In-Context Inpainting for Time Series Forecasting
cs.AI
Submitted: 2026-08-24
Updated: 2026-08-24
Code: https://github.com/zhouhaoyi/ETDataset
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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).
Terminology
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.
Sources
- ChartLlama: A Multimodal LLM for Chart Understanding and Generation
- OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting
- SVTime: Small Time Series Forecasting Models Informed by "Physics" of Large Vision Model Forecasters
- VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones
- Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review
- Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems