% ====================================================================== % references.bib % Time Series Forecasting: From VAR to Transformers and Diffusion % All works referenced in the slides, outline, and literature review. % ====================================================================== @inproceedings{wen2023transformers, author = {Wen, Qingsong and Zhou, Tian and Zhang, Chaoli and Chen, Weiqi and Ma, Ziqing and Yan, Junchi and Sun, Liang}, title = {Transformers in Time Series: A Survey}, booktitle = {Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI)}, year = {2023}, pages = {6778--6786} } @article{diebold1995comparing, author = {Diebold, Francis X. and Mariano, Roberto S.}, title = {Comparing Predictive Accuracy}, journal = {Journal of Business \& Economic Statistics}, year = {1995}, volume = {13}, number = {3}, pages = {253--263} } @inproceedings{liu2022nonstationary, title={Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting}, author={Liu, Yong and Wu, Haixu and Wang, Jianmin and Long, Mingsheng}, booktitle={Advances in Neural Information Processing Systems}, year={2022} } @article{ansari2024chronos2, author={Ansari, Abdul Fatir and Shchur, Oleksandr and K{\"u}ken, Jaris and Auer, Andreas and Han, Boran and Mercado, Pedro and Rangapuram, Syama Sundar and Shen, Huibin and Stella, Lorenzo and Zhang, Xiyuan and others}, title = {Chronos-2: From Univariate to Universal Forecasting}, journal = {arXiv preprint arXiv:2510.15821}, year = {2025} } @article{li2024automatic, author = {Li, Jie and Fearnhead, Paul and Fryzlewicz, Piotr and Wang, Tengyao}, title = {Automatic Change-Point Detection in Time Series via Deep Learning}, journal = {Journal of the Royal Statistical Society Series B: Statistical Methodology}, year = {2024}, volume = {86}, number = {2}, pages = {273--285} } % ---------- Classical multivariate time series ---------- @article{sims1980macroeconomics, author = {Sims, Christopher A.}, title = {Macroeconomics and Reality}, journal = {Econometrica}, year = {1980}, volume = {48}, number = {1}, pages = {1--48} } @article{granger1969investigating, author = {Granger, C. W. J.}, title = {Investigating Causal Relations by Econometric Models and Cross-spectral Methods}, journal = {Econometrica}, year = {1969}, volume = {37}, number = {3}, pages = {424--438} } @inproceedings{xie2022icl, author = {Xie, Sang Michael and Raghunathan, Aditi and Liang, Percy and Ma, Tengyu}, title = {An Explanation of In-Context Learning as Implicit {B}ayesian Inference}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2022} } @inproceedings{sohldickstein2015, title = {Deep Unsupervised Learning using Nonequilibrium Thermodynamics}, author = {Sohl-Dickstein, Jascha and Weiss, Eric A. and Maheswaranathan, Niru and Ganguli, Surya}, booktitle = {Proceedings of the 32nd International Conference on Machine Learning (ICML)}, series = {PMLR}, volume = {37}, pages = {2256--2265}, year = {2015} } @article{yan2021scoregrad, author = {Yan, Tijin and Zhang, Hongwei and Zhou, Tong and Zhan, Yufeng and Xia, Yuanqing}, title = {{ScoreGrad}: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models}, journal = {arXiv preprint arXiv:2106.10121}, year = {2021} } @inproceedings{li2022d3vae, author = {Li, Yan and Lu, Xinjiang and Wang, Yaqing and Dou, Dejing}, title = {Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2022} } @inproceedings{yuan2024diffts, author = {Yuan, Xinyu and Qiao, Yan}, title = {{Diffusion-TS}: Interpretable Diffusion for General Time Series Generation}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{ li2024tmdm, title={Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting}, author={Yuxin Li and Wenchao Chen and Xinyue Hu and Bo Chen and Baolin Sun and Mingyuan Zhou}, booktitle={International Conference on Learning Representations (ICLR)}, year={2024} } @inproceedings{song2019score, title = {Generative Modeling by Estimating Gradients of the Data Distribution}, author = {Song, Yang and Ermon, Stefano}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2019} } @inproceedings{song2023consistency, title = {Consistency Models}, author = {Song, Yang and Dhariwal, Prafulla and Chen, Mark and Sutskever, Ilya}, booktitle = {Proceedings of the 40th International Conference on Machine Learning (ICML)}, year = {2023} } @inproceedings{liu2023rectified, title = {Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow}, author = {Liu, Xingchao and Gong, Chengyue and Liu, Qiang}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } @inproceedings{muller2022pfn, author = {M{\"u}ller, Samuel and Hollmann, Noah and Pineda Arango, Sebastian and Grabocka, Josif and Hutter, Frank}, title = {Transformers Can Do {B}ayesian Inference}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2022} } @inproceedings{wies2023learnability, author = {Wies, Noam and Levine, Yoav and Shashua, Amnon}, title = {The Learnability of In-Context Learning}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2023} } @article{fryzlewicz2014wbs, author = {Fryzlewicz, Piotr}, title = {Wild Binary Segmentation for Multiple Change-Point Detection}, journal = {The Annals of Statistics}, year = {2014}, volume = {42}, number = {6}, pages = {2243--2281} } @article{dahlhaus1997fitting, author = {Dahlhaus, Rainer}, title = {Fitting Time Series Models to Nonstationary Processes}, journal = {The Annals of Statistics}, year = {1997}, volume = {25}, number = {1}, pages = {1--37} } @article{engle1987cointegration, author = {Engle, Robert F. and Granger, C. W. J.}, title = {Co-integration and Error Correction: Representation, Estimation, and Testing}, journal = {Econometrica}, year = {1987}, volume = {55}, number = {2}, pages = {251--276} } @article{johansen1991estimation, author = {Johansen, S{\o}ren}, title = {Estimation and Hypothesis Testing of Cointegration Vectors in Gaussian Vector Autoregressive Models}, journal = {Econometrica}, year = {1991}, volume = {59}, number = {6}, pages = {1551--1580} } @book{lutkepohl2005new, author = {L{\"u}tkepohl, Helmut}, title = {New Introduction to Multiple Time Series Analysis}, publisher = {Springer}, year = {2005} } @book{hamilton1994time, author = {Hamilton, James D.}, title = {Time Series Analysis}, publisher = {Princeton University Press}, year = {1994} } % ---------- Foundations of attention and transformers ---------- @inproceedings{vaswani2017attention, author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, Lukasz and Polosukhin, Illia}, title = {Attention Is All You Need}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2017} } % ---------- Transformers for time series ---------- @inproceedings{zhou2021informer, author = {Zhou, Haoyi and Zhang, Shanghang and Peng, Jieqi and Zhang, Shuai and Li, Jianxin and Xiong, Hui and Zhang, Wancai}, title = {Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, year = {2021} } @inproceedings{wu2021autoformer, author = {Wu, Haixu and Xu, Jiehui and Wang, Jianmin and Long, Mingsheng}, title = {Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2021} } @inproceedings{zhou2022fedformer, author = {Zhou, Tian and Ma, Ziqing and Wen, Qingsong and Wang, Xue and Sun, Liang and Jin, Rong}, title = {{FEDformer}: Frequency Enhanced Decomposed Transformer for Long-Term Series Forecasting}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2022} } @inproceedings{zeng2023transformers, author = {Zeng, Ailing and Chen, Muxi and Zhang, Lei and Xu, Qiang}, title = {Are Transformers Effective for Time Series Forecasting?}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, year = {2023} } @inproceedings{nie2023patchtst, author = {Nie, Yuqi and Nguyen, Nam H. and Sinthong, Phanwadee and Kalagnanam, Jayant}, title = {A Time Series Is Worth 64 Words: Long-Term Forecasting with Transformers}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } @inproceedings{liu2024itransformer, author = {Liu, Yong and Hu, Tengge and Zhang, Haoran and Wu, Haixu and Wang, Shiyu and Ma, Lintao and Long, Mingsheng}, title = {{iTransformer}: Inverted Transformers Are Effective for Time Series Forecasting}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @article{salinas2020deepar, author = {Salinas, David and Flunkert, Valentin and Gasthaus, Jan and Januschowski, Tim}, title = {{DeepAR}: Probabilistic Forecasting with Autoregressive Recurrent Networks}, journal = {International Journal of Forecasting}, year = {2020}, volume = {36}, number = {3}, pages = {1181--1191} } @inproceedings{oreshkin2020nbeats, author = {Oreshkin, Boris N. and Carpov, Dmitri and Chapados, Nicolas and Bengio, Yoshua}, title = {{N-BEATS}: Neural Basis Expansion Analysis for Interpretable Time Series Forecasting}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2020} } % ---------- Foundation models for time series ---------- @article{ ansari2024chronos, title={Chronos: Learning the Language of Time Series}, author={Abdul Fatir Ansari and Lorenzo Stella and Caner Turkmen and Xiyuan Zhang and Pedro Mercado and Huibin Shen and Oleksandr Shchur and Syama Sundar Rangapuram and Sebastian Pineda Arango and Shubham Kapoor and Jasper Zschiegner and Danielle C. Maddix and Hao Wang and Michael W. Mahoney and Kari Torkkola and Andrew Gordon Wilson and Michael Bohlke-Schneider and Yuyang Wang}, journal={Transactions on Machine Learning Research}, issn={2835-8856}, year={2024} } @article{hyndman2008automatic, author = {Hyndman, Rob J. and Khandakar, Yeasmin}, title = {Automatic Time Series Forecasting: The forecast Package for {R}}, journal = {Journal of Statistical Software}, year = {2008}, volume = {27}, number = {3}, pages = {1--22} } @article{liu2025moirai2, author = {Liu, Chenghao and Aksu, Taha and Liu, Juncheng and Liu, Xu and Yan, Hanshu and Pham, Quang and Savarese, Silvio and Sahoo, Doyen and Xiong, Caiming and Li, Junnan}, title = {Moirai 2.0: When Less Is More for Time Series Forecasting}, journal = {arXiv preprint arXiv:2511.11698}, year = {2025} } @inproceedings{das2024timesfm, author = {Das, Abhimanyu and Kong, Weihao and Sen, Rajat and Zhou, Yichen}, title = {A Decoder-Only Foundation Model for Time-Series Forecasting}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2024} } @inproceedings{woo2024moirai, author = {Woo, Gerald and Liu, Chenghao and Kumar, Akshat and Xiong, Caiming and Savarese, Silvio and Sahoo, Doyen}, title = {Unified Training of Universal Time Series Forecasting Transformers}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2024} } @article{garza2023timegpt, author = {Garza, Azul and Challu, Cristian and Mergenthaler-Canseco, Max}, title = {{TimeGPT-1}}, journal = {arXiv preprint arXiv:2310.03589}, year = {2023} } @article{rasul2023lagllama, author = {Rasul, Kashif and Ashok, Arjun and Williams, Andrew Robert and Ghonia, Hena and Bhagwatkar, Rishika and Khorasani, Arian and Darvishi Bayazi, Mohammad Javad and Adamopoulos, George and Riachi, Roland and Hassen, Nadhir and Bilo{\v{s}}, Marin and Garg, Sahil and Schneider, Anderson and Chapados, Nicolas and Drouin, Alexandre and Zantedeschi, Valentina and Nevmyvaka, Yuriy and Rish, Irina}, title = {Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting}, journal = {arXiv preprint arXiv:2310.08278}, year = {2023} } @inproceedings{shi2024timemoe, author = {Shi, Xiaoming and Wang, Shiyu and Nie, Yuqi and Li, Dianqi and Ye, Zhou and Wen, Qingsong and Jin, Ming}, title = {{Time-MoE}: Billion-Scale Time Series Foundation Models with Mixture of Experts}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @article{aksu2024gifteval, author = {Aksu, Taha and Woo, Gerald and Liu, Juncheng and Liu, Xu and Liu, Chenghao and Savarese, Silvio and Xiong, Caiming and Sahoo, Doyen}, title = {{GIFT-Eval}: A Benchmark for General Time Series Forecasting Model Evaluation}, journal = {arXiv preprint arXiv:2410.10393}, year = {2024} } % ---------- Diffusion and score-based generative models ---------- @inproceedings{ho2020denoising, author = {Ho, Jonathan and Jain, Ajay and Abbeel, Pieter}, title = {Denoising Diffusion Probabilistic Models}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2020} } @inproceedings{song2021scorebased, author = {Song, Yang and Sohl-Dickstein, Jascha and Kingma, Diederik P. and Kumar, Abhishek and Ermon, Stefano and Poole, Ben}, title = {Score-Based Generative Modeling through Stochastic Differential Equations}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2021} } @inproceedings{song2021ddim, author = {Song, Jiaming and Meng, Chenlin and Ermon, Stefano}, title = {Denoising Diffusion Implicit Models}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2021} } @inproceedings{lee2024ant, title={ANT: Adaptive Noise Schedule for Time Series Diffusion Models}, author={Lee, Seunghan and Lee, Kibok and Park, Taeyoung}, booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, year={2024} } @article{GRANGER1974111, title = {Spurious regressions in econometrics}, journal = {Journal of Econometrics}, volume = {2}, number = {2}, pages = {111-120}, year = {1974}, issn = {0304-4076}, author = {C.W.J. Granger and P. Newbold} } @article{challu2023nhits, title={{NHITS}: Neural Hierarchical Interpolation for Time Series Forecasting}, author={Challu, Cristian and Olivares, Kin G. and Oreshkin, Boris N. and Garza Ramirez, Federico and Mergenthaler Canseco, Max and Dubrawski, Artur}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={37}, number={6}, pages={6989--6997}, year={2023} } @article{marcellino2006comparison, author = {Marcellino, Massimiliano and Stock, James H. and Watson, Mark W.