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

Hugging Face Trending Papers

Sep 21

MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting

Multivariate time-series forecasting is essential to many real-world applications. Recent large vision models (LVMs) offer a promising paradigm by transferring cross-domain visual priors to time-serie...

benchmarks

arXiv Machine Learning

Sep 22

MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting

arXiv:2609.24441v1 Announce Type: new Abstract: Multivariate time-series forecasting is essential to many real-world applications. Recent large vision models (LVMs) offer a promising paradigm by tran...

By Xinying Cai, Junkai Lu, Yuhan Zhu, Xiaoyun Yu, Xiangfei Qiu, Jilin Hu

benchmarks

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

Oct 1

WinoTS: Wavelet-based Self-Distillation for Time Series Models

WinoTS introduces a wavelet‑based self‑distillation framework for time‑series models that uses time‑frequency augmentations to create multi‑scale structural views, avoiding distortion of signal dynamics. The method outperforms state‑of‑the‑art baselines in long‑term forecasting, cross‑domain zero‑shot transfer, and unsupervised anomaly detection, and linear probing on frozen representations often beats fully supervised training from scratch. Ablation studies show WinoTS is architecture‑agnostic and demonstrates that time‑frequency transformations offer a principled alternative to vision‑style spatial augmentations.

By Noam Major, Kathy Razmadze, Yoli Shavit

computer-vision efficiency 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

One email a morning, machine-written

Related stories

In-Context Inpainting for Time Series Forecasting

MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting

MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting

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

WinoTS: Wavelet-based Self-Distillation for Time Series Models

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