研究人员推出TiRex-2，这是一种基于xLSTM架构的新型递归基础模型，专为多元时间序列预测而设计。该模型通过有效处理流数据和整合未来已知协变量同时保持因果关系，解决了现有基于Transformer方法的局限性。TiRex-2在GIFT-Eval和fev-bench等基准测试中实现了最先进的零样本性能，在流数据条件下提供了稳定的性能和恒定的推理成本。 AI
影响 该模型为复杂的时间序列预测任务提供了更高效、更强大的解决方案，可能影响依赖于准确序列数据预测的领域。
排序理由 该集群包含一篇详细介绍时间序列预测新模型架构的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.01204v1 Announce Type: new Abstract: We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. Real-world forecasting is inherently sequential: obse…
We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. Real-world forecasting is inherently sequential: observations arrive continuously, variables evolve j…