Time_Series
-
Backpropagation-free Deep Learning for Time-Series Classification
2026-10-30 14:33:27Miha Kap\v{s}, Bla\v{z} Bertalani\v{c}, Carolina FortunaAbstract
Deep neural networks for time series classification (TSC) are trained almost exclusively by error backpropagation, which imposes update locking and the weight-transport problem. Backpropagation-free learning rules such as Direct Feedback Alignment (DFA), Direct Random Target Projection (DRTP), and the diffusion-inspired NoProp relax these constraints but have been evaluated almost exclusively on 2D image benchmarks. We adapt these three learners to univariate TSC with 1D convolutional architectures and present the first systematic study of them across 112 datasets from the UCR time series archive, with one hyperparameter-optimized configuration per method. The optimized learners reach mean F1 scores of 0.76 to 0.79, below ROCKET (0.83) and InceptionTime (0.84). We propose an analysis framework that relates the per-dataset gap to InceptionTime to dataset properties and tests convolutional feature learning by replacing the flatten readout with global average pooling, measured as a difference-in-differences (DD) against a backpropagation control on the identical architecture. Intra-class temporal variability is the dataset property most consistently associated with the gap for all three learners (partial Spearman $\rho$ from $0.28$ to $0.40$). Pooling harms DFA and DRTP more than backpropagation (DD $-0.025$ and $-0.055$), consistent with near-random convolutional features, whereas NoProp tolerates pooling as backpropagation does (DD $+0.013$). Relative to backpropagation on the same architectures, DRTP reduces training floating-point operations (FLOPs) by 33% and trains faster only on series longer than about 700 time steps, DFA yields no computational reduction, and NoProp reduces peak memory by 38% at the cost of 48% longer training.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41805
PDF
-
SAR-TS-BERT: Physics-Guided Self-Supervised Pre-Training With Polarimetric Features for SAR Time-Series Crop Classification
2026-10-30 13:37:27Jieqiu Wang, Yuhan Zhang, Bo Zheng, Shaoming ZhangAbstract
Multitemporal synthetic aperture radar (SAR) imagery provides continuous, cloud-free observations of crop phenology for agricultural monitoring in cloudy and rainy regions, yet high-accuracy classification typically requires extensive labeled samples. Although self-supervised pre-training mitigates label dependency in remote sensing, existing frameworks primarily target optical imagery or generic spatial SAR scenes, underutilizing temporal backscatter dynamics and polarimetric scattering mechanisms. We propose SAR-TS-BERT, a physics-guided BERT-style self-supervised pre-training framework for SAR time-series crop classification. SAR-TS-BERT integrates backscatter intensities and polarimetric ratio features (VV, VH, and VV/VH) with dual-polarimetric Cloude-Pottier decomposition parameters ($H/\alpha/A$) into a six-band input representation through two core designs: 1) a physics-guided span masking strategy (SpanPhysics) that adaptively selects contiguous masked spans based on temporal backscatter change rates to prioritize key phenological transitions; and 2) a dual-branch cross-modal fusion encoder that models backscatter and polarimetric decomposition features through separate Transformer branches followed by bidirectional cross-attention fusion. On independent test sets in Estonia (EuroCropsML) and the USA (California CDL), SAR-TS-BERT achieves overall accuracies (OAs) of 96.78% and 87.29%, respectively, and attains a mean monthly OA of 99.37% on Chongming Island, Shanghai. On the Estonia benchmark, pre-training improves OA and Macro F1 by 1.17 and 1.59 percentage points over training from scratch under full supervision, and by 2.58 and 5.19 percentage points using only 1% labeled data. Incorporating SAR scattering physics into temporal self-supervised pre-training effectively enhances crop classification accuracy, parcel-level mapping consistency, and few-shot transferability.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41728
PDF
-
QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models
2026-10-30 00:41:39Junhyeok Kang, Sangjun Han, Jun Seo, Seunghan Lee, Jaehoon Lee, Dongwan Kang, Minjae Kim, Sungdong Yoo, Tae Yoon Lim, Hwanil Choi, Soonyoung Lee, Wonbin AhnAbstract
