---
title: "STReasoner — paper by Ni et al. (2026) — summary and ideas"
description: "LLMs are increasingly applied to time-series domains. 109 references, cited by 2 papers here."
authors: ["Juntong Ni", "Shiyu Wang", "Qi He", "Ming Jin", "Wei Jin"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.702/"
doi: "10.18653/v1/2026.acl-long.702"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/ni-2026-streasoner-empowering-llms-spatio-temporal/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ni-2026-streasoner-empowering-llms-spatio-temporal/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/) / STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning

# STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning

**Authors:** Juntong Ni, [Shiyu Wang](https://md.research.elamur.ai/free/en/authors/shiyu-wang/), [Qi He](https://md.research.elamur.ai/free/en/authors/qi-he/), [Ming Jin](https://md.research.elamur.ai/free/en/authors/ming-jin/) and Wei Jin · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.702/) · [PDF](https://aclanthology.org/2026.acl-long.702.pdf) · [DOI 10.18653/v1/2026.acl-long.702](https://doi.org/10.18653/v1/2026.acl-long.702) · [OpenAlex](https://openalex.org/W7166802108)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · 2 in our library, of the 149,439 papers whose bibliographies we read

## Summary
LLMs are increasingly applied to time-series domains. Yet settings such as traffic networks, power grids or epidemic spread need more than point forecasts. Decision-makers want to know the cause, location and timing of events, which means linking signals across graph-connected nodes while accounting for propagation delays. The authors formalise this as spatio-temporal reasoning in time series: a model receives a query, per-node series and a graph, and returns a reasoning trace and an answer.

Paired data of this kind with text barely exists, so they build a synthesis pipeline. In it, six LLM agents draft, parse and validate scenarios, then configure network SDEs with time-varying adjacency and lags. This yields ST-Bench, which has four tasks plus a real-world subset for zero-shot testing.

Their model, STReasoner, pairs a time series encoder with an LLM. It is trained in three stages: alignment, SFT and RL. The RL stage uses S-GRPO, which gives extra reward only when graph input genuinely improves results. STReasoner clearly outperforms baselines at a small fraction of proprietary-model cost. This suggests a practical path toward explainable, spatially grounded decision support.

## Key points
- ST-Bench spans four kinds of task: reasoning about etiology across space, identifying spatial entities, reasoning about spatial correlations, and forecasting in context. It also includes a real-world dataset for zero-shot evaluation.
- STReasoner reports average accuracy gains of 17%–135%. It achieves this at roughly 0.004× the cost of proprietary models.
- S-GRPO increases reliance on the graph during training. On Task 1, the accuracy gap between runs with and without the graph grows from 0.5 at step 1 to 6.2 at step 51. Moderate spatial reward weights (α = 0.1 or 0.2) work best, while α = 0, 0.5 or 1 hurts at least one metric.
- The time series encoder is a simple MLP. Full training takes about 27 h, 215.77 GPU-hours and 30.45 kg CO2e.
- Code is available at github.com/LingFengGold/STReasoner. The authors acknowledge that the work relies heavily on synthetic data.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Microsoft](https://md.research.elamur.ai/free/en/companies/microsoft/) — Company, Redmond, United States · 378 works · 161,630 citations
- [Emory University](https://md.research.elamur.ai/free/en/universities/emory-university/) — University, Atlanta, United States · 42 works · 39,899 citations
- [Griffith University](https://md.research.elamur.ai/free/en/universities/griffith-university/) — University, Brisbane, Australia · 11 works · 4,223 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 188 works · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 493 works · [⚙️ Building and Construction](https://md.research.elamur.ai/free/en/shelves/engineering/building-and-construction/) · 7 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Juntong Ni, Shiyu Wang, Qi He, Ming Jin and Wei Jin. 2026. STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{ni2026streasoner,
  title = {{STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning}},
  author = {Juntong Ni, Shiyu Wang, Qi He, Ming Jin and Wei Jin},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.702},
  url = {https://doi.org/10.18653/v1/2026.acl-long.702}
}
```

- [← previous StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding](https://md.research.elamur.ai/free/en/papers/wang-2026-streammeco-long-term-agent-memory/)
- [next → Stress Testing Factual Consistency Metrics for Long-Document Summarization](https://md.research.elamur.ai/free/en/papers/mujahid-2026-stress-testing-factual-consistency-metrics/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/)

## References

109 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Janice Ahn, Rishu Verma, Renze Lou, Di Liu, Rui Zhang, and Wenpeng Yin. 2024. [Large language models for mathematical reasoning: Progresses and challenges](https://md.research.elamur.ai/free/en/papers/ahn-2024-large-language-models-mathematical-reasoning/). arXiv preprint arXiv:2402.00157.
2. Anthropic. 2025. Introducing claude sonnet 4.5. [https://www.anthropic.com/news/](https://www.anthropic.com/news/) claude-sonnet-4-5. [↗](https://www.anthropic.com/news/)
3. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and 1 others. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI conference on a… [find](https://scholar.google.com/scholar?q=Maciej+Besta%2C+Nils+Blach%2C+Ales+Kubicek%2C+Robert+Gerstenberger%2C+Michal+Podstawski%2C+Lukas+Gianinazzi%2C+Joanna+Gajda%2C+Tomasz+Lehmann%2C+Hubert+Niewiadomski%2C+Piotr+Nyczyk%2C+and+1+others%2E+2024%2E+Graph+of+thought)
4. Yifu Cai, Arjun Choudhry, Mononito Goswami, and Artur Dubrawski. 2024. Timeseriesexam: A time series understanding exam. arXiv preprint arXiv:2410.14752. — [arXiv:2410.14752](https://arxiv.org/abs/2410.14752) [find](https://scholar.google.com/scholar?q=Yifu+Cai%2C+Arjun+Choudhry%2C+Mononito+Goswami%2C+and+Artur+Dubrawski%2E+2024%2E+Timeseriesexam%3A+A+time+series+understanding+exam%2E+arXiv+preprint+arXiv%3A2410%2E14752%2E+%E2%80%94+%5BarXiv%3A2410%2E14752%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F241)
5. Jialin Chen, Aosong Feng, Ziyu Zhao, Juan Garza, Gaukhar Nurbek, Cheng Qin, Ali Maatouk, Leandros Tassiulas, Yifeng Gao, and Rex Ying. 2025. Mtbench: A multimodal time series benchmark for temporal reasoning and question answering. arXiv preprint arXiv:2503.16858. — [arXiv:2503.16858](https://arxiv.org/abs/2503.16858) [find](https://scholar.google.com/scholar?q=Jialin+Chen%2C+Aosong+Feng%2C+Ziyu+Zhao%2C+Juan+Garza%2C+Gaukhar+Nurbek%2C+Cheng+Qin%2C+Ali+Maatouk%2C+Leandros+Tassiulas%2C+Yifeng+Gao%2C+and+Rex+Ying%2E+2025%2E+Mtbench%3A+A+multimodal+time+series+benchmark+for+temporal+re)
6. Wei Chen and Yuxuan Liang. 2025. Learning with calibration: Exploring test-time computing of spatio-temporal forecasting. arXiv preprint arXiv:2506.00635. — [arXiv:2506.00635](https://arxiv.org/abs/2506.00635) [find](https://scholar.google.com/scholar?q=Wei+Chen+and+Yuxuan+Liang%2E+2025%2E+Learning+with+calibration%3A+Exploring+test%2Dtime+computing+of+spatio%2Dtemporal+forecasting%2E+arXiv+preprint+arXiv%3A2506%2E00635%2E+%E2%80%94+%5BarXiv%3A2506%2E00635%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F25)
7. Zixu Cheng, Jian Hu, Ziquan Liu, Chenyang Si, Wei Li, and Shaogang Gong. 2025. V-star: Benchmarking video-llms on video spatio-temporal reasoning. arXiv preprint arXiv:2503.11495. — [arXiv:2503.11495](https://arxiv.org/abs/2503.11495) [find](https://scholar.google.com/scholar?q=Zixu+Cheng%2C+Jian+Hu%2C+Ziquan+Liu%2C+Chenyang+Si%2C+Wei+Li%2C+and+Shaogang+Gong%2E+2025%2E+V%2Dstar%3A+Benchmarking+video%2Dllms+on+video+spatio%2Dtemporal+reasoning%2E+arXiv+preprint+arXiv%3A2503%2E11495%2E+%E2%80%94+%5BarXiv%3A2503%2E11495%5D)
8. Winnie Chow, Lauren Gardiner, Haraldur T Hallgríms-son, Maxwell A Xu, and Shirley You Ren. 2024. Towards time series reasoning with llms. arXiv preprint arXiv:2409.11376. — [arXiv:2409.11376](https://arxiv.org/abs/2409.11376) [find](https://scholar.google.com/scholar?q=Winnie+Chow%2C+Lauren+Gardiner%2C+Haraldur+T+Hallgr%C3%ADms%2Dson%2C+Maxwell+A+Xu%2C+and+Shirley+You+Ren%2E+2024%2E+Towards+time+series+reasoning+with+llms%2E+arXiv+preprint+arXiv%3A2409%2E11376%2E+%E2%80%94+%5BarXiv%3A2409%2E11376%5D%28https%3A%2F%2F)
9. Zhixuan Chu, Hui Ding, Guang Zeng, Shiyu Wang, and Yiming Li. 2024. Causal interventional prediction system for robust and explainable effect forecasting. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pages 4431–4438. [find](https://scholar.google.com/scholar?q=Zhixuan+Chu%2C+Hui+Ding%2C+Guang+Zeng%2C+Shiyu+Wang%2C+and+Yiming+Li%2E+2024%2E+Causal+interventional+prediction+system+for+robust+and+explainable+effect+forecasting%2E+In+Proceedings+of+the+33rd+ACM+International+)
10. Yuchen Fang, Shiyu Wang, Yuxuan Liang, Zhou Ye, Yang Xiang, Yan Zhao, and Kai Zheng. 2026. Efficient high-dimensional time series forecasting with transformers: A channel reordering perspective. In Proceedings of the ACM Web Conference 2026. [find](https://scholar.google.com/scholar?q=Yuchen+Fang%2C+Shiyu+Wang%2C+Yuxuan+Liang%2C+Zhou+Ye%2C+Yang+Xiang%2C+Yan+Zhao%2C+and+Kai+Zheng%2E+2026%2E+Efficient+high%2Ddimensional+time+series+forecasting+with+transformers%3A+A+channel+reordering+perspective%2E+In+Pr)
11. Jie Feng, Shengyuan Wang, Tianhui Liu, Yanxin Xi, and Yong Li. 2025a. Urbanllava: A multi-modal large language model for urban intelligence with spatial reasoning and understanding. arXiv preprint arXiv:2506.23219. — [arXiv:2506.23219](https://arxiv.org/abs/2506.23219) [find](https://scholar.google.com/scholar?q=Jie+Feng%2C+Shengyuan+Wang%2C+Tianhui+Liu%2C+Yanxin+Xi%2C+and+Yong+Li%2E+2025a%2E+Urbanllava%3A+A+multi%2Dmodal+large+language+model+for+urban+intelligence+with+spatial+reasoning+and+understanding%2E+arXiv+preprint+arX)
12. Jie Feng, Jun Zhang, Tianhui Liu, Xin Zhang, Tianjian Ouyang, Junbo Yan, Yuwei Du, Siqi Guo, and Yong Li. 2025b. Citybench: Evaluating the capabilities of large language models for urban tasks. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, pages 5413–5… [find](https://scholar.google.com/scholar?q=Jie+Feng%2C+Jun+Zhang%2C+Tianhui+Liu%2C+Xin+Zhang%2C+Tianjian+Ouyang%2C+Junbo+Yan%2C+Yuwei+Du%2C+Siqi+Guo%2C+and+Yong+Li%2E+2025b%2E+Citybench%3A+Evaluating+the+capabilities+of+large+language+models+for+urban+tasks%2E+In+Pro)
13. Kaituo Feng, Kaixiong Gong, Bohao Li, Zonghao Guo, Yibing Wang, Tianshuo Peng, Junfei Wu, Xiaoying Zhang, Benyou Wang, and Xiangyu Yue. 2025c. Video-r1: Reinforcing video reasoning in mllms. arXiv preprint arXiv:2503.21776. — [arXiv:2503.21776](https://arxiv.org/abs/2503.21776) [find](https://scholar.google.com/scholar?q=Kaituo+Feng%2C+Kaixiong+Gong%2C+Bohao+Li%2C+Zonghao+Guo%2C+Yibing+Wang%2C+Tianshuo+Peng%2C+Junfei+Wu%2C+Xiaoying+Zhang%2C+Benyou+Wang%2C+and+Xiangyu+Yue%2E+2025c%2E+Video%2Dr1%3A+Reinforcing+video+reasoning+in+mllms%2E+arXiv+pre)
14. Fanzhe Fu, Junru Chen, Jing Zhang, Carl Yang, Lvbin Ma, and Yang Yang. 2024. Are synthetic time-series data really not as good as real data? arXiv preprint arXiv:2402.00607. — [arXiv:2402.00607](https://arxiv.org/abs/2402.00607) [find](https://scholar.google.com/scholar?q=Fanzhe+Fu%2C+Junru+Chen%2C+Jing+Zhang%2C+Carl+Yang%2C+Lvbin+Ma%2C+and+Yang+Yang%2E+2024%2E+Are+synthetic+time%2Dseries+data+really+not+as+good+as+real+data%3F+arXiv+preprint+arXiv%3A2402%2E00607%2E+%E2%80%94+%5BarXiv%3A2402%2E00607%5D%28https)
15. Haotian Gao, Zheng Dong, Jiawei Yong, Shintaro Fukushima, Kenjiro Taura, and Renhe Jiang. 2025. How different from the past? spatio-temporal time series forecasting with self-supervised deviation learning. arXiv preprint arXiv:2510.04908. — [arXiv:2510.04908](https://arxiv.org/abs/2510.04908) [find](https://scholar.google.com/scholar?q=Haotian+Gao%2C+Zheng+Dong%2C+Jiawei+Yong%2C+Shintaro+Fukushima%2C+Kenjiro+Taura%2C+and+Renhe+Jiang%2E+2025%2E+How+different+from+the+past%3F+spatio%2Dtemporal+time+series+forecasting+with+self%2Dsupervised+deviation+lear)
16. Parker Glenn, Parag Dakle, Liang Wang, and Preethi Raghavan. 2024. Blendsql: A scalable dialect for unifying hybrid question answering in relational algebra. In Findings of the Association for Computational Linguistics: ACL 2024, pages 453–466. [find](https://scholar.google.com/scholar?q=Parker+Glenn%2C+Parag+Dakle%2C+Liang+Wang%2C+and+Preethi+Raghavan%2E+2024%2E+Blendsql%3A+A+scalable+dialect+for+unifying+hybrid+question+answering+in+relational+algebra%2E+In+Findings+of+the+Association+for+Computa)
17. Francesco Iafrate and Stefano Iacus. 2024. Ergodic network stochastic differential equations. arXiv preprint arXiv:2412.17779. — [arXiv:2412.17779](https://arxiv.org/abs/2412.17779) [find](https://scholar.google.com/scholar?q=Francesco+Iafrate+and+Stefano+Iacus%2E+2024%2E+Ergodic+network+stochastic+differential+equations%2E+arXiv+preprint+arXiv%3A2412%2E17779%2E+%E2%80%94+%5BarXiv%3A2412%2E17779%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2412%2E17779%29)
18. Yue Jiang, Qin Chao, Yile Chen, Xiucheng Li, Shuai Liu, and Gao Cong. 2024. Urbanllm: Autonomous urban activity planning and management with large language models. arXiv preprint arXiv:2406.12360. [find](https://scholar.google.com/scholar?q=Yue+Jiang%2C+Qin+Chao%2C+Yile+Chen%2C+Xiucheng+Li%2C+Shuai+Liu%2C+and+Gao+Cong%2E+2024%2E+Urbanllm%3A+Autonomous+urban+activity+planning+and+management+with+large+language+models%2E+arXiv+preprint+arXiv%3A2406%2E12360%2E)
19. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025. [Search-r1: Training llms to reason and leverage search engines with reinforcement learning](https://md.research.elamur.ai/free/en/papers/jin-2025-search-r1-training-llms-reason/). arXiv preprint arXiv:2503.09516.
20. Ming Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu, James Y Zhang, Xiaoming Shi, Pin-Yu Chen, Yuxuan Liang, Yuan-Fang Li, Shirui Pan, and 1 others. 2023a. [Time-llm: Time series forecasting by reprogramming large language models](https://md.research.elamur.ai/free/en/papers/jin-2023-time-llm-time-series-forecasting/). arXiv preprint arXiv:2310.01728.
21. Shengbo Gong, Xianfeng Tang, Carl Yang, and 1 others. 2025. Beyond chunks and graphs: Retrieval-augmented generation through triplet-driven thinking. arXiv preprint arXiv:2508.02435. [find](https://scholar.google.com/scholar?q=Shengbo+Gong%2C+Xianfeng+Tang%2C+Carl+Yang%2C+and+1+others%2E+2025%2E+Beyond+chunks+and+graphs%3A+Retrieval%2Daugmented+generation+through+triplet%2Ddriven+thinking%2E+arXiv+preprint+arXiv%3A2508%2E02435%2E)
22. Ming Jin, Qingsong Wen, Yuxuan Liang, Chaoli Zhang, Siqiao Xue, Xue Wang, James Zhang, Yi Wang, Haifeng Chen, Xiaoli Li, and 1 others. 2023b. Large models for time series and spatio-temporal data: A survey and outlook. arXiv preprint arXiv:2310.10196. — [arXiv:2310.10196](https://arxiv.org/abs/2310.10196) [find](https://scholar.google.com/scholar?q=Ming+Jin%2C+Qingsong+Wen%2C+Yuxuan+Liang%2C+Chaoli+Zhang%2C+Siqiao+Xue%2C+Xue+Wang%2C+James+Zhang%2C+Yi+Wang%2C+Haifeng+Chen%2C+Xiaoli+Li%2C+and+1+others%2E+2023b%2E+Large+models+for+time+series+and+spatio%2Dtemporal+data%3A+A+s)
23. Tong Guan, Zijie Meng, Dianqi Li, Shiyu Wang, Chao-Han Huck Yang, Qingsong Wen, Zuozhu Liu, Sabato Marco Siniscalchi, Ming Jin, and Shirui Pan. 2025. Timeomni-1: Incentivizing complex reasoning with time series in large language models. arXiv preprint arXiv:2509.24803. — [arXiv:2509.24803](https://arxiv.org/abs/2509.24803) [find](https://scholar.google.com/scholar?q=Tong+Guan%2C+Zijie+Meng%2C+Dianqi+Li%2C+Shiyu+Wang%2C+Chao%2DHan+Huck+Yang%2C+Qingsong+Wen%2C+Zuozhu+Liu%2C+Sabato+Marco+Siniscalchi%2C+Ming+Jin%2C+and+Shirui+Pan%2E+2025%2E+Timeomni%2D1%3A+Incentivizing+complex+reasoning+with+t)
24. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). Advances in neural information processing systems, 35:22199– 22213.
25. Yanchu Guan, Dong Wang, Zhixuan Chu, Shiyu Wang, Feiyue Ni, Ruihua Song, and Chenyi Zhuang. 2024. Intelligent agents with llm-based process automation. In Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining, pages 5018– 5027. [find](https://scholar.google.com/scholar?q=Yanchu+Guan%2C+Dong+Wang%2C+Zhixuan+Chu%2C+Shiyu+Wang%2C+Feiyue+Ni%2C+Ruihua+Song%2C+and+Chenyi+Zhuang%2E+2024%2E+Intelligent+agents+with+llm%2Dbased+process+automation%2E+In+Proceedings+of+the+30th+ACM+SIGKDD+conference)
26. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
27. Kethmi Hirushini Hettige, Jiahao Ji, Cheng Long, Shili Xiang, Gao Cong, and Jingyuan Wang. 2025. A modular multitask reasoning framework integrating spatio-temporal models and llms. arXiv preprint arXiv:2506.20073. — [arXiv:2506.20073](https://arxiv.org/abs/2506.20073) [find](https://scholar.google.com/scholar?q=Kethmi+Hirushini+Hettige%2C+Jiahao+Ji%2C+Cheng+Long%2C+Shili+Xiang%2C+Gao+Cong%2C+and+Jingyuan+Wang%2E+2025%2E+A+modular+multitask+reasoning+framework+integrating+spatio%2Dtemporal+models+and+llms%2E+arXiv+preprint+arX)
28. Yaxuan Kong, Yiyuan Yang, Yoontae Hwang, Wenjie Du, Stefan Zohren, Zhangyang Wang, Ming Jin, and Qingsong Wen. 2025. [Time-mqa: Time series multi-task question answering with context enhancement](https://md.research.elamur.ai/free/en/papers/kong-2025-time-mqa-time-series-multi/). arXiv preprint arXiv:2503.01875.
29. Patrick Langer, Thomas Kaar, Max Rosenblattl, Maxwell A Xu, Winnie Chow, Martin Maritsch, Aradhana Verma, Brian Han, Daniel Seung Kim, Henry Chubb, and 1 others. 2025. Opentslm: Timeseries language models for reasoning over multivariate medical text-and time-series data. arXiv preprint arXiv:2510.02… [find](https://scholar.google.com/scholar?q=Patrick+Langer%2C+Thomas+Kaar%2C+Max+Rosenblattl%2C+Maxwell+A+Xu%2C+Winnie+Chow%2C+Martin+Maritsch%2C+Aradhana+Verma%2C+Brian+Han%2C+Daniel+Seung+Kim%2C+Henry+Chubb%2C+and+1+others%2E+2025%2E+Opentslm%3A+Timeseries+language+mo)
30. Max SY Lau, C Jessica E Metcalf, Zewen Liu, Bryan T Grenfell, and Wei Jin. 2026. Toward ai foundation models for epidemics: Promise, challenges, and paths forward. Proceedings of the National Academy of Sciences, 123(13):e2526192123. [find](https://scholar.google.com/scholar?q=Max+SY+Lau%2C+C+Jessica+E+Metcalf%2C+Zewen+Liu%2C+Bryan+T+Grenfell%2C+and+Wei+Jin%2E+2026%2E+Toward+ai+foundation+models+for+epidemics%3A+Promise%2C+challenges%2C+and+paths+forward%2E+Proceedings+of+the+National+Academy+)
31. Congcong Hu, Yuang Shi, Fan Huang, Yang Xiang, Zhou Ye, Ming Jin, and Shiyu Wang. 2026. Event-cast: Hybrid demand forecasting in e-commerce with llm-based event knowledge. arXiv preprint arXiv:2602.07695. — [arXiv:2602.07695](https://arxiv.org/abs/2602.07695) [find](https://scholar.google.com/scholar?q=Congcong+Hu%2C+Yuang+Shi%2C+Fan+Huang%2C+Yang+Xiang%2C+Zhou+Ye%2C+Ming+Jin%2C+and+Shiyu+Wang%2E+2026%2E+Event%2Dcast%3A+Hybrid+demand+forecasting+in+e%2Dcommerce+with+llm%2Dbased+event+knowledge%2E+arXiv+preprint+arXiv%3A2602%2E07)
32. Yongjia Lei, Haoyu Han, Ryan A Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M Halappanavar, Jiliang Tang, and Yu Wang. 2025. Mixture of structural-and-textual retrieval over text-rich graph knowledge bases. In Findings of the Association for Computational Linguistics: ACL 2025, pages 18306–1832… [find](https://scholar.google.com/scholar?q=Yongjia+Lei%2C+Haoyu+Han%2C+Ryan+A+Rossi%2C+Franck+Dernoncourt%2C+Nedim+Lipka%2C+Mahantesh+M+Halappanavar%2C+Jiliang+Tang%2C+and+Yu+Wang%2E+2025%2E+Mixture+of+structural%2Dand%2Dtextual+retrieval+over+text%2Drich+graph+knowl)
33. Wenxuan Huang, Bohan Jia, Zijie Zhai, Shaosheng Cao, Zheyu Ye, Fei Zhao, Zhe Xu, Yao Hu, and Shaohui Lin. 2025. [Vision-r1: Incentivizing reasoning capability in multimodal large language models](https://md.research.elamur.ai/free/en/papers/huang-2025-vision-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2503.06749.
34. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, and 1 others. 2024a. [Llava-onevision: Easy visual task transfer](https://md.research.elamur.ai/free/en/papers/li-2024-llava-onevision-easy-visual-task/). arXiv preprint arXiv:2408.03326.
35. Wenbin Li, Di Yao, Ruibo Zhao, Wenjie Chen, Zijie Xu, Chengxue Luo, Chang Gong, Quanliang Jing, Haining Tan, and Jingping Bi. 2025. Stbench: Assessing the ability of large language models in spatiotemporal analysis. In Companion Proceedings of the ACM on Web Conference 2025, pages 749–752. [find](https://scholar.google.com/scholar?q=Wenbin+Li%2C+Di+Yao%2C+Ruibo+Zhao%2C+Wenjie+Chen%2C+Zijie+Xu%2C+Chengxue+Luo%2C+Chang+Gong%2C+Quanliang+Jing%2C+Haining+Tan%2C+and+Jingping+Bi%2E+2025%2E+Stbench%3A+Assessing+the+ability+of+large+language+models+in+spatiotem)
36. Zhonghang Li, Lianghao Xia, Jiabin Tang, Yong Xu, Lei Shi, Long Xia, Dawei Yin, and Chao Huang. 2024b. Urbangpt: Spatio-temporal large language models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 5351–5362. [find](https://scholar.google.com/scholar?q=Zhonghang+Li%2C+Lianghao+Xia%2C+Jiabin+Tang%2C+Yong+Xu%2C+Lei+Shi%2C+Long+Xia%2C+Dawei+Yin%2C+and+Chao+Huang%2E+2024b%2E+Urbangpt%3A+Spatio%2Dtemporal+large+language+models%2E+In+Proceedings+of+the+30th+ACM+SIGKDD+Conference)
37. Zhonghang Li, Lianghao Xia, Yong Xu, and Chao Huang. 2023. Gpt-st: generative pre-training of spatio-temporal graph neural networks. Advances in neural information processing systems, 36:70229– 70246. [find](https://scholar.google.com/scholar?q=Zhonghang+Li%2C+Lianghao+Xia%2C+Yong+Xu%2C+and+Chao+Huang%2E+2023%2E+Gpt%2Dst%3A+generative+pre%2Dtraining+of+spatio%2Dtemporal+graph+neural+networks%2E+Advances+in+neural+information+processing+systems%2C+36%3A70229%E2%80%93+70246%2E)
38. Yuxuan Liang, Haomin Wen, Yuqi Nie, Yushan Jiang, Ming Jin, Dongjin Song, Shirui Pan, and Qingsong Wen. 2024. Foundation models for time series analysis: A tutorial and survey. In Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining, pages 6555–6565. [find](https://scholar.google.com/scholar?q=Yuxuan+Liang%2C+Haomin+Wen%2C+Yuqi+Nie%2C+Yushan+Jiang%2C+Ming+Jin%2C+Dongjin+Song%2C+Shirui+Pan%2C+and+Qingsong+Wen%2E+2024%2E+Foundation+models+for+time+series+analysis%3A+A+tutorial+and+survey%2E+In+Proceedings+of+the+3)
39. Yuxuan Liang, Haomin Wen, Yutong Xia, Ming Jin, Bin Yang, Flora Salim, Qingsong Wen, Shirui Pan, and Gao Cong. 2025. Foundation models for spatiotemporal data science: A tutorial and survey. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, pages 6063–6073… [find](https://scholar.google.com/scholar?q=Yuxuan+Liang%2C+Haomin+Wen%2C+Yutong+Xia%2C+Ming+Jin%2C+Bin+Yang%2C+Flora+Salim%2C+Qingsong+Wen%2C+Shirui+Pan%2C+and+Gao+Cong%2E+2025%2E+Foundation+models+for+spatiotemporal+data+science%3A+A+tutorial+and+survey%2E+In+Procee)
40. Yuxuan Liang, Yutong Xia, Songyu Ke, Yiwei Wang, Qingsong Wen, Junbo Zhang, Yu Zheng, and Roger Zimmermann. 2023. Airformer: Predicting nationwide air quality in china with transformers. In Proceedings of the AAAI conference on artificial intelligence, volume 37, pages 14329–14337. [find](https://scholar.google.com/scholar?q=Yuxuan+Liang%2C+Yutong+Xia%2C+Songyu+Ke%2C+Yiwei+Wang%2C+Qingsong+Wen%2C+Junbo+Zhang%2C+Yu+Zheng%2C+and+Roger+Zimmermann%2E+2023%2E+Airformer%3A+Predicting+nationwide+air+quality+in+china+with+transformers%2E+In+Proceeding)
41. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). In The Twelfth International Conference on Learning Representations.
