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.

Related

• VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion
• Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting
• The Hidden Evolution of Disguised Visual Context inside the VLM
• AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse

Source: arXiv cs.AI | 2026-08-26