Study model composition across expert towers
Investigate how different backbone choices for the perception, reasoning, and forecasting expert towers affect the performance of unified time-series and language models.
References
The choice of backbone for each expert tower is not limited under this framework, and we leave the study of model composition as future work.
— TimeBraid: Unifying Time Series and Language for Understanding and Forecasting
(2609.29792 - Wang et al., 24 Sep 2026) in Section 3, subsection “Unified Time-Series and Language Modeling,” paragraph “Tri-Expert Architecture”
We leave the study of using different time-series foundation models for different experts for future work.
— TimeBraid: Unifying Time Series and Language for Understanding and Forecasting
(2609.29792 - Wang et al., 24 Sep 2026) in Section 5, subsection “Ablation Studies,” paragraph “RQ2: Expert Separation”
Understanding how this capacity threshold interacts with model architecture and task complexity remains an open question.
— Lapras: Latent Reasoning for Time Series Language Models
(2610.11111 - Chen et al., 8 Oct 2026) in Section 6, “Limitations and future work,” p. 9