Decouple to Reuse: Fine-Grained Knowledge Augmentation for Time Series Foundation Models
cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/yuppielqx/TSFM-Component-Token-Adapter
Terminology
Sources
- CODEBLOCK: Learning to Supervise Code at the Right Granularity
- LM-mixup: Text Data Augmentation via Language Model based Mixup
- UniTS: A Unified Multi-Task Time Series Model
- TimeGPT-1
- MOMENT: A Family of Open Time-series Foundation Models
- Rationale-Grounded In-Context Learning for Time Series Reasoning with Multimodal Large Language Models
- Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
- Sundial: A Family of Highly Capable Time Series Foundation Models
- Timer: Generative Pre-trained Transformers Are Large Time Series Models
- TS-Memory: Plug-and-Play Memory for Time Series Foundation Models
- CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
- Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
- Retrieval Augmented Time Series Forecasting
- Unified Training of Universal Time Series Forecasting Transformers
- TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
- Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation
- Beyond Regularity: Modeling Chaotic Mobility Patterns for Next Location Prediction
- MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models
- Stationarity-Aware Retrieval-Augmented Time Series Forecasting
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis