# TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching

arXiv: https://arxiv.org/abs/2606.03121 · HTML: https://mlsanity.com/paper/2606.03121/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting](https://mlsanity.com/paper/2103.07719/) (2021)
- [Multi-Time Attention Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/2101.10318/) (2021)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [Neural Flows: Efficient Alternative to Neural ODEs](https://mlsanity.com/paper/2110.13040/) (2021)
- [TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting](https://mlsanity.com/paper/2410.11802/) (2024)
- [Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline](https://mlsanity.com/paper/2505.11250/) (2025)
- [TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop](https://mlsanity.com/paper/2503.01013/) (2025)
- [GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images](https://mlsanity.com/paper/2503.06073/) (2025)
- [Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective](https://mlsanity.com/paper/2510.14510/) (2025)
- [DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2509.14933/) (2025)
- [LightPath: Lightweight and Scalable Path Representation Learning](https://mlsanity.com/paper/2307.10171/) (2023)
- [LightGTS: A Lightweight General Time Series Forecasting Model](https://mlsanity.com/paper/2506.06005/) (2025)
- [Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems](https://mlsanity.com/paper/2410.19892/) (2024)
- [Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series](https://mlsanity.com/paper/2410.14030/) (2024)
- [MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version](https://mlsanity.com/paper/2411.18428/) (2024)
- [TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding](https://mlsanity.com/paper/2509.19406/) (2025)
- [ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting](https://mlsanity.com/paper/2510.09734/) (2025)
- [CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter](https://mlsanity.com/paper/2603.21828/) (2026)
- [CSformer: Combining Channel Independence and Mixing for Robust Multivariate Time Series Forecasting](https://mlsanity.com/paper/2312.06220/) (2023)
- [Orca: Ocean Significant Wave Height Estimation with Spatio-temporally Aware Large Language Models](https://mlsanity.com/paper/2407.20053/) (2024)
- [SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement](https://mlsanity.com/paper/2602.00589/) (2026)

## Built on by (most cited first, 2 of 2)

- [Rethinking Cross-Channel Importance in Time-Series Forecasting](https://mlsanity.com/paper/2609.32187/) (2026)
- [BITS: Rethinking Fair and Comprehensive Evaluation for Irregular Time Series Forecasting](https://mlsanity.com/paper/2609.33303/) (2026)

## Abstract (arXiv)

Multivariate time series forecasting plays a critical role in real-world applications, including weather prediction, stock analysis, and health monitoring. Due to the diversity of data sources, time series exhibit diverse temporal dynamics, often accompanied by various irregularities such as missing values and non-uniform sampling frequencies. Such irregularities lead to complex and asynchronous temporal dependencies across channels. Thus, a single model with a fixed patching scheme often fails to adapt well to diverse multivariate time series, hindering accurate forecasting. In this paper, we propose TiWeaver, a unified framework designed to handle temporal dynamics and fine-grained inter-channel dependencies adaptively. Specifically, we introduce a Graph-Guided Adaptive Tokenizer (G2AT) that divides time series into high contextually coherent patches by jointly considering temporal density and representation consistency. In addition, we propose a Fine-grained Asynchronous Dependency Extractor (FADE), which is designed to model fine-grained asynchronous inter-channel dependencies while incorporating long-term historical dependencies. We evaluate TiWeaver on 12 real-world time series datasets, where it achieves state-of-the-art performance, outperforming existing methods up to 25%. These results demonstrate its robustness and effectiveness across diverse domains and data characteristics.