aiqbench analysis
ICI-Time reframes time series forecasting as a visual inpainting task, leveraging pre-trained large vision models to solve temporal prediction without fine-tuning or architectural changes. By mapping numerical data to spatial layouts, this approach demonstrates strong adaptability in limited-data scenarios across domains like epidemiology and power systems using standard grid-structured prompts.
In-Context Inpainting for Time Series Forecasting
arXiv:2608.23855v1 Announce Type: new Abstract: 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 specialised temporal architectures and extensive domain-specific training, ICI-Time transforms time series into structured visual representations (area charts) and applies visual in-context learning, reformulating forecasting as pattern completion within a grid-structured prompt that pre-trained vision transformers can solve without fine-tuning or architectural modification. Temporal dependencies are represented through spatial layout, with a consistent, invertible mapping between numerical and visual domains. Extensive experiments across epidemiology, meteorology, and power systems demonstrate that ICI-Time performs competitively against deep learning baselines and shows promising adaptability under limited-data settings, introducing a new paradigm that bridges temporal and visual domains.
Abstract: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 specialised temporal architectures and extensive domain-specific training, ICI-Time transforms time series into structured visual representations (area charts) and applies visual in-context learning, reformulating forecasting as pattern completion within a grid-structured prompt that pre-trained vision transformers can solve without fine-tuning or architectural modification. Temporal dependencies are represented through spatial layout, with a consistent, invertible mapping between numerical and visual domains. Extensive experiments across epidemiology, meteorology, and power systems demonstrate that ICI-Time performs competitively against deep learning baselines and shows promising adaptability under limited-data settings, introducing a new paradigm that bridges temporal and visual domains.
Artificial Intelligence (cs.AI)
arXiv:2608.23855 [cs.AI]
(or arXiv:2608.23855v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.23855 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 216 words
Related coverage
Introducing Timestral
Mistral AI · Oct 15, 2026
Real-Time Intelligence with IBM Time Series Models on Confluent
Hugging Face · Sep 2, 2026
World2TS: Real-World Event Context for Time-Series Forecasting
arXiv · Oct 14, 2026
OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning
arXiv · Oct 1, 2026