42. Yijun Lin, Nikhit Mago, Yu Gao, Yaguang Li, Yao-Yi Chiang, Cyrus Shahabi, and José Luis Ambite. 2018. Exploiting spatiotemporal patterns for accurate air quality forecasting using deep learning. In Proceedings of the 26th ACM SIGSPATIAL international conference on advances in geographic information… [find](https://scholar.google.com/scholar?q=Yijun+Lin%2C+Nikhit+Mago%2C+Yu+Gao%2C+Yaguang+Li%2C+Yao%2DYi+Chiang%2C+Cyrus+Shahabi%2C+and+Jos%C3%A9+Luis+Ambite%2E+2018%2E+Exploiting+spatiotemporal+patterns+for+accurate+air+quality+forecasting+using+deep+learning%2E+In+Pr)
43. Chenxi Liu, Kethmi Hirushini Hettige, Qianxiong Xu, Cheng Long, Shili Xiang, Gao Cong, Ziyue Li, and Rui Zhao. 2025a. St-llm+: Graph enhanced spatiotemporal large language models for traffic prediction. IEEE Transactions on Knowledge and Data Engineering. [find](https://scholar.google.com/scholar?q=Chenxi+Liu%2C+Kethmi+Hirushini+Hettige%2C+Qianxiong+Xu%2C+Cheng+Long%2C+Shili+Xiang%2C+Gao+Cong%2C+Ziyue+Li%2C+and+Rui+Zhao%2E+2025a%2E+St%2Dllm%2B%3A+Graph+enhanced+spatiotemporal+large+language+models+for+traffic+predictio)
44. Chenxi Liu, Sun Yang, Qianxiong Xu, Zhishuai Li, Cheng Long, Ziyue Li, and Rui Zhao. 2024a. Spatial-temporal large language model for traffic prediction. [find](https://scholar.google.com/scholar?q=Chenxi+Liu%2C+Sun+Yang%2C+Qianxiong+Xu%2C+Zhishuai+Li%2C+Cheng+Long%2C+Ziyue+Li%2C+and+Rui+Zhao%2E+2024a%2E+Spatial%2Dtemporal+large+language+model+for+traffic+prediction%2E)
45. In 2024 25th IEEE International Conference on Mobile Data Management (MDM), pages 31–40. IEEE. [find](https://scholar.google.com/scholar?q=In+2024+25th+IEEE+International+Conference+on+Mobile+Data+Management+%28MDM%29%2C+pages+31%E2%80%9340%2E+IEEE%2E)
46. Haoxin Liu, Chenghao Liu, and B Aditya Prakash. 2025b. A picture is worth a thousand numbers: Enabling llms reason about time series via visualization. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Techno… [find](https://scholar.google.com/scholar?q=Haoxin+Liu%2C+Chenghao+Liu%2C+and+B+Aditya+Prakash%2E+2025b%2E+A+picture+is+worth+a+thousand+numbers%3A+Enabling+llms+reason+about+time+series+via+visualization%2E+In+Proceedings+of+the+2025+Conference+of+the+Nat)
47. Haoxin Liu, Shangqing Xu, Zhiyuan Zhao, Lingkai Kong, Harshavardhan Prabhakar Kamarthi, Aditya Sasanur, Megha Sharma, Jiaming Cui, Qingsong Wen, Chao Zhang, and 1 others. 2024b. Time-mmd: Multi-domain multimodal dataset for time series analysis. Advances in Neural Information Processing Systems, 37:… [find](https://scholar.google.com/scholar?q=Haoxin+Liu%2C+Shangqing+Xu%2C+Zhiyuan+Zhao%2C+Lingkai+Kong%2C+Harshavardhan+Prabhakar+Kamarthi%2C+Aditya+Sasanur%2C+Megha+Sharma%2C+Jiaming+Cui%2C+Qingsong+Wen%2C+Chao+Zhang%2C+and+1+others%2E+2024b%2E+Time%2Dmmd%3A+Multi%2Ddomain)
48. Lei Liu, Shuo Yu, Runze Wang, Zhenxun Ma, and Yanming Shen. 2024c. How can large language models understand spatial-temporal data? arXiv preprint arXiv:2401.14192. — [arXiv:2401.14192](https://arxiv.org/abs/2401.14192) [find](https://scholar.google.com/scholar?q=Lei+Liu%2C+Shuo+Yu%2C+Runze+Wang%2C+Zhenxun+Ma%2C+and+Yanming+Shen%2E+2024c%2E+How+can+large+language+models+understand+spatial%2Dtemporal+data%3F+arXiv+preprint+arXiv%3A2401%2E14192%2E+%E2%80%94+%5BarXiv%3A2401%2E14192%5D%28https%3A%2F%2Farxiv%2Eo)
49. Xu Liu, Yutong Xia, Yuxuan Liang, Junfeng Hu, Yiwei Wang, Lei Bai, Chao Huang, Zhenguang Liu, Bryan Hooi, and Roger Zimmermann. 2023. Largest: A benchmark dataset for large-scale traffic forecasting. Advances in Neural Information Processing Systems, 36:75354–75371. [find](https://scholar.google.com/scholar?q=Xu+Liu%2C+Yutong+Xia%2C+Yuxuan+Liang%2C+Junfeng+Hu%2C+Yiwei+Wang%2C+Lei+Bai%2C+Chao+Huang%2C+Zhenguang+Liu%2C+Bryan+Hooi%2C+and+Roger+Zimmermann%2E+2023%2E+Largest%3A+A+benchmark+dataset+for+large%2Dscale+traffic+forecasting%2E+)
50. Yezi Liu, William Youngwoo Chung, Hanning Chen, Calvin Yeung, and Mohsen Imani. 2025c. Are hypervectors enough? single-call llm reasoning over knowledge graphs. arXiv preprint arXiv:2512.09369. [find](https://scholar.google.com/scholar?q=Yezi+Liu%2C+William+Youngwoo+Chung%2C+Hanning+Chen%2C+Calvin+Yeung%2C+and+Mohsen+Imani%2E+2025c%2E+Are+hypervectors+enough%3F+single%2Dcall+llm+reasoning+over+knowledge+graphs%2E+arXiv+preprint+arXiv%3A2512%2E09369%2E)
51. Yong Liu, Xingjian Su, Shiyu Wang, Haoran Zhang, Haixuan Liu, Yuxuan Wang, Zhou Ye, Yang Xiang, Jianmin Wang, and Mingsheng Long. 2026. Timers1: A billion-scale time series foundation model with serial scaling. arXiv preprint arXiv:2603.04791. — [arXiv:2603.04791](https://arxiv.org/abs/2603.04791) [find](https://scholar.google.com/scholar?q=Yong+Liu%2C+Xingjian+Su%2C+Shiyu+Wang%2C+Haoran+Zhang%2C+Haixuan+Liu%2C+Yuxuan+Wang%2C+Zhou+Ye%2C+Yang+Xiang%2C+Jianmin+Wang%2C+and+Mingsheng+Long%2E+2026%2E+Timers1%3A+A+billion%2Dscale+time+series+foundation+model+with+seria)
52. Zewen Liu, Juntong Ni, Max SY Lau, and Wei Jin. 2025d. Cape: Covariate-adjusted pre-training for epidemic time series forecasting. arXiv preprint arXiv:2502.03393. — [arXiv:2502.03393](https://arxiv.org/abs/2502.03393) [find](https://scholar.google.com/scholar?q=Zewen+Liu%2C+Juntong+Ni%2C+Max+SY+Lau%2C+and+Wei+Jin%2E+2025d%2E+Cape%3A+Covariate%2Dadjusted+pre%2Dtraining+for+epidemic+time+series+forecasting%2E+arXiv+preprint+arXiv%3A2502%2E03393%2E+%E2%80%94+%5BarXiv%3A2502%2E03393%5D%28https%3A%2F%2Farxiv%2Eo)
53. Zewen Liu, Juntong Ni, Xianfeng Tang, Max SY Lau, Wenpeng Yin, and Wei Jin. 2025e. Can large language models adequately perform symbolic reasoning over time series? arXiv preprint arXiv:2508.03963. [find](https://scholar.google.com/scholar?q=Zewen+Liu%2C+Juntong+Ni%2C+Xianfeng+Tang%2C+Max+SY+Lau%2C+Wenpeng+Yin%2C+and+Wei+Jin%2E+2025e%2E+Can+large+language+models+adequately+perform+symbolic+reasoning+over+time+series%3F+arXiv+preprint+arXiv%3A2508%2E03963%2E)
54. Zewen Liu, Guancheng Wan, B Aditya Prakash, Max SY Lau, and Wei Jin. 2024d. A review of graph neural networks in epidemic modeling. In Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining, pages 6577–6587. [find](https://scholar.google.com/scholar?q=Zewen+Liu%2C+Guancheng+Wan%2C+B+Aditya+Prakash%2C+Max+SY+Lau%2C+and+Wei+Jin%2E+2024d%2E+A+review+of+graph+neural+networks+in+epidemic+modeling%2E+In+Proceedings+of+the+30th+ACM+SIGKDD+conference+on+knowledge+discov)
