arXiv AI August 26, 2026 By Thang Nguyen, Dung Nguyen, Romero Morais, Truyen Tran

In-Context Inpainting for Time Series Forecasting

The paper introduces ICI-Time, a framework that casts time series forecasting as a visual inpainting problem. By converting series into area‑chart images, it enables pre‑trained vision transformers to perform forecasting through in‑context learning without fine‑tuning or new temporal architectures. Experiments on epidemiology, meteorology, and power systems show competitive performance and strong adaptability in low‑data scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Aug 24

In-Context Inpainting for Time Series Forecasting

We propose ICI-Time, a novel framework that reframes time series forecasting as a visual inpainting task, leveraging the generalisation power of large vision models (LVMs). Unlike methods that require...

llms fine-tuning

arXiv AI

Jun 9

VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion

arXiv:2510. 03244v2 Announce Type: replace-cross Abstract: Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores crucial cross-channel dependencies.

By Yanlong Wang, Hang Yu, Jian Xu, Fei Ma, Hongkang Zhang, Tongtong Feng, Zijian Zhang, Shao-Lun Huang, Danny Dongning Sun, Xiao-Ping Zhang

multimodal benchmarks

arXiv AI

Jun 15

MP3: Multi-Period Pattern Pre-training for Spatio-Temporal Forecasting

arXiv:2606. 13119v2 Announce Type: replace-cross Abstract: Spatio-Temporal forecasting is crucial in diverse fields, such as transportation, climate, and energy.

By Lilan Peng, Yandi Liu, Qingren Yao, Chongshou Li, Tianrui Li

llms

arXiv Machine Learning

Jul 16

Overcoming the Modality Gap in Context-Aided Forecasting

arXiv:2603. 12451v4 Announce Type: replace Abstract: Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods.

By Vincent Zhihao Zheng, \'Etienne Marcotte, Arjun Ashok, Andrew Robert Williams, Lijun Sun, Alexandre Drouin, Valentina Zantedeschi

multimodal

arXiv AI

Jun 12

MP3: Multi-Period Pattern Pre-training forSpatio-Temporal Forecasting

arXiv:2606. 13119v1 Announce Type: cross Abstract: Spatio-Temporal forecasting is crucial in diverse fields, such as transportation, climate, and energy.

By Lilan Peng, Yandi Liu, Qingren Yao, Chongshou Li, Tianrui Li

llms

arXiv Machine Learning

4d ago

PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting

arXiv:2601.20845v2 Announce Type: replace Abstract: Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require do...

By Olaf Yunus Laitinen Imanov, Derya Umut Kulali, Taner Yilmaz

llms fine-tuning efficiency benchmarks

One email a morning, machine-written

Related stories

In-Context Inpainting for Time Series Forecasting

VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion

MP3: Multi-Period Pattern Pre-training for Spatio-Temporal Forecasting

Overcoming the Modality Gap in Context-Aided Forecasting

MP3: Multi-Period Pattern Pre-training forSpatio-Temporal Forecasting

PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting