Imagen de Portada

Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Lifan, Shen, Yanyan, Liu, Zhaoyang, Wang, Xue, Deng, Jiaji
Formato:	Preprint
Publicado:	2025
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

Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
por: Zhao, Lifan, et al.
Publicado: (2024)

Proactive Model Adaptation Against Concept Drift for Online Time Series Forecasting
por: Zhao, Lifan, et al.
Publicado: (2024)

Pruning Foundation Models for High Accuracy without Retraining
por: Zhao, Pu, et al.
Publicado: (2024)

Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling
por: Zhao, Sinong, et al.
Publicado: (2024)

Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptation
por: Tan, Jiayao, et al.
Publicado: (2024)

Discrete Prototypical Memories for Federated Time Series Foundation Models
por: Deng, Liwei, et al.
Publicado: (2026)

KairosHope: A Next-Generation Time-Series Foundation Model for Specialized Classification via Dual-Memory Architecture
por: Balderas, Luis, et al.
Publicado: (2026)

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

DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting
por: Zhao, Lifan, et al.
Publicado: (2023)

Less is More: Improving LLM Alignment via Preference Data Selection
por: Deng, Xun, et al.
Publicado: (2025)

Transformers and Their Roles as Time Series Foundation Models
por: Wu, Dennis, et al.
Publicado: (2025)

Lightweight Time Series Data Valuation on Time Series Foundation Models via In-Context Finetuning
por: Wu, Shunyu, et al.
Publicado: (2025)

UniCA: Unified Covariate Adaptation for Time Series Foundation Model
por: Han, Lu, et al.
Publicado: (2025)

Synthetic Series-Symbol Data Generation for Time Series Foundation Models
por: Wang, Wenxuan, et al.
Publicado: (2025)

A Time-Series Foundation Model by Universal Delay Embedding
por: Wang, Zijian, et al.
Publicado: (2025)

TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models
por: Li, Hongkai, et al.
Publicado: (2026)

Diversified Scaling Inference in Time Series Foundation Models
por: Hua, Ruijin, et al.
Publicado: (2026)

EIDOS: Latent-Space Predictive Learning for Time Series Foundation Models
por: Zhou, Xinxing, et al.
Publicado: (2026)

Less is More: Undertraining Experts Improves Model Upcycling
por: Horoi, Stefan, et al.
Publicado: (2025)

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

Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
por: Shen, Yuhao, et al.
Publicado: (2026)

Estimating Time Series Foundation Model Transferability via In-Context Learning
por: Yao, Qingren, et al.
Publicado: (2025)

Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
por: Masserano, Luca, et al.
Publicado: (2024)

Black-Box Time-Series Domain Adaptation via Cross-Prompt Foundation Models
por: Furqon, M. T., et al.
Publicado: (2025)

Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation
por: Wang, Wenxuan, et al.
Publicado: (2025)

Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
por: Liu, Zhining, et al.
Publicado: (2025)

This Time is Different: An Observability Perspective on Time Series Foundation Models
por: Cohen, Ben, et al.
Publicado: (2025)

TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
por: Cao, Defu, et al.
Publicado: (2024)

Foundation Models for Time Series: A Survey
por: Kottapalli, Siva Rama Krishna, et al.
Publicado: (2025)

Time-Prompt: Integrated Heterogeneous Prompts for Unlocking LLMs in Time Series Forecasting
por: Wang, Zesen, et al.
Publicado: (2025)

Transformer Multivariate Forecasting: Less is More?
por: Xu, Jingjing, et al.
Publicado: (2023)

Wisdom of Committee: Distilling from Foundation Model to Specialized Application Model
por: Liu, Zichang, et al.
Publicado: (2024)

Time Series Foundation Models for Process Model Forecasting
por: Yu, Yongbo, et al.
Publicado: (2025)

Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs
por: Chang, Qian, et al.
Publicado: (2026)

Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment
por: Liu, Jun, et al.
Publicado: (2024)

Less is More: on the Over-Globalizing Problem in Graph Transformers
por: Xing, Yujie, et al.
Publicado: (2024)

Cut Less, Fold More: Model Compression through the Lens of Projection Geometry
por: Saukh, Olga, et al.
Publicado: (2026)

Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling
por: Liu, Yiding, et al.
Publicado: (2026)

When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs
por: Wang, Keyu, et al.
Publicado: (2025)

OLMA: One Loss for More Accurate Time Series Forecasting
por: Shi, Tianyi, et al.
Publicado: (2025)