arXiv cs.CL· Hedi Zisling, Liran Nochumsohn, Ilan Naiman, Mihir Parmar, Omri Azencot·· 2 天前AI 评分31
双重视角互补表征如何提升时间序列推理能力
Twice Upon a Time: Complementary Representations for Time-Series Reasoning
AI 导读
基于 Qwen3-VL-8B 的双视图模型将线图与归一化延迟嵌入结合，在 TSRBench 上把整体准确率从单用线图的 44.5% 提升至 53.2%，超过最强专用 TSLM 基线的 36.7%。该模型在 TSExam 上达到 89.9% 准确率，在多变量 ChatTS 对齐上取得 86.8% 数值准确率。消融实验显示，两种视图组合在预测与推理任务上的增益尤为显著。
正文 · 原文
Abstract:Time Series Language Models (TSLMs) enable language-based understanding and reasoning over temporal data, yet a fundamental question remains: what information should their time-series representations preserve, and what variation should they factor out? Existing TSLMs typically expose the language model to a single representation, imposing a fixed inductive bias across downstream tasks. We instead introduce complementary representations as a design principle for time-series reasoning. Our model combines two visual views: line plots preserve absolute measurements and the observed coordinate frame, while normalized delay embeddings factor out positive amplitude rescaling and offsets while exposing temporal structure. Dedicated visual encoders integrate both views into a shared language model through visual tokens and multi-level feature fusion. Evaluation-time interventions verify that the two views exhibit distinct invariance profiles, while single-view ablations show that their combination is particularly beneficial beyond basic perception, with the large gains in prediction and reasoning. Built on Qwen3-VL-8B, our dual-view model improves overall TSRBench accuracy from 44.5% with line plots alone to 53.2%, substantially exceeding the strongest evaluated dedicated TSLM baseline at 36.7%. It further achieves 89.9% accuracy on TSExam and 86.8% numerical accuracy on multivariate ChatTS alignment. Together, these results demonstrate that complementary representations provide an effective design principle for general-purpose TSLMs, enabling models to exploit temporal structure without sacrificing access to the original measurement frame.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22327 [cs.LG] |
| (or arXiv:2610.22327v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22327 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hedi Zisling [view email]
[v1]
Thu, 15 Oct 2026 17:52:18 UTC (493 KB)
来源：arXiv cs.CL · arxiv.org