Accepted Papers

2026

1. Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks

   Bethmage Mayuka Jayawardhana, Nihal Sharma, Kazem Meidani, C. Bayan Bruss, Tom Goldstein, and Doron L Bergman
2. The Arrow of Time: What Tabular Foundation Models Miss in Time Series Forecasting

   Andres Potapczynski, Ravi Kiran Selvam, Tatiana Konstantinova, Malcolm Wolff, Kin G. Olivares, Ruijun Ma, Michael W. Mahoney, Andrew Gordon Wilson, Boris N. Oreshkin, and Dmitry Efimov
3. EnergyX: An Agentic Framework for Explainable Energy Forecasting and Anomaly Detection

   Sanyat Fale, Naman Srivastava, and Pandarasamy Arjunan
4. Expressive Power of Recurrent Spiking Neural Networks for Sequence Modeling

   Duc Anh Nguyen, Massimiliano Datres, Ernesto Araya, and Gitta Kutyniok
5. TS-Haystack: A Multi-Scale Retrieval Benchmark for Time Series Language Models

   Nicolas Zumarraga, Thomas Kaar, Ning Wang, Maxwell A Xu, Max Rosenblattl, Markus Kreft, Kevin O’Sullivan, Paul Schmiedmayer, Patrick Langer, and Robert Jakob
6. An Agentic Framework for Causal Discovery and Forecasting in Oil and Gas Time Series

   Ahmed Esmin, Alexandre Mello Ferreira, and Anderson Rocha
7. Benchmarking LLM Summaries of Multimodal Clinical Time Series for Remote Monitoring

   Aditya Shukla, Yining Yuan, J. Ben Tamo, Yifei Wang, Micky C. Nnamdi, Benoit Louis Marteau, Shaun Qien Yeau Tan, Jieru Li, Brad Willingham, and May Dongmei Wang
8. From Noisy Neural Time Series to Structured Language: A Foundation Model for Imagined Speech Decoding from EEG signals

   Sparsh Rastogi, Kanav Dhanda, Akshat Bakshi, Tanmay Kumar, and Jatin Bedi
9. PETS: Inference-Time Differentially Private Synthetic Time Series Generation

   Yangzhixin Luo, Haibo Wu, Alessandro Cornacchia, Chenxi Liu, and Marco Canini
10. WaveFM: Wavelet Decomposition Masked Reconstruction for Multi-Scale Time-series Foundation Model

    Seongbeom Park, Hyunwoo Seo, Yichen Ma, Hojin Cho, Chiehyeon Lim, and Jianjun Shi
11. Do We Need Domain-Specific Time-Series Models? Insights from EEG Classification Benchmarks

    Liuyin Yang, Qiang Sun, and Marc M. Van Hulle
12. Balanced Latent Semantics and Signal Fidelity for EEG representation learning

    Van-Chien Nguyen, Trung-Hieu Tran, Tuan-Kiet Doan, Quang Hung Pham, Ngoc-Son Vu, Duc Han LE, Huy Phan, Phi Le Nguyen, Nikola Simidjievski, Samuel Tardieu, and Van-Tam Nguyen
13. Hindsight Preference Optimization for Financial Time Series Advisory

    Yanwei CUI, Guanghui Wang, Xing Zhang, Peiyang He, Ziyuan Li, Bing Zhu, Qucy Wei Qiu, Xusheng WANG, Zheng Yu, and Anqi Xin
14. Complementing Domain Labels with WaveEnergy Signatures for Time Series Heterogeneity

    Seongbeom Park, Hyunwoo Seo, Yichen Ma, Hojin Cho, Chiehyeon Lim, and Jianjun Shi
15. Status-Aware Self-Supervised Forecasting for Irregular Clinical Time Series

    Kwanhyung Lee, Joohyung Lee, Jong-Heon Kim, Sangchul Hahn, and Eunho Yang
16. Do Normalization Choice Matter for Causal Large Time-Series Models?

    Samy-Melwan Vilhes, Gilles Gasso, and Mokhtar Z. Alaya
17. Auditing Black-Box Trends: Structural Inductive Bias Facilitates Causal Interpretability in Clinical Time Series

    Aditya Kumar Karna, and Trina Dutta Barlow
18. Cached Foundation Model Summaries for Memory-Efficient Clinical Time Series Inference

    Rafi Al Attrach, Rajna Fani, David Restrepo, Yugang jia, Leo Anthony Celi, and Peter J. Schüffler
19. GPT2MEG: Quantizing MEG for Autoregressive Generation

    Richard Csaky, Mats W.J. Van Es, Oiwi Parker Jones, and Mark Woolrich
20. Factor Dimensionality and the Bias–Variance Tradeoff in Diffusion Portfolio Models

    Avi Bagchi, Michael Tesfaye, and Om Shastri
21. TimEE: Towards End-to-end Time Series Classification via In-Context Learning

    Jaris Küken, Shi Bin Hoo, Lennart Purucker, and Frank Hutter
22. Beyond Fit & Predict: Forecasting API for the Foundation Model Era

    Franz J Király, Felipe Lourenço Angelim Vieira, Simon Blanke, Benedikt Heidrich, and  Jigyasu
23. TiCT: A Synthetically Pre-Trained Foundation Model for Time Series Classification

    Chin-Chia Michael Yeh, Uday Singh Saini, Junpeng Wang, Xin Dai, Xiran Fan, Jiarui Sun, Yujie Fan, and Yan Zheng
24. ZODIAC—ZERO-INFLATED OVERSHOOT CONTROLLED DUAL-HEAD INTEGRATION FOR ASYMMETRIC CROSS-DOMAIN FORECASTING

    Igor Yakushin, Sai Krishna Kiran Beathanabhotla, Dhruv Garg, and Md Mahmudur Rahman
25. Regimen-Aware Forecasting for Mechanistic Virtual Patients with Time-Series Foundation Models

    Charlie George Barker, Ahmad Wisnu Mulyadi, Sanjana Balaji Kuttae, Ansh Kumar, Lilija Wehling, Thomas Rückle, Sommer Anjum, Anastasios Siokis, Hans-Christoph Schneider, Sven Jager, Thomas Klabunde, Tommaso Andreani, and Gurdeep Singh
26. Improving Conditional Coverage in Time-Series Foundation Models via Direct Volatility Modeling

    Jason B. Cho, and David S. Matteson
27. UTICA: Multi-Objective Self-Distllation Fondation Model Pretraining for Time Series Classification

    Yessin Moakher, Youssef Attia El Hili, and Vasilii Feofanov
28. Multi-agentic Framework for Developing and Evaluating Biometric-based Multimodal Synthetic Personas: A Case Study on Pregnancy and Postpartum Users

    Poojita Garg, Conor Heneghan, Katherine A Heller, Taedong Yun, Maja Mataric, and Mercy Nyamewaa Asiedu
29. Time Series Foundation Models Improve LLM Decisions: A Case Study in Stock Trading

    Shifeng Xie, Ziwei Li, Themis Palpanas, Peilin Zhao, and Chenghao Liu
30. Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies

    Vasilii Feofanov, Songkang Wen, Lujia Pan, Jianfeng Zhang, and Ievgen Redko
31. PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning

    Hengbo Xiao, Jingyuan Fan, Xin Tong, Jingzhao Zhang, Chao Lu, and Guannan He
32. Learning to Query History: Nonstationary Classification via Learned Retrieval

    Jimmy Gammell, Bishal Thapaliya, Bilel Fehri, Riyasat Ohib, and Deepayan Chakrabarti
33. APTGuard: An APT Detection Method Based on LLM and Time-Series Augmentation

    Xinran Li, and Zijun Dou
34. TS-Arena: A Live Forecast Pre-Registration Platform for Leakage-Free Evaluation of Time Series Foundation Models

    Marcel Meyer, Sascha Kaltenpoth, Henrik Albers, Kevin Zalipski, and Oliver Mueller
35. Large EEG Foundation Model Learns Informative Low-Frequency Representations from Intracranial Brain Signals

    Qiang Sun, Liuyin Yang, Eva Calvo Merino, and Marc M. Van Hulle
36. Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings

    Gerardo Pastrana, Sina Khoshfetrat Pakazad, Utsav Dutta, and Henrik Ohlsson
37. WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting

    Shunyu Wu, Jiawei Huang, Weibin Feng, Boxin Li, Xiao Zhang, Erli Meng, Dan Li, Jian Lou, and See-Kiong Ng
38. Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting

    Rishi Ahuja, Kumar Prateek, Simranjit Singh, and Dr Vijay Kumar
39. KeyTrend: Automated Keyword Synthesis via LLMs for Demand Forecasting with Google Trends

    Ali Barooni, Patrick Munroe, and Frédéric Quesnel
40. Overcoming the Modality Gap in Context-Aided Forecasting

    Vincent Zhihao Zheng,  Marcotte, Arjun Ashok, Andrew Robert Williams, Lijun Sun, Alexandre Drouin, and Valentina Zantedeschi
41. Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models

    Anurag Mishra
42. Do Foundation Models Generalize to Real-World EV Fleets? A 1.1M-Drive Benchmark

    Patrick Ahrend, Stefan Pfund, and Felix Divo
43. Non-Stationarity in the Embedding Space of Time Series Foundation Models

    Jinmyeong Choi, Brad Shook, and Artur Dubrawski
44. Rethinking Multimodal Time-Series Forecasting Evaluation

    Haoxin Liu, Yichen Zhou, Rajat Sen, B. Aditya Prakash, and Abhimanyu Das
45. TimeSAE: Mechanistic Interpretability for Time-Series Foundation Models

    Vedika Sanjeev Lakhanpal
46. TF-JEPA: Predictive Alignment of Time–Frequency Representations Without Contrastive Pairs

    Michael Chaykowsky
47. Narrative of Time across Scales (NoTS)

    Wenrui Ma, Ran Liu, Ellen L. Zippi, Christopher Michael Sandino, Juri Minxha, Behrooz Mahasseni, Erdrin Azemi, Ali Moin, and Eva L Dyer
48. STAMP: Shared-Dictionary Shapelet Tokenization For Multi-Resolution Time-Series Compression

    Bibhus Luitel, Payal Mohapatra, Subrata Biswas, and Bashima Islam
49. Time-Series as Feedback: Evaluating Adaptive Reasoning in LLM Agents

    Ryo Kuroki, Amin Mansouri, and Philippe Schwaller
50. Beyond Statistical Changepoint Detection: Semantic Interpretation of Time Series via LLMs

    Hong Kiat Tan, Trilokya Akula, Akash Tonne, and Thomas Blake
51. Tune-as-Inference: Amortized Configuration Learning for Time Series Foundation Models

    Piyush Gupta, Doyen Sahoo, Manpreet Singh, and Vikram Pudi
52. Forecasting Solar Flares with the EVEREST Transformer

    Antanas Žilinskas, Robert Noel Shorten, and Jakub Marecek
53. Interventional Time Series Priors for Causal Foundation Models

    Dennis Thumm, and Ying Chen
54. State-Space Modeling in Natural Language

    Nikita Mehandru, Marie-Laure Charpignon, Kaihua Hou, David Bamman, and Ahmed Alaa
55. Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS

    Gaspard Berthelier, Mariia Baranova, Andrei-Tiberiu Pantea, Etienne Le Naour, Adrien Petralia, Tahar Nabil, and Themis Palpanas
56. The Geometry of Time-Series Diffusion: Why Latent Space Diffusion Works for Generation and Imputation

    Afshin Asadi, and Ramin Moghaddass
57. Beyond Flat Taxonomies: Hierarchical Capability Profiling for Time-Series Understanding and Reasoning in Large Models