}, title = {A Comparison of Direct and Iterated Multistep {AR} Methods for Forecasting Macroeconomic Time Series}, journal = {Journal of Econometrics}, year = {2006}, volume = {135}, number = {1--2}, pages = {499--526} } @article{ho2022classifierfree, author = {Ho, Jonathan and Salimans, Tim}, title = {Classifier-Free Diffusion Guidance}, journal = {arXiv preprint arXiv:2207.12598}, year = {2022} } @inproceedings{lipman2023flow, author = {Lipman, Yaron and Chen, Ricky T. Q. and Ben-Hamu, Heli and Nickel, Maximilian and Le, Matt}, title = {Flow Matching for Generative Modeling}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } % ---------- Diffusion for time series forecasting ---------- @inproceedings{rasul2021timegrad, author = {Rasul, Kashif and Seward, Calvin and Schuster, Ingmar and Vollgraf, Roland}, title = {Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2021} } @inproceedings{tashiro2021csdi, author = {Tashiro, Yusuke and Song, Jiaming and Song, Yang and Ermon, Stefano}, title = {{CSDI}: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2021} } @article{alcaraz2023sssd, author = {{Lopez Alcaraz}, Juan Miguel and Strodthoff, Nils}, title = {Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models}, journal = {Transactions on Machine Learning Research (TMLR)}, year = {2023} } @inproceedings{shen2023timediff, author = {Shen, Lifeng and Kwok, James T.}, title = {Non-autoregressive Conditional Diffusion Models for Time Series Prediction}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2023} } @inproceedings{kollovieh2023tsdiff, author = {Kollovieh, Marcel and Ansari, Abdul Fatir and Bohlke-Schneider, Michael and Zschiegner, Jasper and Wang, Hao and Wang, Yuyang}, title = {Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2023} } @inproceedings{fan2024mgtsd, author = {Fan, Xinyao and Wu, Yueying and Xu, Chang and Huang, Yuhao and Liu, Weiqing and Bian, Jiang}, title = {{MG-TSD}: Multi-Granularity Time Series Diffusion Models with Guided Learning Process}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{shen2024mrdiff, author = {Shen, Lifeng and Chen, Weiyu and Kwok, James T.}, title = {Multi-Resolution Diffusion Models for Time Series Forecasting}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } % ---------- State-space backbone used by SSSD ---------- @inproceedings{gu2022s4, author = {Gu, Albert and Goel, Karan and R{\'e}, Christopher}, title = {Efficiently Modeling Long Sequences with Structured State Spaces}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2022} } % ---------- Surveys ---------- @article{yang2024survey, author = {Yang, Yiyuan and Jin, Ming and Wen, Haomin and Zhang, Chaoli and Liang, Yuxuan and Ma, Lintao and Wang, Yi and Liu, Chenghao and Yang, Bin and Xu, Zenglin and Bian, Jiang and Pan, Shirui and Wen, Qingsong}, title = {A Survey on Diffusion Models for Time Series and Spatio-Temporal Data}, journal = {arXiv preprint arXiv:2404.18886}, year = {2024} } @article{meijer2024rise, author = {Meijer, Caspar and Chen, Lydia Y.}, title = {The Rise of Diffusion Models in Time-Series Forecasting}, journal = {arXiv preprint arXiv:2401.03006}, year = {2024} } % ---------- Evaluation ---------- @article{makridakis2020m4, author = {Makridakis, Spyros and Spiliotis, Evangelos and Assimakopoulos, Vassilios}, title = {The {M4} Competition: 100,000 Time Series and 61 Forecasting Methods}, journal = {International Journal of Forecasting}, year = {2020}, volume = {36}, number = {1}, pages = {54--74} } @article{makridakis2022m5, author = {Makridakis, Spyros and Spiliotis, Evangelos and Assimakopoulos, Vassilios}, title = {The {M5} Competition: Background, Organization, and Implementation}, journal = {International Journal of Forecasting}, year = {2022}, volume = {38}, number = {4}, pages = {1325--1336} } @article{gneiting2007strictly, author = {Gneiting, Tilmann and Raftery, Adrian E.