analiza aiqbench
The paper is a preprint on time-series language models that feeds a vision-language model two complementary plot-based views: raw line plots that keep absolute scale, and normalized delay embeddings that discard amplitude and offset. The reported gains are benchmark-specific (TSRBench rises from 44.5% to 53.2%, against a 36.7% dedicated-TSLM baseline), so readers should check whether they hold on real-world forecasting and reasoning tasks. The core idea, that a model may need to be given explicitly invariant views rather than one fixed representation, is useful for anyone building multimodal models over sensor or temporal data.
Twice Upon a Time: Complementary Representations for Time-Series Reasoning
arXiv:2610.22327v1 Announce Type: cross 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.
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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
arXiv:2610.22327 [cs.LG]
(or arXiv:2610.22327v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.22327 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 317 cuvinte
Subiecte conexe
Article: Governing AI in the Cloud: A Practical Guide for Architects
InfoQ · 15 iun. 2026
Building a Foundation Stack for General-Purpose Robots
IEEE Spectrum · 13 iul. 2026
LiveLaw Supreme Court Half-Yearly Digest: January - June 2026 [Part 2]
livelaw.in · 13 sept. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026