← Back to the wire

TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning

AchievementResearchJul 9, 2026

TSRouter, developed by Fangxu Yu, is a graph-based dynamic routing framework that selects the optimal modality and model for time series reasoning queries. It constructs a heterogeneous graph of task, query, modality, and model nodes to evaluate modality-model pairs based on performance-cost preferences. Evaluations across four tasks show "16% to 46% relative improvements" over baselines, with robust zero-shot generalization to unseen models and reduced computational overhead.

Receipt № 5981 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01medPRIMARY
TSRouterModelFangxu YuPerson
Canonical: https://arxiv.org/abs/2607.08940