}, title = {Strictly Proper Scoring Rules, Prediction, and Estimation}, journal = {Journal of the American Statistical Association}, year = {2007}, volume = {102}, number = {477}, pages = {359--378} } @inproceedings{kim2022revin, author = {Kim, Taesung and Kim, Jinhee and Tae, Yunwon and Park, Cheonbok and Choi, Jang-Ho and Choo, Jaegul}, title = {Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2022} } @article{litterman1986forecasting, author = {Litterman, Robert B.}, title = {Forecasting with {B}ayesian Vector Autoregressions---Five Years of Experience}, journal = {Journal of Business \& Economic Statistics}, year = {1986}, volume = {4}, number = {1}, pages = {25--38} } @article{banbura2010large, author = {Ba\'nbura, Marta and Giannone, Domenico and Reichlin, Lucrezia}, title = {Large {B}ayesian Vector Auto Regressions}, journal = {Journal of Applied Econometrics}, year = {2010}, volume = {25}, number = {1}, pages = {71--92} } @article{stock2002forecasting, author = {Stock, James H. and Watson, Mark W.}, title = {Forecasting Using Principal Components from a Large Number of Predictors}, journal = {Journal of the American Statistical Association}, year = {2002}, volume = {97}, number = {460}, pages = {1167--1179} } @article{baing2002, author = {Bai, Jushan and Ng, Serena}, title = {Determining the Number of Factors in Approximate Factor Models}, journal = {Econometrica}, year = {2002}, volume = {70}, number = {1}, pages = {191--221} } @article{basu2015, author = {Basu, Sumanta and Michailidis, George}, title = {Regularized Estimation in Sparse High-Dimensional Time Series Models}, journal = {The Annals of Statistics}, year = {2015}, volume = {43}, number = {4}, pages = {1535--1567} } @article{kock2015, author = {Kock, Anders Bredahl and Callot, Laurent}, title = {Oracle Inequalities for High Dimensional Vector Autoregressions}, journal = {Journal of Econometrics}, year = {2015}, volume = {186}, number = {2}, pages = {325--344} } @article{dickey1979, author = {Dickey, David A. and Fuller, Wayne A.}, title = {Distribution of the Estimators for Autoregressive Time Series with a Unit Root}, journal = {Journal of the American Statistical Association}, year = {1979}, volume = {74}, number = {366}, pages = {427--431} } @article{phillips1988, author = {Phillips, Peter C. B. and Perron, Pierre}, title = {Testing for a Unit Root in Time Series Regression}, journal = {Biometrika}, year = {1988}, volume = {75}, number = {2}, pages = {335--346} } @article{blanchard1989, author = {Blanchard, Olivier Jean and Quah, Danny}, title = {The Dynamic Effects of Aggregate Demand and Supply Disturbances}, journal = {The American Economic Review}, year = {1989}, volume = {79}, number = {4}, pages = {655--673} } @book{kilian2017, author = {Kilian, Lutz and L\"utkepohl, Helmut}, title = {Structural Vector Autoregressive Analysis}, publisher = {Cambridge University Press}, year = {2017} } @book{johansen1995, author = {Johansen, S{\o}ren}, title = {Likelihood-Based Inference in Cointegrated Vector Autoregressive Models}, publisher = {Oxford University Press}, year = {1995} } @misc{jain2026timesfm3, author = {Jain, Ayush and Sen, Rajat}, title = {{TimesFM-3}: A Zero-Shot Foundation Model for Multivariate Forecasting}, howpublished = {Google Research Blog}, year = {2026}, month = aug, note = {Model weights released as google/timesfm-3.0-pytorch}, url = {https://research.google/blog/timesfm-3-a-zero-shot-foundation-model-for-multivariate-forecasting/} } @article{das2025synapse, author = {Das, Sarkar Snigdha Sarathi and Goyal, Palash and Parmar, Mihir and Song, Yiwen and Le, Long T. and Miculicich, Lesly and Yoon, Jinsung and Zhang, Rui and Palangi, Hamid and Pfister, Tomas}, title = {{Synapse}: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models}, journal = {arXiv preprint arXiv:2511.05460}, year = {2025} } @article{laglil2026finetuning, author = {Laglil, Morad and Pracca, Bertrand and Devijver, Emilie and Gaussier, Eric}, title = {Foundation Models and Fine-Tuning: Toward a New Generation of Models for Time Series Forecasting}, journal = {arXiv preprint arXiv:2607.23146}, year = {2026} }