    Yao Yin, Zhenyu Xiao, Musheng Li, Yiwen Liu, Sutong Nan, Yiting He, Ruiqi Wang, Zhenwei Zhang, Qingmin Liao, and Yuantao Gu
58. Context-Informed Sequence Classification: A Multimodal Approach to Vehicle Diagnostics

    Hugo Math, and Rainer Lienhart
59. A Learnable Wavelet Transformer for Long-Short Equity Trading and Risk-Adjusted Return Optimization

    Shuozhe Li, Du Cheng, Amy Zhang, and Liu Leqi
60. LLM-Assisted Logic Rule Learning: Scaling Human Expertise for Time Series Anomaly Detection

    Haoting Zhang, and Shekhar Jain
61. Time-Series Foundation Model Embeddings as Means for Physiological Feature Extraction

    Yujin Lee, Fanurs C.E. Teh, Joo Heung Yoon, and Artur Dubrawski
62. Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting

    Azul Garza, Renee Rosillo Garcia, Rodrigo Mendoza Smith, David Salinas, Andrew Robert Williams, Arjun Ashok, Mononito Goswami, and José Martı́n Juárez Vargas
63. Convolutional Tokenization Improves Transformers for Multi-Channel Time Series Classification

    Lev Kung, Brandon Yee, and Maximilian Rutkowski
64. ARFBench: Benchmarking Multimodal Time Series Reasoning for Software Incident Response

    Stephan Xie, Ben Cohen, Mononito Goswami, Junhong Shen, Emaad Khwaja, Chenghao Liu, David Asker, Othmane Abou-Amal, and Ameet Talwalkar
65. Structure-Aware Set Transformers: Temporal and Variable-type Attention Biases for Asynchronous Clinical Time Series

    Joohyung Lee, Kwanhyung Lee, Changhun Kim, and Eunho Yang
66. CLIC: Contextual Language-Informed Cardiac Pathology Classification

    Giovani D. Lucafó, Rafael Costa Silva, João Lucas Luz Lima Sarcinelli, Andre Guarnier De Mitri, and Diego Furtado Silva
67. On the Role of Context in Zero-Shot Multivariate Time-Series Forecasting

    Rohith Saai Pemmasani Prabakaran, Stijn Verdenius, Partha Das, and Christian A. Naesseth
68. DynLMC: Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series

    Annita Vapsi, Penghang Liu, Saheed Obitayo,  Aakriti, Manoj Cherukumalli, Prathamesh Patil, Amit Varshney, Nicolas Marchesotti, Elizabeth Fons, Vamsi K. Potluru, and Manuela Veloso
69. Finding the Zeitgeist in Time Series Foundation Models

    Felix Divo, Maurice Kraus, Ruben Härle, Patrick Ahrend, and Kristian Kersting
70. LLM4Series: Structured Prompting for Time Series Forecasting with LLMs

    Wesley Barbosa Silva, Maria Fernanda Aquino Freitas Scarcela, Luiz Zairo Bastos Viana, Carlos Caminha, João Paulo Vale Madeiro, and José Wellington Franco Silva
71. From Foundation Model to Tiny Time Series Classifier through Knowledge Distillation

    Adilson Medronha, and Diego Furtado Silva
72. ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series

    Saiyue Lyu, Ruizhi Deng, Thibaut Durand, and Zhitian Zhang
73. Beyond Earthbound Benchmarks: Evaluating Time Series Foundation Models on Satellite Telemetry Data

    Geremia Pompei, and Deepan Anbarasan
74. Learning Transferable Sensor Models via Language-Informed Pretraining

    Yuliang Chen, Arvind Pillai, Yu Wu, Tess Z Griffin, Lisa Marsch, Michael V. Heinz, Nicholas C. Jacobson, and Andrew Campbell
75. ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoders

    Jonathan Raymond Huml, and Beren Millidge