KALEIDO: Input-Space Adaptation of a Vision Model for Time-Series Forecasting Through Gated Fold Geometries

arXiv:2610.04786 · cs.LG, cs.CV · Submitted 2026-10-03 · Read on arXiv

cs.LG, cs.CV

Submitted: 2026-10-03

Updated: 2026-10-03

Comments: Accepted at the NeurIPS 2026 Workshop on Foundation Models for Temporal Systems (FMTS)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 1× in this paper · explained in 1 episode

Sources

• GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
• Chronos: Learning the Language of Time Series
• VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
• Masked Autoencoders Are Scalable Vision Learners
• Times2D: Multi-Period Decomposition and Derivative Mapping for General Time Series Forecasting
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting
• VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones
• Unified Training of Universal Time Series Forecasting Transformers
• TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
• SSDA: Bridging Spectral and Structural Gaps via Dual Adaptation for Vision-Based Time Series Forecasting

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks