🧪 Test?View on arXiv
TimeOmni-o1: Bidirectionally Coupling Time Series Foundation Models and LLMs for Multimodal Reasoning and Forecasting
Author1, Author2, Author3, Author4, Author5
multimodalreasoningtime seriesforecasting
2611.12902
Builder Relevance
8h ago80%
Abstract
TimeOmni-o1 couples time series foundation models and large language models for enhanced multimodal reasoning and forecasting.
Reality Card
Core Claim
TimeOmni-o1 outperforms existing models in understanding and forecasting tasks across multiple domains by effectively integrating TSFMs and LLMs.
Method / Result
Achieved superior performance on the MMTR dataset, outperforming existing models in both understanding and forecasting tasks.
Limitations
The main limitation is the potential difficulty in replicating the multimodal time series reasoning dataset (MMTR) due to its size and complexity.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.