FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908821918580736 |
|---|---|
| author | Wu, Xingjian Cheng, Hanyin Qiu, Xiangfei Li, Zhengyu Hu, Jilin Guo, Chenjuan Yang, Bin |
| author_facet | Wu, Xingjian Cheng, Hanyin Qiu, Xiangfei Li, Zhengyu Hu, Jilin Guo, Chenjuan Yang, Bin |
| contents | In this work, we introduce FLAME, a family of extremely lightweight and capable Time Series Foundation Models, which support both deterministic and probabilistic forecasting via generative probabilistic modeling, thus ensuring both efficiency and robustness. FLAME utilizes the Legendre Memory for strong generalization capabilities. Through adapting variants of Legendre Memory, i.e., translated Legendre (LegT) and scaled Legendre (LegS), in the Encoding and Decoding phases, FLAME can effectively capture the inherent inductive bias within data and make efficient long-range inferences. To enhance the accuracy of probabilistic forecasting while keeping efficient, FLAME adopts a Normalization Flow based forecasting head, which can model the arbitrarily intricate distributions over the forecasting horizon in a generative manner. Comprehensive experiments on well-recognized benchmarks, including TSFM-Bench and ProbTS, demonstrate the consistent state-of-the-art zero-shot performance of FLAME on both deterministic and probabilistic forecasting tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14253 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting Wu, Xingjian Cheng, Hanyin Qiu, Xiangfei Li, Zhengyu Hu, Jilin Guo, Chenjuan Yang, Bin Machine Learning In this work, we introduce FLAME, a family of extremely lightweight and capable Time Series Foundation Models, which support both deterministic and probabilistic forecasting via generative probabilistic modeling, thus ensuring both efficiency and robustness. FLAME utilizes the Legendre Memory for strong generalization capabilities. Through adapting variants of Legendre Memory, i.e., translated Legendre (LegT) and scaled Legendre (LegS), in the Encoding and Decoding phases, FLAME can effectively capture the inherent inductive bias within data and make efficient long-range inferences. To enhance the accuracy of probabilistic forecasting while keeping efficient, FLAME adopts a Normalization Flow based forecasting head, which can model the arbitrarily intricate distributions over the forecasting horizon in a generative manner. Comprehensive experiments on well-recognized benchmarks, including TSFM-Bench and ProbTS, demonstrate the consistent state-of-the-art zero-shot performance of FLAME on both deterministic and probabilistic forecasting tasks. |
| title | FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.14253 |