arXiv Machine Learning August 19, 2026 By Tuan-Binh Tran, Dat Nguyen Cong, Duc-Trong Le, Thanh Trung Huynh, Tung Kieu

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

Read the original on arXiv Machine Learning →

SCENARIODIFF is a hierarchical contextual reasoning framework designed for multimodal time series forecasting, especially in event-driven domains. It processes textual context through three agents—Historical Context, Scenario, and Anchor Guidance—to generate structured signals that condition a Multimodal Diffusion Transformer. The framework also employs Anchor Blended Sampling to locally refine forecast trajectories without retraining, and demonstrates superior performance on the Time‑MMD benchmark.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Aug 17

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

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 hist...

llms agents diffusion multimodal benchmarks

arXiv AI

Sep 15

Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterogeneous Context

arXiv:2609.15087v1 Announce Type: cross Abstract: Most time series forecasting benchmarks remain numerical-centric and provide limited support for evaluating contextual information that shapes real-w...

By Peng Chen, Zhihao Zhuang, Hongzhou Chen, Junhao Huang, Aiping Yang, Mengsen Wu, Yiding Liu, Xilin Dai, Zewei Dong

llms multimodal benchmarks

arXiv Machine Learning

Aug 19

TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts

The paper introduces TiMi, a framework that enhances time series transformers with a Multimodal Mixture-of-Experts (MMoE) module to incorporate multimodal data, especially textual information, into forecasting. TiMi leverages large language models to generate future inferences that guide predictions, eliminating the need for explicit representation alignment. Experiments show TiMi achieves state‑of‑the‑art performance on sixteen real‑world multimodal forecasting benchmarks, outperforming advanced baselines while maintaining adaptability and interpretability.

By Jiafeng Lin, Yuxuan Wang, Huakun Luo, Jianmin Wang, Zhongyi Pei

llms multimodal benchmarks safety

arXiv AI

Aug 7

MM-ISTS: Cooperating Irregularly Sampled Time Series Forecasting with Multimodal Vision-Text LLMs

arXiv:2603. 05997v2 Announce Type: replace-cross Abstract: Irregularly sampled time series (ISTS) are widespread in real-world scenarios, exhibiting asynchronous observations on uneven time intervals across diverse variables.

By Zhi Lei, Chenxi Liu, Hao Miao, Wanghui Qiu, Bin Yang, Chenjuan Guo

llms rag multimodal safety

arXiv AI

Jun 29

Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting

arXiv:2602. 01588v3 Announce Type: replace-cross Abstract: Multimodal time series forecasting is crucial in real-world applications, where decisions depend on both numerical data and contextual signals.

By Huu Hiep Nguyen, Minh Hoang Nguyen, Dung Nguyen, Hung Le

rag multimodal benchmarks safety

arXiv Machine Learning

Jul 16

Overcoming the Modality Gap in Context-Aided Forecasting

arXiv:2603. 12451v4 Announce Type: replace Abstract: Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods.

By Vincent Zhihao Zheng, \'Etienne Marcotte, Arjun Ashok, Andrew Robert Williams, Lijun Sun, Alexandre Drouin, Valentina Zantedeschi

multimodal

One email a morning, machine-written

Related stories

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

Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterogeneous Context

TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts

MM-ISTS: Cooperating Irregularly Sampled Time Series Forecasting with Multimodal Vision-Text LLMs

Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting

Overcoming the Modality Gap in Context-Aided Forecasting