TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting

ArXi:2603.11352v1 Announce Type: new Transformer-based time series foundation models face a fundamental trade-off in choice of tokenization: point-wise embeddings preserve temporal fidelity but scale poorly with sequence length, whereas fixed-length patching improves efficiency by imposing uniform boundaries that may disrupt natural transitions and blur informative local dynamics. In order to address these limitations, we