# TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment

arXiv: https://arxiv.org/abs/2406.01638 · HTML: https://mlsanity.com/paper/2406.01638/

## Key facts

- Cited by 103 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Builds on (most cited first, 14 of 14)

- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [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)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods](https://mlsanity.com/paper/2403.20150/) (2024)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series](https://mlsanity.com/paper/2308.08241/) (2023)
- [Spatial-Temporal Large Language Model for Traffic Prediction](https://mlsanity.com/paper/2401.10134/) (2024)
- [Leveraging Language Foundation Models for Human Mobility Forecasting](https://mlsanity.com/paper/2209.05479/) (2022)
- [A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data](https://mlsanity.com/paper/2404.14999/) (2024)
- [LightTR: A Lightweight Framework for Federated Trajectory Recovery](https://mlsanity.com/paper/2405.03409/) (2024)
- [SQL-to-Schema Enhances Schema Linking in Text-to-SQL](https://mlsanity.com/paper/2405.09593/) (2024)

## Built on by (most cited first, 30 of 103)

- [TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting](https://mlsanity.com/paper/2410.11802/) (2024)
- [DBLoss: Decomposition-based Loss Function for Time Series Forecasting](https://mlsanity.com/paper/2510.23672/) (2025)
- [TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting](https://mlsanity.com/paper/2410.04442/) (2024)
- [TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop](https://mlsanity.com/paper/2503.01013/) (2025)
- [Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective](https://mlsanity.com/paper/2510.14510/) (2025)
- [Aurora: Towards Universal Generative Multimodal Time Series Forecasting](https://mlsanity.com/paper/2509.22295/) (2025)
- [Multi-modal Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2503.13709/) (2025)
- [Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation](https://mlsanity.com/paper/2505.02138/) (2025)
- [TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning](https://mlsanity.com/paper/2506.13705/) (2025)
- [BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models](https://mlsanity.com/paper/2505.17871/) (2025)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era](https://mlsanity.com/paper/2505.02583/) (2025)
- [TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting](https://mlsanity.com/paper/2510.00461/) (2025)
- [Distilling Time Series Foundation Models for Efficient Forecasting](https://mlsanity.com/paper/2601.12785/) (2026)
- [Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting](https://mlsanity.com/paper/2602.13802/) (2026)
- [MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning](https://mlsanity.com/paper/2602.03164/) (2026)
- [K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2505.23017/) (2025)
- [TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval](https://mlsanity.com/paper/2506.09114/) (2025)
- [DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework](https://mlsanity.com/paper/2507.21830/) (2025)
- [T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion](https://mlsanity.com/paper/2508.04251/) (2025)
- [Text Reinforcement for Multimodal Time Series Forecasting](https://mlsanity.com/paper/2509.00687/) (2025)
- [Predicting the Future by Retrieving the Past](https://mlsanity.com/paper/2511.05859/) (2025)
- [CC-Time: Cross-Model and Cross-Modality Time Series Forecasting](https://mlsanity.com/paper/2508.12235/) (2025)
- [USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents](https://mlsanity.com/paper/2505.17572/) (2025)
- [Foundation Models for Demand Forecasting via Dual-Strategy Ensembling](https://mlsanity.com/paper/2507.22053/) (2025)
- [TimeSAF: Towards LLM-Guided Semantic Asynchronous Fusion for Time Series Forecasting](https://mlsanity.com/paper/2604.12648/) (2026)
- [DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classification](https://mlsanity.com/paper/2507.04600/) (2025)
- [AIS-LLM: A Unified Framework for Maritime Trajectory Prediction, Anomaly Detection, and Collision Risk Assessment with Explainable Forecasting](https://mlsanity.com/paper/2508.07668/) (2025)
- [TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts](https://mlsanity.com/paper/2602.21693/) (2026)
- [Skin Cancer Detection utilizing Deep Learning: Classification of Skin Lesion Images using a Vision Transformer](https://mlsanity.com/paper/2407.18554/) (2024)

## Abstract (arXiv)

Multivariate time series forecasting (MTSF) aims to learn temporal dynamics among variables to forecast future time series. Existing statistical and deep learning-based methods suffer from limited learnable parameters and small-scale training data. Recently, large language models (LLMs) combining time series with textual prompts have achieved promising performance in MTSF. However, we discovered that current LLM-based solutions fall short in learning disentangled embeddings. We introduce TimeCMA, an intuitive yet effective framework for MTSF via cross-modality alignment. Specifically, we present a dual-modality encoding with two branches: the time series encoding branch extracts disentangled yet weak time series embeddings, and the LLM-empowered encoding branch wraps the same time series with text as prompts to obtain entangled yet robust prompt embeddings. As a result, such a cross-modality alignment retrieves both disentangled and robust time series embeddings, "the best of two worlds", from the prompt embeddings based on time series and prompt modality similarities. As another key design, to reduce the computational costs from time series with their length textual prompts, we design an effective prompt to encourage the most essential temporal information to be encapsulated in the last token: only the last token is passed to downstream prediction. We further store the last token embeddings to accelerate inference speed. Extensive experiments on eight real datasets demonstrate that TimeCMA outperforms state-of-the-arts.