paper-with-me

홈 › Papers

Moirai 2.0: When Less Is More for Time Series Forecasting

2025-11-12 · Chenghao Liu, Taha Aksu, Juncheng Liu, Xu Liu, Hanshu Yan, Quang Pham, Silvio Savarese, Doyen Sahoo, Caiming Xiong, Junnan Li arxiv

We introduce Moirai 2.0, a decoder-only time-series foundation model trained on a new corpus of 36M series. The model adopts quantile forecasting and multi-token prediction, improving both probabilistic accuracy and inference efficiency. On the Gift-Eval benchmark, it ranks among the top pretrained models while achieving a strong trade-off between accuracy, speed, and model size. Compared to Moirai 1.0, Moirai 2.0 replaces masked-encoder training, multi-patch inputs, and mixture-distribution outputs with a simpler decoder-only architecture, single patch, and quantile loss. Ablation studies isolate these changes -- showing that the decoder-only backbone along with recursive multi-quantile decoding contribute most to the gains. Additional experiments show that Moirai 2.0 outperforms larger models from the same family and exhibits robust domain-level results. In terms of efficiency and model size, Moirai 2.0 is twice as fast and thirty times smaller than its prior best version, Moirai 1.0-Large, while also performing better. Model performance plateaus with increasing parameter count and declines at longer horizons, motivating future work on data scaling and long-horizon modeling. We release code and evaluation details to support further research.

📄 PDF Abstract BibTeX arXiv:2511.11698

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series Forecasting

Similar Papers 제목 키워드 기반

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

2024-10-14 · Xu Liu, Juncheng Liu, Gerald Woo, Taha Aksu 외

Time series foundation models have demonstrated impressive performance as zero-shot forecasters. However, achieving effectively unified training on time series remains an open challenge. Existing approaches introduce som…

Mixture-of-ExpertsTime Series

Unified Training of Universal Time Series Forecasting Transformers

2024-02-04 · Gerald Woo, Chenghao Liu, Akshat Kumar, Caiming Xiong 외

Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models. The concept of unive…

Time SeriesTime Series Forecasting

Time Series Foundation Models are Flow Predictors

2025-07-01 · Massimiliano Luca, Ciro Beneduce, Bruno Lepri arxiv

We investigate the effectiveness of time series foundation models (TSFMs) for crowd flow prediction, focusing on Moirai and TimesFM. Evaluated on three real-world mobility datasets-Bike NYC, Taxi Beijing, and Spanish nat…

Moirai: Towards Optimal Placement for Distributed Inference on Heterogeneous Devices

2023-12-07 · Beibei Zhang, Hongwei Zhu, Feng Gao, Zhihui Yang 외

The escalating size of Deep Neural Networks (DNNs) has spurred a growing research interest in hosting and serving DNN models across multiple devices. A number of studies have been reported to partition a DNN model across…

Evaluating Spatio-Temporal Forecasting Trade-offs Between Graph Neural Networks and Foundation Models

2025-11-07 · Ragini Gupta, Naman Raina, Bo Chen, Li Chen 외 arxiv

Modern IoT deployments for environmental sensing produce high volume spatiotemporal data to support downstream tasks such as forecasting, typically powered by machine learning models. While existing filtering and strateg…