Time-series foundation models (TSFMs) provide zero-shot forecasts for unseen series, but their accuracy varies across datasets. Combining several models can reduce this variability, yet zero-shot deployment provides no target labels for selecting or weighting them. We find that a model pool is useful not only as a final ensemble, but also as a probability reference for transforming each member forecast. Aligning quantiles through this pool-relative reference improves every member forecast in aggregate. Motivated by this finding, we propose QUAL (Quantile alignment), a simple label-free framework for improving and combining diverse TSFMs. QUAL first produces aligned member forecasts, then applies Huber aggregation and rearrangement to obtain a robust combined forecast without training or model modification. On GIFT-Eval, quantile alignment reduces average member MASE and CRPS by 7.4% and 9.8%. The full framework remains robust when weak forecasters enter a candidate pool whose quality cannot be verified in advance. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41100
PDF
-
TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research
2026-10-29 19:22:33ChengAo Shen, Yanjun Zhao, Haoxin Liu, Bonnie Chen, Miles Ma, Dongjin Song, Hanghang Tong, Qingsong Wen, Jingrui He, Jingchao NiAbstract
As publications and products on time series forecasting (TSF) proliferate, researchers face a growing burden of analyzing existing work. First, not all publications release code. For instance, only about 20% of arXiv TSF papers have a code link in the surveyed period. Second, released code also requires manual maintenance. Thus, TSF researchers must constantly adapt or implement existing works. However, independent implementations can differ in experimental settings and are difficult to maintain. We therefore propose to use AI agents for benchmarking TSF research and even supporting autoresearch, e.g., developing new TSF models. Yet directly applying existing coding agents, such as Claude Code and Codex, is suboptimal: prohibitive costs, limited scalability to large research projects (e.g., benchmarking), and lack of self-maintenance. To address these challenges, we propose TSFLab, a self-improving agent-agnostic "workbench" that equips compatible coding agents with shared resources and tools for low-cost TSF research and continuous maintenance of research resources. Our experiments cover reproduction, benchmarking, and new method development. In reproduction and benchmarking, TSFLab improves task completion by 20-163% and cuts fresh tokens per completed task by 11-66% across baselines. A pilot study of agent-driven method development also shows improved forecasting accuracy via TSFLab, with 32.8-73.6% fewer fresh tokens and 9.2-68.8% less development time than the other settings.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40901
PDF
-
Multistep and Multivariate Time Series Explainability with GradientSHAP: A Wind Power Case Study
2026-10-29 15:57:13Robbie Southam, Zhong Fan, Ke LiAbstract
As the effects of climate change become increasingly apparent, the demand for renewable energy sources such as wind power continues to grow. However, renewables' variable and intermittent nature presents significant challenges in their integration into energy grids. Artificial intelligence (AI) has emerged as a powerful tool to address these issues. Still, its adoption in the energy sector has been hindered by the opacity of many AI models, which often function as black boxes. This paper introduces a carefully adapted GradientSHAP approach to provide interpretability for multivariate, multistep wind power forecasting -- a largely underexplored area. This capability is critical for day-ahead grid management and, to the best of our knowledge, this is the first study to apply GradientSHAP in the context of wind power forecasting. To address the inherent dimensionality, we developed novel visualizations that deliver both local and global explanations, uncovering intricate relationships between environmental factors, site-specific conditions, and temporal dynamics. While GradientSHAP is not an out-of-the-box solution, our findings demonstrate that, with thoughtful handling of SHAP values and domain expertise, it can offer valuable insights into model behaviour, supporting more informed and trustworthy decision-making. Nevertheless, its complexity poses challenges for practical implementation. Future research should focus on streamlining these interpretability methods to make them more actionable for routine deployment in critical energy applications.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40330
PDF
-
Understanding axial attention in TSFMs through single location regression
2026-10-29 14:46:50Andrei-Tiberiu Pantea, Aymeric DieuleveutAbstract
