# UniCast: A Unified Framework for Instance-Conditioned Multimodal Time-Series Forecasting

arXiv: https://arxiv.org/abs/2508.11954 · HTML: https://mlsanity.com/paper/2508.11954/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 16 Aug 2025.

## Builds on (most cited first, 12 of 12)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series](https://mlsanity.com/paper/2308.08241/) (2023)
- [CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning](https://mlsanity.com/paper/2403.07300/) (2024)
- [ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://mlsanity.com/paper/2412.11376/) (2024)
- [VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2408.17253/) (2024)
- [Time Series as Images: Vision Transformer for Irregularly Sampled Time Series](https://mlsanity.com/paper/2303.12799/) (2023)
- [LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting](https://mlsanity.com/paper/2402.16132/) (2024)
- [TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop](https://mlsanity.com/paper/2503.01013/) (2025)
- [LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization](https://mlsanity.com/paper/2503.08271/) (2025)
- [ViTime: Foundation Model for Time Series Forecasting Powered by Vision Intelligence](https://mlsanity.com/paper/2407.07311/) (2024)
- [Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2505.24003/) (2025)

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

- [UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting](https://mlsanity.com/paper/2512.07184/) (2025)
- [Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion](https://mlsanity.com/paper/2603.22372/) (2026)

## Abstract (arXiv)

Time series forecasting underpins applications in finance, healthcare, and environmental monitoring. Despite the success of Time Series Foundation Models (TSFMs), existing approaches operate in a unimodal setting and rely on static prompts or fixed fusion schemes, limiting their ability to exploit multimodal context and adapt to instance-level variation. We propose UniCast, a parameter-efficient multimodal framework that extends TSFMs through instance conditioned prompting and dynamic modality routing. UniCast infers a conditional prompt from time series, vision, and text inputs via a Transformer-based contextual distiller, enabling input-specific adaptation without updating the forecasting backbone. To regulate how auxiliary modalities influence predictions, UniCast employs Modality Routing, a cross-attention mechanism that estimates modality relevance given the current temporal state and selectively amplifies informative signals while suppressing noise. Integrated with a frozen TSFM via soft prompt tuning, UniCast preserves foundation-level generalization while enabling effective multimodal control. Extensive experiments across diverse forecasting benchmarks show that UniCast consistently outperforms all existing TSFM baselines, demonstrating that instance-conditioned multimodal control is critical for next-generation time series forecasting.