TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
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 jointly, and a subset of covariates is known ahead of time. Existing Transformer-based time series foundation models capture cross-variate dependencies but incur quadratic complexity in context length and require full-history recomputation as new observations arrive. TiRex-2 addresses these limitations through a memory-
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 45%amazon-science/chronos-forecasting →
- LinkedLinked via arxiv author · 85%Patrick Podest →
“TiRex-2: Generalizing TiRex to Multivariate Data and Streaming”
- LinkedLinked via arxiv author · 85%Marco Pichler →
“TiRex-2: Generalizing TiRex to Multivariate Data and Streaming”
- LinkedLinked via arxiv author · 85%Elias Bürger →
“TiRex-2: Generalizing TiRex to Multivariate Data and Streaming”
- LinkedLinked via arxiv author · 85%Levente Zólyomi →
“TiRex-2: Generalizing TiRex to Multivariate Data and Streaming”
- LinkedLinked via arxiv author · 85%Bernhard Voggenberger →
“TiRex-2: Generalizing TiRex to Multivariate Data and Streaming”
- LinkedLinked via arxiv author · 85%Wilhelm Berghammer →
“TiRex-2: Generalizing TiRex to Multivariate Data and Streaming”
- LinkedLinked via arxiv author · 85%Daniel Klotz →
“TiRex-2: Generalizing TiRex to Multivariate Data and Streaming”