SCENARIODIFF: A Scenario-level Guidance Framework for Multimodal Time Series Forecasting--Extended Version

• URL: http://arxiv.org/abs/2608.17164v1
• Date: Mon, 17 Aug 2026 22:05:09 GMT
• Title: SCENARIODIFF: A Scenario-level Guidance Framework for Multimodal Time Series Forecasting--Extended Version
• Abstract summary: We propose SCENARIODIFF, a hierarchical contextual reasoning framework for multimodal time series forecasting.<n>SCENARIODIFF organizes contextual information into three levels: a Historical Context Agent extracts stepwise evidence from raw documents, a Scenario Agent produces a qualitative scenario description for the forecast horizon, and an Anchor Guidance Agent generates sparse anchor points for event-relevant future regions.<n> Experiments on the Time-MMD benchmark show that SCENARIODIFF is especially effective in event-driven domains.
• Score: 5.00208619516796
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events that are not yet visible in historical values. Existing multimodal forecasting methods often either ask large language models (LLMs) to predict numerical values directly or fuse text and time series implicitly, making contextual influence difficult to interpret and control. We propose SCENARIODIFF, a hierarchical contextual reasoning framework for multimodal time series forecasting under noisy and weakly aligned documents. SCENARIODIFF organizes contextual information into three levels: a Historical Context Agent extracts stepwise evidence from raw documents, a Scenario Agent produces a qualitative scenario description for the forecast horizon, and an Anchor Guidance Agent generates sparse anchor points for event-relevant future regions. These structured signals condition a Multimodal Diffusion Transformer, while Anchor Blended Sampling locally refines generated trajectories without retraining. Experiments on the Time-MMD benchmark show that SCENARIODIFF is especially effective in event-driven domains, demonstrating the value of explicit hierarchical scenario guidance for multimodal time series forecasting. Our full implementation is available at https://anonymous.4open.science/r/ScenarioDiff_ICDM-2C4C

Related papers

• Spectral-Aware Text-to-Time Series Generation with Billion-Scale Multimodal Meteorological Data [5.582207674658708]
  We introduce MeteoCap-3B, a billion-scale weather dataset paired with expert-level captions constructed via a Collaborative Captioning (MACC) pipeline.<n>We then propose MTransformer, a diffusion-based model that enables precise semantic control by mapping textual descriptions into multi-band spectral priors.<n>Experiments on real-world benchmarks demonstrate state-of-the-art generation quality, accurate cross-modal alignment, strong semantic controllability, and substantial gains in downstream forecasting.
  arXiv  Detail & Related papers  (2026-03-28T04:55:00Z)
• What If TSF: A Benchmark for Reframing Forecasting as Scenario-Guided Multimodal Forecasting [8.593646221015264]
  What If TSF (WIT) is a benchmark designed to evaluate whether models can condition their forecasts on contextual text.<n>WIT offers a rigorous testbed for scenario-guided multimodal forecasting.
  arXiv  Detail & Related papers  (2026-01-13T12:47:43Z)
• Adaptive Information Routing for Multimodal Time Series Forecasting [11.180175447040694]
  Time series forecasting is a critical task for artificial intelligence with numerous real-world applications.<n>Traditional approaches primarily rely on historical time series data to predict the future values.<n>We introduce the Adaptive Information Routing framework, a novel approach for multimodal time series forecasting.
  arXiv  Detail & Related papers  (2025-12-11T02:25:27Z)
• UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting [90.47915032778366]
  We propose UniDiff, a unified diffusion framework for multimodal time series forecasting.<n>At its core lies a unified and parallel fusion module, where a single cross-attention mechanism integrates structural information from timestamps and semantic context from texts.<n>Experiments on real-world benchmark datasets across eight domains demonstrate that the proposed UniDiff model achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-08T05:36:14Z)
• NUM2EVENT: Interpretable Event Reasoning from Numerical time-series [6.45945124018154]
  We introduce the task of number-to-event reasoning and decoding, which aims to infer interpretable structured events from numerical inputs.<n>To address the data scarcity and semantic alignment challenges, we propose a reasoning-aware framework.<n>Our model explicitly reasons over numerical changes, generates intermediate explanations, and outputs structured event hypotheses.
  arXiv  Detail & Related papers  (2025-10-24T02:57:11Z)
• Aurora: Towards Universal Generative Multimodal Time Series Forecasting [18.584127942149028]
  Cross-domain generalization is very important in Time Series Forecasting.<n>Recent works focus on building unimodal time series foundation models and end-to-end multimodal supervised models.<n>We introduce Aurora, a Multimodal Time Series Foundation Model, which supports multimodal inputs and zero-shot inference.
  arXiv  Detail & Related papers  (2025-09-26T12:56:20Z)
• EventTSF: Event-Aware Non-Stationary Time Series Forecasting [73.54313384419792]
  EventTSF is an autoregressive generation framework that integrates historical time series with textual events to make subsequent forecasts.<n>Experiments on 8 synthetic and real-world datasets show that EventTSF outperforms 12 baselines across diverse event-aware non-stationary time series forecasting scenarios.
  arXiv  Detail & Related papers  (2025-08-19T01:28:47Z)
• When Does Multimodality Lead to Better Time Series Forecasting? [96.26052272121615]
  We investigate whether and under what conditions such multimodal integration consistently yields gains.<n>Our findings reveal that the benefits of multimodality are highly condition-dependent.<n>Our study offers a rigorous, quantitative foundation for understanding when multimodality can be expected to aid forecasting tasks.
  arXiv  Detail & Related papers  (2025-06-20T23:55:56Z)
• TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents [52.13094810313054]
  TimeCAP is a time-series processing framework that creatively employs Large Language Models (LLMs) as contextualizers of time series data.<n>TimeCAP incorporates two independent LLM agents: one generates a textual summary capturing the context of the time series, while the other uses this enriched summary to make more informed predictions.<n> Experimental results on real-world datasets demonstrate that TimeCAP outperforms state-of-the-art methods for time series event prediction.
  arXiv  Detail & Related papers  (2025-02-17T04:17:27Z)
• Timer-XL: Long-Context Transformers for Unified Time Series Forecasting [67.83502953961505]
  We present Timer-XL, a causal Transformer for unified time series forecasting.<n>Based on large-scale pre-training, Timer-XL achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2024-10-07T07:27:39Z)
• SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction [72.37440317774556]
  We propose advances that address two key challenges in future trajectory prediction. multimodality in both training data and predictions and constant time inference regardless of number of agents.
  arXiv  Detail & Related papers  (2020-07-26T08:17:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.