Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
For time series practitioners, Zeus provides a single general-purpose model that eliminates the need for task-specific tuning, though results are competitive rather than state-of-the-art.
Zeus is a tuning-free time series foundation model that achieves competitive performance across five diverse tasks (e.g., forecasting, interpolation) without task-specific fine-tuning, using a multi-scale Transformer and multi-objective temporal masking.
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.