augmentation for Time Series Foundation Models
por: Deng, Junwei, et al.
Publicado: (2026)

TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare
por: Song, Ziyang, et al.
Publicado: (2023)

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
por: Cao, Defu, et al.
Publicado: (2023)

How Foundational are Foundation Models for Time Series Forecasting?
por: Karaouli, Nouha, et al.
Publicado: (2025)

Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?
por: Sakai, Yusuke, et al.
Publicado: (2023)

Evaluating Time Series Foundation Models on Noisy Periodic Time Series
por: Gupta, Syamantak Datta
Publicado: (2025)

Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics
por: Bobrin, Maksim, et al.
Publicado: (2025)

Pre-trained Large Language Models Learn Hidden Markov Models In-context
por: Dai, Yijia, et al.
Publicado: (2025)

A Mamba Foundation Model for Time Series Forecasting
por: Ma, Haoyu, et al.
Publicado: (2024)