55. Zewen Liu, Xiaoda Wang, Bohan Wang, Zijie Huang, Carl Yang, and Wei Jin. 2025f. Graph odes and beyond: A comprehensive survey on integrating differential equations with graph neural networks. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, pages 6118–612… [find](https://scholar.google.com/scholar?q=Zewen+Liu%2C+Xiaoda+Wang%2C+Bohan+Wang%2C+Zijie+Huang%2C+Carl+Yang%2C+and+Wei+Jin%2E+2025f%2E+Graph+odes+and+beyond%3A+A+comprehensive+survey+on+integrating+differential+equations+with+graph+neural+networks%2E+In+Proce)
56. Zijia Liu, Peixuan Han, Haofei Yu, Haoru Li, and Jiaxuan You. 2025g. Time-r1: Towards comprehensive temporal reasoning in llms. arXiv preprint arXiv:2505.13508. [find](https://scholar.google.com/scholar?q=Zijia+Liu%2C+Peixuan+Han%2C+Haofei+Yu%2C+Haoru+Li%2C+and+Jiaxuan+You%2E+2025g%2E+Time%2Dr1%3A+Towards+comprehensive+temporal+reasoning+in+llms%2E+arXiv+preprint+arXiv%3A2505%2E13508%2E)
57. Yucong Luo, Yitong Zhou, Mingyue Cheng, Jiahao Wang, Daoyu Wang, Tingyue Pan, and Jintao Zhang. 2025. Time series forecasting as reasoning: A slow-thinking approach with reinforced llms. arXiv preprint arXiv:2506.10630. [find](https://scholar.google.com/scholar?q=Yucong+Luo%2C+Yitong+Zhou%2C+Mingyue+Cheng%2C+Jiahao+Wang%2C+Daoyu+Wang%2C+Tingyue+Pan%2C+and+Jintao+Zhang%2E+2025%2E+Time+series+forecasting+as+reasoning%3A+A+slow%2Dthinking+approach+with+reinforced+llms%2E+arXiv+preprin)
58. Mike A Merrill, Mingtian Tan, Vinayak Gupta, Thomas Hartvigsen, and Tim Althoff. 2024. Language models still struggle to zero-shot reason about time series. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3512–3533. [find](https://scholar.google.com/scholar?q=Mike+A+Merrill%2C+Mingtian+Tan%2C+Vinayak+Gupta%2C+Thomas+Hartvigsen%2C+and+Tim+Althoff%2E+2024%2E+Language+models+still+struggle+to+zero%2Dshot+reason+about+time+series%2E+In+Findings+of+the+Association+for+Computat)
59. Juntong Ni, Zewen Liu, Shiyu Wang, Ming Jin, and Wei Jin. 2025a. Timedistill: Efficient long-term time series forecasting with mlp via cross-architecture distillation. arXiv preprint arXiv:2502.15016. — [arXiv:2502.15016](https://arxiv.org/abs/2502.15016) [find](https://scholar.google.com/scholar?q=Juntong+Ni%2C+Zewen+Liu%2C+Shiyu+Wang%2C+Ming+Jin%2C+and+Wei+Jin%2E+2025a%2E+Timedistill%3A+Efficient+long%2Dterm+time+series+forecasting+with+mlp+via+cross%2Darchitecture+distillation%2E+arXiv+preprint+arXiv%3A2502%2E15016%2E)
60. Juntong Ni, Shiyu Wang, Zewen Liu, Xiaoming Shi, Xinyue Zhong, Zhou Ye, and Wei Jin. 2025b. U-cast: Learning hierarchical structures for high-dimensional time series forecasting. arXiv preprint arXiv:2507.15119. — [arXiv:2507.15119](https://arxiv.org/abs/2507.15119) [find](https://scholar.google.com/scholar?q=Juntong+Ni%2C+Shiyu+Wang%2C+Zewen+Liu%2C+Xiaoming+Shi%2C+Xinyue+Zhong%2C+Zhou+Ye%2C+and+Wei+Jin%2E+2025b%2E+U%2Dcast%3A+Learning+hierarchical+structures+for+high%2Ddimensional+time+series+forecasting%2E+arXiv+preprint+arXiv%3A)
61. Y Nie. 2022. [A time series is worth 64words: Long-term forecasting with transformers](https://md.research.elamur.ai/free/en/papers/nie-2022-time-series-worth-64-words/). arXiv preprint arXiv:2211.14730.
62. Kanghui Ning, Zijie Pan, Yushan Jiang, Anderson Schneider, Yuriy Nevmyvaka, and Dongjin Song. 2025. Towards interpretable and trustworthy time series reasoning: A bluesky vision. arXiv preprint arXiv:2510.16980. — [arXiv:2510.16980](https://arxiv.org/abs/2510.16980) [find](https://scholar.google.com/scholar?q=Kanghui+Ning%2C+Zijie+Pan%2C+Yushan+Jiang%2C+Anderson+Schneider%2C+Yuriy+Nevmyvaka%2C+and+Dongjin+Song%2E+2025%2E+Towards+interpretable+and+trustworthy+time+series+reasoning%3A+A+bluesky+vision%2E+arXiv+preprint+arXiv%3A)
63. Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, Richard Yi Da Xu, Guo Li, Xian Yang, and 1 others. 2025. Promedts: A self-supervised, prompt-guided multimodal approach for integrating medical text and time series. In Findings of the Association for Computational Linguistics: ACL 2025, page… [find](https://scholar.google.com/scholar?q=Shuai+Niu%2C+Jing+Ma%2C+Hongzhan+Lin%2C+Liang+Bai%2C+Zhihua+Wang%2C+Richard+Yi+Da+Xu%2C+Guo+Li%2C+Xian+Yang%2C+and+1+others%2E+2025%2E+Promedts%3A+A+self%2Dsupervised%2C+prompt%2Dguided+multimodal+approach+for+integrating+medica)
64. OpenAI. 2025. Gpt-5 system card. Technical report. Technical report. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Gpt%2D5+system+card%2E+Technical+report%2E+Technical+report%2E)
65. Mathaios Panteli and Pierluigi Mancarella. 2015. Influence of extreme weather and climate change on the resilience of power systems: Impacts and possible mitigation strategies. Electric Power Systems Research, 127:259–270. [find](https://scholar.google.com/scholar?q=Mathaios+Panteli+and+Pierluigi+Mancarella%2E+2015%2E+Influence+of+extreme+weather+and+climate+change+on+the+resilience+of+power+systems%3A+Impacts+and+possible+mitigation+strategies%2E+Electric+Power+Systems+)
66. Chris Paola, Efi Foufoula-Georgiou, William E Dietrich, Miki Hondzo, David Mohrig, Gary Parker, Mary E Power, Ignacio Rodriguez-Iturbe, Vaughan Voller, and Peter Wilcock. 2006. Toward a unified science of the earth’s surface: Opportunities for synthesis among hydrology, geomorphology, geochemistry,… [find](https://scholar.google.com/scholar?q=Chris+Paola%2C+Efi+Foufoula%2DGeorgiou%2C+William+E+Dietrich%2C+Miki+Hondzo%2C+David+Mohrig%2C+Gary+Parker%2C+Mary+E+Power%2C+Ignacio+Rodriguez%2DIturbe%2C+Vaughan+Voller%2C+and+Peter+Wilcock%2E+2006%2E+Toward+a+unified+scienc)
67. Pengrui Quan, Brian Wang, Kang Yang, Liying Han, and Mani Srivastava. 2025. Benchmarking spatiotemporal reasoning in llms and reasoning models: Capabilities and challenges. arXiv preprint arXiv:2505.11618. — [arXiv:2505.11618](https://arxiv.org/abs/2505.11618) [find](https://scholar.google.com/scholar?q=Pengrui+Quan%2C+Brian+Wang%2C+Kang+Yang%2C+Liying+Han%2C+and+Mani+Srivastava%2E+2025%2E+Benchmarking+spatiotemporal+reasoning+in+llms+and+reasoning+models%3A+Capabilities+and+challenges%2E+arXiv+preprint+arXiv%3A2505%2E1)
68. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, and 1 others. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300.
69. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2025. [Hybridflow: A flexible and efficient rlhf framework](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). In Proceedings of the Twentieth European Conference on Computer Systems, pages 1279–1297.
70. Xiaoming Shi, Shiyu Wang, Yuqi Nie, Dianqi Li, Zhou Ye, Qingsong Wen, and Ming Jin. 2024. Time-moe: Billion-scale time series foundation models with mixture of experts. arXiv preprint arXiv:2409.16040. — [arXiv:2409.16040](https://arxiv.org/abs/2409.16040) [find](https://scholar.google.com/scholar?q=Xiaoming+Shi%2C+Shiyu+Wang%2C+Yuqi+Nie%2C+Dianqi+Li%2C+Zhou+Ye%2C+Qingsong+Wen%2C+and+Ming+Jin%2E+2024%2E+Time%2Dmoe%3A+Billion%2Dscale+time+series+foundation+models+with+mixture+of+experts%2E+arXiv+preprint+arXiv%3A2409%2E16040)
71. Gideon Stein, Maha Shadaydeh, Jan Blunk, Niklas Penzel, and Joachim Denzler. 2025. Causalrivers– scaling up benchmarking of causal discovery for real-world time-series. arXiv preprint arXiv:2503.17452. — [arXiv:2503.17452](https://arxiv.org/abs/2503.17452) [find](https://scholar.google.com/scholar?q=Gideon+Stein%2C+Maha+Shadaydeh%2C+Jan+Blunk%2C+Niklas+Penzel%2C+and+Joachim+Denzler%2E+2025%2E+Causalrivers%E2%80%93+scaling+up+benchmarking+of+causal+discovery+for+real%2Dworld+time%2Dseries%2E+arXiv+preprint+arXiv%3A2503%2E17452)
72. Mingtian Tan, Mike A Merrill, Zack Gottesman, Tim Althoff, David Evans, and Tom Hartvigsen. 2025. [Inferring events from time series using language models](https://md.research.elamur.ai/free/en/papers/tan-2026-inferring-events-time-series-language/). arXiv preprint arXiv:2503.14190.
73. Jonathan Tremblay, Aayush Prakash, David Acuna, Mark Brophy, Varun Jampani, Cem Anil, Thang To, Eric Cameracci, Shaad Boochoon, and Stan Birchfield. 2018. Training deep networks with synthetic data: Bridging the reality gap by domain randomization. In Proceedings of the IEEE conference on computer v… [find](https://scholar.google.com/scholar?q=Jonathan+Tremblay%2C+Aayush+Prakash%2C+David+Acuna%2C+Mark+Brophy%2C+Varun+Jampani%2C+Cem+Anil%2C+Thang+To%2C+Eric+Cameracci%2C+Shaad+Boochoon%2C+and+Stan+Birchfield%2E+2018%2E+Training+deep+networks+with+synthetic+data%3A+B)
74. Chengsen Wang, Qi Qi, Jingyu Wang, Haifeng Sun, Zirui Zhuang, Jinming Wu, Lei Zhang, and Jianxin Liao. 2025a. Chattime: A unified multimodal time series foundation model bridging numerical and textual data. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 12694– 127… [find](https://scholar.google.com/scholar?q=Chengsen+Wang%2C+Qi+Qi%2C+Jingyu+Wang%2C+Haifeng+Sun%2C+Zirui+Zhuang%2C+Jinming+Wu%2C+Lei+Zhang%2C+and+Jianxin+Liao%2E+2025a%2E+Chattime%3A+A+unified+multimodal+time+series+foundation+model+bridging+numerical+and+textual)
75. Jiahao Wang, Mingyue Cheng, and Qi Liu. 2025b. Can slow-thinking llms reason over time? empirical studies in time series forecasting. arXiv preprint arXiv:2505.24511. — [arXiv:2505.24511](https://arxiv.org/abs/2505.24511) [find](https://scholar.google.com/scholar?q=Jiahao+Wang%2C+Mingyue+Cheng%2C+and+Qi+Liu%2E+2025b%2E+Can+slow%2Dthinking+llms+reason+over+time%3F+empirical+studies+in+time+series+forecasting%2E+arXiv+preprint+arXiv%3A2505%2E24511%2E+%E2%80%94+%5BarXiv%3A2505%2E24511%5D%28https%3A%2F%2Farxi)
76. Liang Wang, Ivano Lauriola, and Alessandro Moschitti. 2023a. Accurate training of web-based question answering systems with feedback from ranked users. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 660–667. [find](https://scholar.google.com/scholar?q=Liang+Wang%2C+Ivano+Lauriola%2C+and+Alessandro+Moschitti%2E+2023a%2E+Accurate+training+of+web%2Dbased+question+answering+systems+with+feedback+from+ranked+users%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the)
77. Senzhang Wang, Jiannong Cao, and S Yu Philip. 2020. Deep learning for spatio-temporal data mining: A survey. IEEE transactions on knowledge and data engineering, 34(8):3681–3700. [find](https://scholar.google.com/scholar?q=Senzhang+Wang%2C+Jiannong+Cao%2C+and+S+Yu+Philip%2E+2020%2E+Deep+learning+for+spatio%2Dtemporal+data+mining%3A+A+survey%2E+IEEE+transactions+on+knowledge+and+data+engineering%2C+34%288%29%3A3681%E2%80%933700%2E)
78. Shiyu Wang. 2024. Neuralreconciler for hierarchical time series forecasting. In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pages 731–739. [find](https://scholar.google.com/scholar?q=Shiyu+Wang%2E+2024%2E+Neuralreconciler+for+hierarchical+time+series+forecasting%2E+In+Proceedings+of+the+17th+ACM+International+Conference+on+Web+Search+and+Data+Mining%2C+pages+731%E2%80%93739%2E)
79. Shiyu Wang, Zhixuan Chu, Yinbo Sun, Yu Liu, Yuliang Guo, Yang Chen, Huiyang Jian, Lintao Ma, Xingyu Lu, and Jun Zhou. 2024a. Multiscale representation enhanced temporal flow fusion model for long-term workload forecasting. In Proceedings of the 33rd ACM International Conference on Information and Kn… [find](https://scholar.google.com/scholar?q=Shiyu+Wang%2C+Zhixuan+Chu%2C+Yinbo+Sun%2C+Yu+Liu%2C+Yuliang+Guo%2C+Yang+Chen%2C+Huiyang+Jian%2C+Lintao+Ma%2C+Xingyu+Lu%2C+and+Jun+Zhou%2E+2024a%2E+Multiscale+representation+enhanced+temporal+flow+fusion+model+for+long%2Dterm)
80. Shiyu Wang, Jiawei Li, Xiaoming Shi, Zhou Ye, Baichuan Mo, Wenze Lin, Shengtong Ju, Zhixuan Chu, and Ming Jin. 2024b. Timemixer++: A general time series pattern machine for universal predictive analysis. arXiv preprint arXiv:2410.16032. — [arXiv:2410.16032](https://arxiv.org/abs/2410.16032) [find](https://scholar.google.com/scholar?q=Shiyu+Wang%2C+Jiawei+Li%2C+Xiaoming+Shi%2C+Zhou+Ye%2C+Baichuan+Mo%2C+Wenze+Lin%2C+Shengtong+Ju%2C+Zhixuan+Chu%2C+and+Ming+Jin%2E+2024b%2E+Timemixer%2B%2B%3A+A+general+time+series+pattern+machine+for+universal+predictive+analys)
