# LLaTiSA：迈向从视觉感知到语义的难度分层时间序列推理

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-19 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmoctgb0905kwslsj1iwxpcdq
- 原文链接：https://arxiv.org/abs/2604.17295

## AI 摘要

研究团队提出四层认知复杂度分类法定义时间序列推理（TSR）任务，发布包含83k样本的HiTSR数据集，涵盖多样化任务组合与验证CoT轨迹。基于此开发的LLaTiSA模型整合可视化模式与精度校准数值表增强视觉语言模型（VLM）的时间感知，经多阶段课程微调策略训练，在多样TSR任务及真实场景中实现卓越性能与强分布外泛化。

## 正文

Comprehensive understanding of time series remains a significant challenge for Large Language Models (LLMs). Current research is hindered by fragmented task definitions and benchmarks with inherent ambiguities, precluding rigorous evaluation and the development of unified Time Series Reasoning Models(TSRMs). To bridge this gap, we formalize Time Series Reasoning (TSR) via a four-level taxonomy of increasing cognitive complexity. We introduce HiTSR, a hierarchical time series reasoning dataset comprising 83k samples with diverse task combinations and verified Chain-of-Thought (CoT) trajectories. Leveraging HiTSR, we propose LLaTiSA, a strong TSRM that integrates visualized patterns with precision-calibrated numerical tables to enhance the temporal perception of Vision-Language Models (VLMs). Through a multi-stage curriculum fine-tuning strategy, LLaTiSA achieves superior performance and exhibits robust out-of-distribution generalization across diverse TSR tasks and real-world scenarios. Our code is available at https://github.com/RainingNovember/LLaTiSA.