TiRex: Closing the Gap Between Recurrent and In-Context Learning

Beschreibung

Recurrent architectures have long been the natural choice for modeling time-dependent data, yet the recent dominance of Transformers has shifted attention away from their unique advantages. In this talk, I will present TiRex, a new zero-shot time series foundation model built on xLSTM, an enhanced recurrent architecture that combines the state-tracking power of LSTMs with in-context learning capabilities previously seen only in Transformers. TiRex leverages these properties to deliver state-of-the-art zero-shot forecasting results on the HuggingFace GiftEval and Chronos-ZS benchmarks, where it outperforms significantly larger Transformer-based models from Google, Amazon, Salesforce, and Alibaba. Beyond its benchmark results, TiRex demonstrates that recurrent models cannot only rival but Pareto-dominate Transformers in accuracy, efficiency, and interpretability, suggesting a new generation of sustainable, foundation models for temporal intelligence.

Zeitraum	04 Nov. 2025
Ereignistitel	INNS Webinar Series
Veranstaltungstyp	Sonstiges
Bekanntheitsgrad	International