# T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion

arXiv: https://arxiv.org/abs/2508.04251 · HTML: https://mlsanity.com/paper/2508.04251/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting](https://mlsanity.com/paper/2103.07719/) (2021)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Pretrained Transformers as Universal Computation Engines](https://mlsanity.com/paper/2103.05247/) (2021)
- [TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment](https://mlsanity.com/paper/2406.01638/) (2024)
- [Spatial-Temporal Large Language Model for Traffic Prediction](https://mlsanity.com/paper/2401.10134/) (2024)
- [Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning](https://mlsanity.com/paper/2202.10629/) (2022)
- [A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data](https://mlsanity.com/paper/2404.14999/) (2024)
- [Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data](https://mlsanity.com/paper/2206.02353/) (2022)
- [SaDI: A Self-adaptive Decomposed Interpretable Framework for Electric Load Forecasting under Extreme Events](https://mlsanity.com/paper/2306.08299/) (2023)
- [LightTR: A Lightweight Framework for Federated Trajectory Recovery](https://mlsanity.com/paper/2405.03409/) (2024)

## Built on by (most cited first, 7 of 7)

- [LaGEA: Language Guided Embodied Agents for Robotic Manipulation](https://mlsanity.com/paper/2509.23155/) (2025)
- [Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion](https://mlsanity.com/paper/2603.22372/) (2026)
- [VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection](https://mlsanity.com/paper/2603.26842/) (2026)
- [FRWKV+: Periodic-Aware Adaptive Gating for Frequency-Space Linear Time Series Forecasting](https://mlsanity.com/paper/2605.15690/) (2026)
- [STaT: Resolving Shape Distortion in Non-Stationary Time Series via Tri-Modal Synergy](https://mlsanity.com/paper/2605.25943/) (2026)
- [Heterogeneous 2D/1D Signal Representation Fusion for Underwater Acoustic Modulation Recognition Under Distribution Shift](https://mlsanity.com/paper/2606.23702/) (2026)
- [When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting](https://mlsanity.com/paper/2609.24862/) (2026)

## Abstract (arXiv)

Multivariate time series forecasting (MTSF) seeks to model temporal dynamics among variables to predict future trends. Transformer-based models and large language models (LLMs) have shown promise due to their ability to capture long-range dependencies and patterns. However, current methods often rely on rigid inductive biases, ignore intervariable interactions, or apply static fusion strategies that limit adaptability across forecast horizons. These limitations create bottlenecks in capturing nuanced, horizon-specific relationships in time-series data. To solve this problem, we propose T3Time, a novel trimodal framework consisting of time, spectral, and prompt branches, where the dedicated frequency encoding branch captures the periodic structures along with a gating mechanism that learns prioritization between temporal and spectral features based on the prediction horizon. We also proposed a mechanism which adaptively aggregates multiple cross-modal alignment heads by dynamically weighting the importance of each head based on the features. Extensive experiments on benchmark datasets demonstrate that our model consistently outperforms state-of-the-art baselines, achieving an average reduction of 3.28% in MSE and 2.29% in MAE. Furthermore, it shows strong generalization in few-shot learning settings: with 5% training data, we see a reduction in MSE and MAE by 4.13% and 1.91%, respectively; and with 10% data, by 3.62% and 1.98% on average. Code - https://github.com/monaf-chowdhury/T3Time/