SAGE: Variate-Wise Semantic Augmentation for Vision-Language Time Series Forecasting
cs.LG, cs.CV
Submitted: 2026-08-27
Updated: 2026-08-27
Terminology
Sources
- Chronos: Learning the Language of Time Series
- Time-Series Representation Learning via Temporal and Contextual Contrasting
- MOMENT: A Family of Open Time-series Foundation Models
- Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
- Harnessing Vision Models for Time Series Analysis: A Survey
- A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
- Frequency-aware Adaptive Contrastive Learning for Sequential Recommendation
- Context is Key: A Benchmark for Forecasting with Essential Textual Information
- CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting
- TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
- Aurora: Towards Universal Generative Multimodal Time Series Forecasting
- Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting
- Informer: Beyond Efficient Transformer for Long Sequence 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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks