按年被提到
20252025 · 2 次2026
机器学习与深度学习›时间序列与天气预报·arXiv:2505.23719 · cs.LG

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

Andreas Auer, Patrick Podest, Daniel Klotz, Sebastian Böck, Günter Klambauer, Sepp Hochreiter · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-06-02 · 最近 2025-07-08
2不同的人
2活跃月份
2讨论串
16被引(OpenAlex)
arXiv 摘要(候选层不写导读)

In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero-shot prediction, where past values serve as context for forecasting future values, making powerful forecasting tools accessible to non-experts and increasing the performance when training data are scarce. Most existing zero-shot forecasting approaches rely on transformer architectures, which, despite their success in language, often fall short of expectations in time series forecasting, where recurrent models like LSTMs frequently have the edge. Conversely, while LSTMs are well-suited for time series modeling due to their state-tracking capabilities, they lack strong in-context learning abilities. We introduce TiRex that closes this gap by leveraging xLSTM, an enhanced LSTM with competitive in-context learning skills. Unlike transformers, state-space models, or parallelizable RNNs such as RWKV, TiRex retains state-tracking, a critical property for long-horizon forecasting. To further facilitate its state-tracking ability, we propose a training-time masking strategy called CPM. TiRex sets a new state of the art in zero-shot time series forecasting on the HuggingFace benchmarks GiftEval and Chronos-ZS, outperforming significantly larger models including TabPFN-TS (Prior Labs), Chronos Bolt (Amazon), TimesFM (Google), and Moirai (Salesforce) across both short- and long-term forecasts.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论nextos · 2025-07

“Second-generation LSTMs (xLSTM) do have leading performance on zero-shot time series forecasting: https://arxiv.org/abs/2505.23719. I think other architectures, aside from the transformer, might lead to SOTA performance, but they remain a bit unexplored.”

The Tradeoffs of SSMs and Transformers原评论 ↗
被提交为 story · 1 次