81. Shiyu Wang, Wei Lu, Jiawei Li, Xiaoming Shi, Xinyue Zhong, Zhou Ye, Ming Jin, and Qingsong Wen. 2025c. Frt: Flow-based reconcile transformer for hierarchical time series. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, pages 4995–5006. [find](https://scholar.google.com/scholar?q=Shiyu+Wang%2C+Wei+Lu%2C+Jiawei+Li%2C+Xiaoming+Shi%2C+Xinyue+Zhong%2C+Zhou+Ye%2C+Ming+Jin%2C+and+Qingsong+Wen%2E+2025c%2E+Frt%3A+Flow%2Dbased+reconcile+transformer+for+hierarchical+time+series%2E+In+Proceedings+of+the+31st+AC)
82. Shiyu Wang, Yinbo Sun, Xiaoming Shi, Shiyi Zhu, Lin-Tao Ma, James Zhang, Yifei Zheng, and Jian Liu. 2023b. Full scaling automation for sustainable development of green data centers. arXiv preprint arXiv:2305.00706. — [arXiv:2305.00706](https://arxiv.org/abs/2305.00706) [find](https://scholar.google.com/scholar?q=Shiyu+Wang%2C+Yinbo+Sun%2C+Xiaoming+Shi%2C+Shiyi+Zhu%2C+Lin%2DTao+Ma%2C+James+Zhang%2C+Yifei+Zheng%2C+and+Jian+Liu%2E+2023b%2E+Full+scaling+automation+for+sustainable+development+of+green+data+centers%2E+arXiv+preprint+arX)
83. Shiyu Wang, Yinbo Sun, Yan Wang, Fan Zhou, Lin-Tao Ma, James Zhang, and YangFei Zheng. 2023c. Flow-based end-to-end model for hierarchical time series forecasting via trainable attentive-reconciliation. In International Conference on Database Systems for Advanced Applications, pages 167–176. Springe… [find](https://scholar.google.com/scholar?q=Shiyu+Wang%2C+Yinbo+Sun%2C+Yan+Wang%2C+Fan+Zhou%2C+Lin%2DTao+Ma%2C+James+Zhang%2C+and+YangFei+Zheng%2E+2023c%2E+Flow%2Dbased+end%2Dto%2Dend+model+for+hierarchical+time+series+forecasting+via+trainable+attentive%2Dreconciliatio)
84. Shiyu Wang, Haixu Wu, Xiaoming Shi, Tengge Hu, Huakun Luo, Lintao Ma, James Y Zhang, and JUN ZHOU. 2024c. Timemixer: Decomposable multi-scale mixing for time series forecasting. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Shiyu+Wang%2C+Haixu+Wu%2C+Xiaoming+Shi%2C+Tengge+Hu%2C+Huakun+Luo%2C+Lintao+Ma%2C+James+Y+Zhang%2C+and+JUN+ZHOU%2E+2024c%2E+Timemixer%3A+Decomposable+multi%2Dscale+mixing+for+time+series+forecasting%2E+In+International+Confe)
85. Shiyu Wang, Fan Zhou, Yinbo Sun, Lintao Ma, James Zhang, and Yangfei Zheng. 2022. End-to-end modeling of hierarchical time series using autoregressive transformer and conditional normalizing flow-based reconciliation. In 2022 IEEE International Conference on Data Mining Workshops (ICDMW), pages 1087… [find](https://scholar.google.com/scholar?q=Shiyu+Wang%2C+Fan+Zhou%2C+Yinbo+Sun%2C+Lintao+Ma%2C+James+Zhang%2C+and+Yangfei+Zheng%2E+2022%2E+End%2Dto%2Dend+modeling+of+hierarchical+time+series+using+autoregressive+transformer+and+conditional+normalizing+flow%2Dbase)
86. Xiaoda Wang, Ching Chang, Defu Cao, Kaiqiao Han, Fang Sun, Yue Huang, Minxiao Wang, Chang Xu, Xiao Luo, Runze Yan, and 1 others. 2026. Position: Beyond prediction: Toward verifiable physiological waveform reasoning with foundation models and agentic llms. Authorea Preprints. [find](https://scholar.google.com/scholar?q=Xiaoda+Wang%2C+Ching+Chang%2C+Defu+Cao%2C+Kaiqiao+Han%2C+Fang+Sun%2C+Yue+Huang%2C+Minxiao+Wang%2C+Chang+Xu%2C+Xiao+Luo%2C+Runze+Yan%2C+and+1+others%2E+2026%2E+Position%3A+Beyond+prediction%3A+Toward+verifiable+physiological+wave)
87. Ye Wang, Ziheng Wang, Boshen Xu, Yang Du, Kejun Lin, Zihan Xiao, Zihao Yue, Jianzhong Ju, Liang Zhang, Dingyi Yang, and 1 others. 2025d. Time-r1: Post-training large vision language model for temporal video grounding. arXiv preprint arXiv:2503.13377. — [arXiv:2503.13377](https://arxiv.org/abs/2503.13377) [find](https://scholar.google.com/scholar?q=Ye+Wang%2C+Ziheng+Wang%2C+Boshen+Xu%2C+Yang+Du%2C+Kejun+Lin%2C+Zihan+Xiao%2C+Zihao+Yue%2C+Jianzhong+Ju%2C+Liang+Zhang%2C+Dingyi+Yang%2C+and+1+others%2E+2025d%2E+Time%2Dr1%3A+Post%2Dtraining+large+vision+language+model+for+temporal)
88. Yilin Wang, Peixuan Lei, Jie Song, Yuzhe Hao, Tao Chen, Yuxuan Zhang, Lei Jia, Yuanxiang Li, and Zhongyu Wei. 2025e. Itformer: Bridging time series and natural language for multi-modal qa with large-scale multitask dataset. arXiv preprint arXiv:2506.20093. — [arXiv:2506.20093](https://arxiv.org/abs/2506.20093) [find](https://scholar.google.com/scholar?q=Yilin+Wang%2C+Peixuan+Lei%2C+Jie+Song%2C+Yuzhe+Hao%2C+Tao+Chen%2C+Yuxuan+Zhang%2C+Lei+Jia%2C+Yuanxiang+Li%2C+and+Zhongyu+Wei%2E+2025e%2E+Itformer%3A+Bridging+time+series+and+natural+language+for+multi%2Dmodal+qa+with+large%2Ds)
89. Yuxuan Wang, Haixu Wu, Yuezhou Ma, Yuchen Fang, Ziyi Zhang, Yong Liu, Shiyu Wang, Zhou Ye, Yang Xiang, Jianmin Wang, and 1 others. 2025f. Accuracy law for the future of deep time series forecasting. arXiv preprint arXiv:2510.02729. — [arXiv:2510.02729](https://arxiv.org/abs/2510.02729) [find](https://scholar.google.com/scholar?q=Yuxuan+Wang%2C+Haixu+Wu%2C+Yuezhou+Ma%2C+Yuchen+Fang%2C+Ziyi+Zhang%2C+Yong+Liu%2C+Shiyu+Wang%2C+Zhou+Ye%2C+Yang+Xiang%2C+Jianmin+Wang%2C+and+1+others%2E+2025f%2E+Accuracy+law+for+the+future+of+deep+time+series+forecasting%2E+a)
90. Zihan Wang, Kangrui Wang, Qineng Wang, Pingyue Zhang, Linjie Li, Zhengyuan Yang, Xing Jin, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, and 1 others. 2025g. [Ragen: Understanding self-evolution in llm agents via multi-turn reinforcement learning](https://md.research.elamur.ai/free/en/papers/wang-2025-ragen-understanding-self-evolution-llm/). arXiv preprint arXiv:2504.20073.
91. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824– 24837.
92. Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, and Chengqi Zhang. 2019. Graph wavenet for deep spatial-temporal graph modeling. arXiv preprint arXiv:1906.00121. [find](https://scholar.google.com/scholar?q=Zonghan+Wu%2C+Shirui+Pan%2C+Guodong+Long%2C+Jing+Jiang%2C+and+Chengqi+Zhang%2E+2019%2E+Graph+wavenet+for+deep+spatial%2Dtemporal+graph+modeling%2E+arXiv+preprint+arXiv%3A1906%2E00121%2E)
93. Tian Xie, Zitian Gao, Qingnan Ren, Haoming Luo, Yuqian Hong, Bryan Dai, Joey Zhou, Kai Qiu, Zhirong Wu, and Chong Luo. 2025. [Logic-rl: Unleashing llm reasoning with rule-based reinforcement learning](https://md.research.elamur.ai/free/en/papers/xie-2025-logic-rl-unleashing-llm/). arXiv preprint arXiv:2502.14768.
