{"ID":5675252,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-07T01:06:03.009715918Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01918","arxiv_id":"2607.01918","title":"Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis","abstract":"We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. Unlike prior studies that primarily focus on zero-shot forecasting but require task-specific tuning for other tasks, Zeus bridges this gap by addressing two fundamental challenges in multi-task generalization. First, to reconcile point-level granularity with long-sequence scalability, Zeus incorporates a multi-scale Transformer featuring point-wise tokenization and a U-shaped hierarchy, effectively balancing fine-grained fidelity with computational efficiency. Second, to accommodate varying inductive biases across different tasks, Zeus introduces Multi-Objective Temporal Masking (MOTM), a unified strategy that supports heterogeneous tasks (e.g., extrapolation, interpolation, and global abstraction) within a single framework. Extensive experiments across five representative tasks demonstrate that Zeus consistently achieves competitive results in tuning-free settings, underscoring its potential as a general-purpose TSFM.","short_abstract":"We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. Unlike prior studies that primarily focus on zero-shot forecasting but require task-specific tuning for other tasks, Zeus bridges this gap by...","url_abs":"https://arxiv.org/abs/2607.01918","url_pdf":"https://arxiv.org/pdf/2607.01918v1","authors":"[\"Yisong Fu\",\"Zezhi Shao\",\"Chengqing Yu\",\"Yujie Li\",\"Yongjun Xu\",\"Xueqi Cheng\",\"Fei Wang\"]","published":"2026-07-02T09:16:51Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}