TimeOmni-o1 is a new model that bidirectionally couples a pretrained time‑series foundation model (TSFM) with a large language model (LLM) to simultaneously read, generate, and reason over both time‑series data and accompanying text. The TSFM encodes the series for the LLM, which performs multimodal reasoning, and the LLM’s output is fed back to the TSFM to produce forecasts conditioned on that reasoning. Trained on the newly created MMTR dataset—over 500,000 samples across 12 domains—TimeOmni-o1 surpasses existing models on both understanding and forecasting tasks, and its performance generalizes to three open benchmarks.
By Ziyang Zhang, Shenyi Li, Wen Wu, Chao Zhang
arXiv:2510. 03519v3 Announce Type: replace-cross Abstract: Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery.
By Fangxu Yu, Hongyu Zhao, Tianyi Zhou
arXiv:2606. 12481v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong reasoning and instruction-following capabilities, making them potentially powerful tools for time-series analysis.
By Jaeho Kim, Changhun Oh, Seokhyun Lee, Irina Rish, Changhee Lee
arXiv:2607. 08940v1 Announce Type: new Abstract: Time series reasoning is essential for real-world problem-solving.
By Fangxu Yu, Tao Feng, Dehai Min, Lu Cheng, Ge Liu, Tianyi Zhou
arXiv:2610.23521v1 Announce Type: new
Abstract: Large language models (LLMs) can now perceive, describe, and reason about images and audio, yet time series understanding remains underestimated: most...
By Xin Qiu, Junlong Tong, Wei Zhang, Xiaoyu Shen
Lapras is a post‑training framework for Time Series Language Models that replaces explicit Chain‑of‑Thought reasoning with continuous latent thoughts in a joint time‑series‑language space. By self‑distilling from a teacher that generates textual rationales, the student model aligns its hidden states at the answer stage, transferring reasoning ability while producing only the final answer in text. Experiments on four TSLM backbones and five benchmarks show Lapras boosts average F1 by up to 10.79% over explicit CoT and reduces token generation by 23.9×, while still enabling readable reasoning traces through standard decoding.
By Yuliang Chen, Yu Yvonne Wu, Patrick Langer, Arvind Pillai, Sudarshan Regmi, Martin Maritsch, Juncheng Liu, Robert Jakob, Thomas Kaar, Tess Z. Griffin, Lisa Marsch, Michael V. Heinz, Nicholas C. Jacobson, Andrew Campbell