TimeRouter routes among time-series foundation models via discriminative routing, selective gating and ensemble fallback, reporting SOTA LB MASE 0.6765 on GIFT-EVAL.
Conversational time series foundation models: Towards explainable and effective forecasting.arXiv preprint arXiv:2512.16022,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
KairosAgent fuses LLM semantic reasoning with TSFM numerical forecasting through dynamic tool use and RL-based multi-turn refinement to deliver superior zero-shot multimodal time series predictions.
AME-TS is a structure-guided sparse MoE foundation model for time series that aligns expert routing with series-level temporal descriptors to achieve strong accuracy-efficiency tradeoffs on GIFT-Eval while improving specialization stability.
TempoWave maps scalar observations to multi-wavelet multi-scale digit embeddings that override standard LLM tokens and improve forecasting performance on five context-enriched benchmarks to a new state-of-the-art.
citing papers explorer
-
TimeRouter: Efficient and Adaptive Routing of Time-Series Foundation Models
TimeRouter routes among time-series foundation models via discriminative routing, selective gating and ensemble fallback, reporting SOTA LB MASE 0.6765 on GIFT-EVAL.
-
KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning
KairosAgent fuses LLM semantic reasoning with TSFM numerical forecasting through dynamic tool use and RL-based multi-turn refinement to deliver superior zero-shot multimodal time series predictions.
-
AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
AME-TS is a structure-guided sparse MoE foundation model for time series that aligns expert routing with series-level temporal descriptors to achieve strong accuracy-efficiency tradeoffs on GIFT-Eval while improving specialization stability.
-
Speaking Numbers to LLMs: Multi-Wavelet Number Embeddings for Time Series Forecasting
TempoWave maps scalar observations to multi-wavelet multi-scale digit embeddings that override standard LLM tokens and improve forecasting performance on five context-enriched benchmarks to a new state-of-the-art.