94. Zhe Xie, Zeyan Li, Xiao He, Longlong Xu, Xidao Wen, Tieying Zhang, Jianjun Chen, Rui Shi, and Dan Pei. 2024. Chatts: Aligning time series with llms via synthetic data for enhanced understanding and reasoning. arXiv preprint arXiv:2412.03104. — [arXiv:2412.03104](https://arxiv.org/abs/2412.03104) [find](https://scholar.google.com/scholar?q=Zhe+Xie%2C+Zeyan+Li%2C+Xiao+He%2C+Longlong+Xu%2C+Xidao+Wen%2C+Tieying+Zhang%2C+Jianjun+Chen%2C+Rui+Shi%2C+and+Dan+Pei%2E+2024%2E+Chatts%3A+Aligning+time+series+with+llms+via+synthetic+data+for+enhanced+understanding+and+re)
95. Gelei Xu, Xueyang Li, Yixiong Chen, Yuying Duan, Shuqing Wu, Alexander Yu, Ching-Hao Chiu, Juntong Ni, Ningzhi Tang, Toby Jia-Jun Li, and 1 others. 2025. A comprehensive survey of agentic ai in healthcare. Authorea Preprints. [find](https://scholar.google.com/scholar?q=Gelei+Xu%2C+Xueyang+Li%2C+Yixiong+Chen%2C+Yuying+Duan%2C+Shuqing+Wu%2C+Alexander+Yu%2C+Ching%2DHao+Chiu%2C+Juntong+Ni%2C+Ningzhi+Tang%2C+Toby+Jia%2DJun+Li%2C+and+1+others%2E+2025%2E+A+comprehensive+survey+of+agentic+ai+in+health)
96. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025a. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
97. Ning Yang, Hengyu Zhong, Haijun Zhang, and Randall Berry. 2025b. Vision-llms for spatiotemporal traffic forecasting. arXiv preprint arXiv:2510.11282. — [arXiv:2510.11282](https://arxiv.org/abs/2510.11282) [find](https://scholar.google.com/scholar?q=Ning+Yang%2C+Hengyu+Zhong%2C+Haijun+Zhang%2C+and+Randall+Berry%2E+2025b%2E+Vision%2Dllms+for+spatiotemporal+traffic+forecasting%2E+arXiv+preprint+arXiv%3A2510%2E11282%2E+%E2%80%94+%5BarXiv%3A2510%2E11282%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2510%2E11)
98. Yiyuan Yang, Zichuan Liu, Lei Song, Kai Ying, Zhiguang Wang, Tom Bamford, Svitlana Vyetrenko, Jiang Bian, and Qingsong Wen. 2025c. Time-ra: Towards time series reasoning for anomaly with llm feedback. arXiv preprint arXiv:2507.15066. — [arXiv:2507.15066](https://arxiv.org/abs/2507.15066) [find](https://scholar.google.com/scholar?q=Yiyuan+Yang%2C+Zichuan+Liu%2C+Lei+Song%2C+Kai+Ying%2C+Zhiguang+Wang%2C+Tom+Bamford%2C+Svitlana+Vyetrenko%2C+Jiang+Bian%2C+and+Qingsong+Wen%2E+2025c%2E+Time%2Dra%3A+Towards+time+series+reasoning+for+anomaly+with+llm+feedback%2E)
99. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, 36:11809–11822. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+Advances+in+neural+inf)
100. Bing Yu, Haoteng Yin, and Zhanxing Zhu. 2017. Spatiotemporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875. — [arXiv:1709.04875](https://arxiv.org/abs/1709.04875) [find](https://scholar.google.com/scholar?q=Bing+Yu%2C+Haoteng+Yin%2C+and+Zhanxing+Zhu%2E+2017%2E+Spatiotemporal+graph+convolutional+networks%3A+A+deep+learning+framework+for+traffic+forecasting%2E+arXiv+preprint+arXiv%3A1709%2E04875%2E+%E2%80%94+%5BarXiv%3A1709%2E04875%5D%28http)
101. Yuan Yuan, Jingtao Ding, Jie Feng, Depeng Jin, and Yong Li. 2024. Unist: A prompt-empowered universal model for urban spatio-temporal prediction. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 4095–4106. [find](https://scholar.google.com/scholar?q=Yuan+Yuan%2C+Jingtao+Ding%2C+Jie+Feng%2C+Depeng+Jin%2C+and+Yong+Li%2E+2024%2E+Unist%3A+A+prompt%2Dempowered+universal+model+for+urban+spatio%2Dtemporal+prediction%2E+In+Proceedings+of+the+30th+ACM+SIGKDD+Conference+on+Kn)
102. Haochuan Zhang, Chunhua Yang, Jie Han, Liyang Qin, and Xiaoli Wang. 2025a. Tempogpt: Enhancing time series reasoning via quantizing embedding. arXiv preprint arXiv:2501.07335. — [arXiv:2501.07335](https://arxiv.org/abs/2501.07335) [find](https://scholar.google.com/scholar?q=Haochuan+Zhang%2C+Chunhua+Yang%2C+Jie+Han%2C+Liyang+Qin%2C+and+Xiaoli+Wang%2E+2025a%2E+Tempogpt%3A+Enhancing+time+series+reasoning+via+quantizing+embedding%2E+arXiv+preprint+arXiv%3A2501%2E07335%2E+%E2%80%94+%5BarXiv%3A2501%2E07335%5D%28htt)
103. Junru Zhang, Lang Feng, Xu Guo, Yuhan Wu, Yabo Dong, and Duanqing Xu. 2025b. Timemas-ter: Training time-series multimodal llms to reason via reinforcement learning. arXiv preprint arXiv:2506.13705. — [arXiv:2506.13705](https://arxiv.org/abs/2506.13705) [find](https://scholar.google.com/scholar?q=Junru+Zhang%2C+Lang+Feng%2C+Xu+Guo%2C+Yuhan+Wu%2C+Yabo+Dong%2C+and+Duanqing+Xu%2E+2025b%2E+Timemas%2Dter%3A+Training+time%2Dseries+multimodal+llms+to+reason+via+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2506%2E13705%2E+%E2%80%94+)
104. Juyuan Zhang, Jiechao Gao, Wenwen Ouyang, Wei Zhu, and Hui Yi Leong. 2025c. Time-llama: Adapting large language models for time series modeling via dynamic low-rank adaptation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Work… [find](https://scholar.google.com/scholar?q=Juyuan+Zhang%2C+Jiechao+Gao%2C+Wenwen+Ouyang%2C+Wei+Zhu%2C+and+Hui+Yi+Leong%2E+2025c%2E+Time%2Dllama%3A+Adapting+large+language+models+for+time+series+modeling+via+dynamic+low%2Drank+adaptation%2E+In+Proceedings+of+the+6)
105. Qianru Zhang, Haixin Wang, Cheng Long, Liangcai Su, Xingwei He, Jianlong Chang, Tailin Wu, Hongzhi Yin, Siu-Ming Yiu, Qi Tian, and 1 others. 2024. A survey of generative techniques for spatial-temporal data mining. arXiv preprint arXiv:2405.09592. — [arXiv:2405.09592](https://arxiv.org/abs/2405.09592) [find](https://scholar.google.com/scholar?q=Qianru+Zhang%2C+Haixin+Wang%2C+Cheng+Long%2C+Liangcai+Su%2C+Xingwei+He%2C+Jianlong+Chang%2C+Tailin+Wu%2C+Hongzhi+Yin%2C+Siu%2DMing+Yiu%2C+Qi+Tian%2C+and+1+others%2E+2024%2E+A+survey+of+generative+techniques+for+spatial%2Dtempora)
106. Weichen Zhang, Zile Zhou, Zhiheng Zheng, Chen Gao, Jinqiang Cui, Yong Li, Xinlei Chen, and Xiao-Ping Zhang. 2025d. Open3dvqa: A benchmark for comprehensive spatial reasoning with multimodal large language model in open space. arXiv preprint arXiv:2503.11094. — [arXiv:2503.11094](https://arxiv.org/abs/2503.11094) [find](https://scholar.google.com/scholar?q=Weichen+Zhang%2C+Zile+Zhou%2C+Zhiheng+Zheng%2C+Chen+Gao%2C+Jinqiang+Cui%2C+Yong+Li%2C+Xinlei+Chen%2C+and+Xiao%2DPing+Zhang%2E+2025d%2E+Open3dvqa%3A+A+benchmark+for+comprehensive+spatial+reasoning+with+multimodal+large+lang)
107. Yaowei Zheng, Junting Lu, Shenzhi Wang, Zhangchi Feng, Dongdong Kuang, and Yuwen Xiong. 2025. Easyr1: An efficient, scalable, multi-modality rl training framework. [find](https://scholar.google.com/scholar?q=Yaowei+Zheng%2C+Junting+Lu%2C+Shenzhi+Wang%2C+Zhangchi+Feng%2C+Dongdong+Kuang%2C+and+Yuwen+Xiong%2E+2025%2E+Easyr1%3A+An+efficient%2C+scalable%2C+multi%2Dmodality+rl+training+framework%2E)
108. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024. [Llamafactory: Unified efficient fine-tuning of 100+ language models](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/). arXiv preprint arXiv:2403.13372.
109. Luca Zhou, Pratham Yashwante, Marshall Fisher, Alessio Sampieri, Zihao Zhou, Fabio Galasso, and Rose Yu. 2025. Cats-bench: Can language models describe numeric time series? arXiv preprint arXiv:2509.20823. — [arXiv:2509.20823](https://arxiv.org/abs/2509.20823) [find](https://scholar.google.com/scholar?q=Luca+Zhou%2C+Pratham+Yashwante%2C+Marshall+Fisher%2C+Alessio+Sampieri%2C+Zihao+Zhou%2C+Fabio+Galasso%2C+and+Rose+Yu%2E+2025%2E+Cats%2Dbench%3A+Can+language+models+describe+numeric+time+series%3F+arXiv+preprint+arXiv%3A2509%2E2)

*Updated 2 November 2026*