TiMi framework integrates LLMs for multimodal time series forecasting

Researchers have developed TiMi, a novel framework that enhances multimodal time series forecasting by integrating Large Language Models (LLMs) with a Multimodal Mixture-of-Experts (MMoE) module. This approach aims to leverage textual information, such as policy announcements and emergency reports, to improve prediction accuracy. TiMi has demonstrated state-of-the-art performance across sixteen real-world benchmarks, offering adaptability and interpretability. AI

IMPACT Enhances multimodal time series forecasting by leveraging LLMs for causal reasoning and improved prediction accuracy.

RANK_REASON The cluster describes a research paper detailing a new model/framework for time series forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Gotit.pub
• Hugging Face
• Jiafeng Lin
• Multimodal Mixture-of-Experts
• ScienceCast
• Timi
• Transformer++

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →