HALO introduces a hyperspherical VAE to constrain continuous latent representations to a fixed‑radius shell, stabilizing numerical fluctuations. It then employs a masked autoregressive model that balances parallel decoding with temporal correlation learning, reducing inference steps and improving stability. Experiments show HALO achieves state‑of‑the‑art generation performance with significantly better inference efficiency compared to existing baselines.
By Chunyi Hou, Xiangfei Qiu, Hanyin Cheng, Yutong Li, Bin Yang
arXiv:2607. 08234v1 Announce Type: cross Abstract: Real-world time series exhibit complex dynamics characterized by multiple simultaneous temporal patterns: short-term fluctuations, periodic seasonal cycles, long-term trends, and irregular abrupt changes.
By Sumit Satishrao Shevtekar, Chandresh Kumar Maurya
arXiv:2607. 19404v1 Announce Type: cross Abstract: Multivariate time series encode structural patterns that unfold across multiple temporal scales, yet most forecasting backbones treat learned representations as transient byproducts of prediction, leaving the organizational geometry of these patterns underexploited.
By Xingsheng Chen, Deyu Yi, Siu-Ming Yiu
arXiv:2501. 04339v2 Announce Type: replace-cross Abstract: We introduce the Deep Convolutional Interpreter for Time Series (DCIts), a deep-learning architecture for nonlinear multivariate time series that provides sample-specific, locally interpretable descriptions of the underlying interaction structure.
By Domjan Baric, Davor Horvatic
arXiv:2606. 15172v1 Announce Type: new Abstract: Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios.
By Zihao Yao, Qi Zheng, Jiankai Zuo, Yaying Zhang
arXiv:2606. 10466v1 Announce Type: cross Abstract: In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains.
By Du Yin, Hao Xue, Jinliang Deng, Yang Yang, Shuang Ao, Arian Prabowo, Flora Salim
arXiv:2608. 06223v1 Announce Type: new Abstract: While deep learning models, particularly transformer-based architectures, have shown impressive performance in time series forecasting, the application of retrieval-augmented generation (RAG) in this domain remains limited.
By Yixiong Xiao, Congxi Xiao, Jingbo Zhou
arXiv:2511. 20577v5 Announce Type: replace Abstract: Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends.
By Sumit S Shevtekar, Chandresh K Maurya
NeST is a framework that adapts large language models (LLMs) for continuous time‑series forecasting by creating neighborhood‑aware text prototypes and aligning them with temporal representations through a nearest‑neighbor contrastive objective. It retrieves the most relevant prototypes and uses them to conditionally modulate time‑series features, enabling more effective integration of textual and temporal information. Experiments show that NeST outperforms state‑of‑the‑art methods on eight benchmarks, reduces MSE by 1.2% for long‑term forecasting, improves zero‑shot forecasting by 4.9%, and boosts R² by 3.3% on a real‑world photovoltaic power forecasting task.
By Jayanie Bogahawatte, Sachith Seneviratne, Maneesha Perera, Saman Halgamuge
The paper introduces m-WCN, an end‑to‑end deep learning framework that neuralizes multi‑wavelet decomposition to jointly extract temporal patterns and frequency components from time series. Two task‑specific architectures built on m‑WCN—TFBC for classification and FTB for forecasting—are shown to outperform baseline models on 64 UCR datasets and seven forecasting benchmarks, achieving average improvements of nearly 20% in both tasks. The approach leverages trainable convolutional operators and orthogonality constraints to produce interpretable multi‑resolution representations.
By Xiaohan Jiang, Jingyuan Wang, Jiahao Ji, Yongyao Wang, Chen Yang, Junjie Wu
arXiv:2606. 10678v1 Announce Type: new Abstract: Transformer-based models have emerged as leading paradigms in time-series forecasting in recent years, employing self-attention mechanisms to capture long-range dependencies.
By Amrijit Biswas, Mustafa Kamal, Robin Krambroeckers, M. M. Lutfe Elahi, Sifat Momen, Nabeel Mohammed, Shafin Rahman
arXiv:2508. 05287v3 Announce Type: replace-cross Abstract: Existing time series foundation models (TSFMs), often based on transformer variants, lack adaptability to different sampling rates, struggle with generalization across varying context and target lengths, and are computationally inefficient.
By Lars Graf, Thomas Ortner, Stanis{\l}aw Wo\'zniak, Angeliki Pantazi