{"ID":2852714,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.21795","arxiv_id":"2510.21795","title":"Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attention","abstract":"The rapid advancement of time series foundation models (TSFMs) has been propelled by migrating architectures from language models. While existing TSFMs demonstrate impressive performance, their direct adoption of cross-domain architectures constrains effective capture of multiscale temporal dependencies inherent to time series data. This limitation becomes particularly pronounced during zero-shot transfer across datasets with divergent underlying patterns and sampling strategies. To address these challenges, we propose Hierarchical Interleaved Block Attention (HIBA) which employs hierarchical inter- and intra-block sparse attention to effectively capture multi-scale dependencies. Intra-block attention facilitates local information exchange, and inter-block attention operates across blocks to capture global temporal pattern interaction and dynamic evolution. Leveraging the HIBA architecture, we introduce Xihe, a scalable TSFM family spanning from an ultra-efficient 9.5M parameter configuration to high-capacity 1.5B variant. Evaluated on the comprehensive GIFT-Eval benchmark, our most compact Xihe-tiny model (9.5M) surpasses the majority of contemporary TSFMs, demonstrating remarkable parameter efficiency. More impressively, Xihe-max (1.5B) establishes new state-of-the-art zero-shot performance, surpassing previous best results by a substantial margin. This consistent performance excellence across the entire parameter spectrum provides compelling evidence for the exceptional generalization capabilities and architectural superiority of HIBA.","short_abstract":"The rapid advancement of time series foundation models (TSFMs) has been propelled by migrating architectures from language models. While existing TSFMs demonstrate impressive performance, their direct adoption of cross-domain architectures constrains effective capture of multiscale temporal dependencies inherent to tim...","url_abs":"https://arxiv.org/abs/2510.21795","url_pdf":"https://arxiv.org/pdf/2510.21795v1","authors":"[\"Yinbo Sun\",\"Yuchen Fang\",\"Zhibo Zhu\",\"Jia Li\",\"Yu Liu\",\"Qiwen Deng\",\"Jun Zhou\",\"Hang Yu\",\"Xingyu Lu\",\"Lintao Ma\"]","published":"2025-10-20T11:10:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false}