arXiv AI By Chenghao Liu, Wei Fan, Jindong Han, Dongjie Wang, Aniket Mahanti, Pengyang Wang, Hao Liu

TimesJev: Thinking Fast on Time Series with System 1 Sufficiency

Read the original on arXiv AI →

TimesJev is a System 1 time‑series model that compresses raw series into a representation preserving key frequency patterns. It optimizes a dual‑objective loss combining sufficiency divergence and realizability divergence, then aligns the compressed representation with the model’s embedding space. Experiments on 13 datasets show TimesJev outperforms reasoning models by over 62 % while reducing inference time by 62.9 % on average.

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 AI.

arXiv Computation and Language
6d ago

TimeOmni-o1: Bidirectionally Coupling Time Series Foundation Models and LLMs for Multimodal Reasoning and Forecasting

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 Machine Learning
Oct 9

Lapras: Latent Reasoning for Time Series Language Models

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