Recent advances in Time Series Foundation Models (TSFMs) increasingly rely on axial attention mechanisms, but despite their empirical success, the theoretical properties of axial attention remain largely unexplored. To bridge this gap, we extend the Single Location Regression framework introduced in Marion et al. [2025] to 2D structured data, in order to study sparse information settings where a target depends on a small number of tokens. We formulate an analytically tractable axial attention-type predictor and rigorously analyze its statistical properties and training dynamics. We prove that under a specific asymptotic regime and with knowledge of the underlying oracle parameters, our predictor achieves Bayes optimality, whereas a class of semi-linear simplifications strictly fails to do so, underlining the role of the inner non-linearity. We prove that for a specific temperature scaling, Projected Gradient Descent converges globally to the optimal oracle parameters. Extensive numerical experiments validate our theoretical findings and highlight the critical role of inverse temperature scheduling in empirical convergence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40188
PDF
-
LLM-PowerTrace: A Dataset of Time-Resolved GPU Power Traces for AI Compute
2026-10-28 05:58:47Jiansheng Wang, Jaskeerat Singh, Haochen Xu, Xinyi Li, Mingyuan Yan, Shaohui Liu, Yuzhuo Li, Yize Chen, Wenqi CuiAbstract
AI compute is becoming large and fast-changing electrical loads. Its impacts on data center infrastructure and power grids depend not only on total energy consumption, but also on how their power draw moves over sub-second to minute timescales, including peaks, ramps, and synchronized fluctuations across accelerators. Existing energy benchmarks for large language models (LLMs) report aggregate quantities such as joules per token and rarely release the underlying time-series measurements, leaving these power dynamics poorly characterized and difficult to model. We introduce LLM-PowerTrace, an open dataset of time-resolved, per-GPU power traces for LLM fine-tuning and inference, sampled every 100\,ms on varying NVIDIA platforms paired with complete workload and system metadata. For fine-tuning, LLM-PowerTrace profiles open model families spanning a wide range of model sizes and fine-tuning methods, together with controlled sweeps over batch size, sequence length, precision, parallelism, and checkpointing. For inference, it covers variations in concurrency, GPU frequency, KV-cache and weight quantization, prompt and output lengths, and request-arrival patterns. LLM-PowerTrace profiles a set of open model families across a wide range of model sizes, and controlled sweeps over batch size, sequence length, precision, parallelism, and checkpointing for fine-tuning, and it sweeps concurrency, GPU frequency, KV cache and weight quantization, prompt and output lengths, and request arrival patterns for inference. Built upon power traces, we define power-grid-facing metrics as well as AI-compute power\&energy scaling law for extrapolating beyond the measured settings. Together, LLM-PowerTrace provides a dataset foundation for modeling, forecasting, and managing the fast-changing electrical behavior of AI compute.
Abstract (translated)
URL
https://arxiv.org/abs/2610.38315
PDF
-
Vendster: An Evaluation Arena to Investigate How Forecasting Tool Quality Affects LLM Agent Behaviors in Buyer-Vendor Negotiation
2026-10-28 05:23:48Charin PolpanumasAbstract
Time-series forecasters are ranked almost entirely by accuracy metrics, but a forecast's decision value, its effect on the downstream decision, need not track accuracy and is rarely measured. This problem compounds as large language model (LLM) agents increasingly consume forecasters as tools, mediating them through stochastic, opaque policies. We present Vendster, an evaluation arena measuring how a forecaster's bias and prediction-interval width change the outcome of a buyer--vendor discount negotiation between two LLM agents. In the reference instance Vendster-M5, sampling base demand patterns from the M5 dataset, we evaluate two frontier-closed LLM families (Claude Opus 4.6 and GPT-5.6 Sol) and two open ones (DeepSeek-V3.2 and Qwen3-235B-A22B). Model-generated forecasts raise sales target attainment by up to +17 percentage points (p<0.001), yet standard forecast evaluation metrics such as relWQL and MASE do not predict negotiation outcomes at a statistically significant level. To isolate the causal structure, we substitute in synthetic forecasts with controlled bias and interval width. Under-prediction bias significantly improves outcomes for agents that react more to the forecasts---dose-response slopes -0.387 and -0.416 (p<0.001). Interval width has no statistically significant effect at zero bias. These findings indicate that the direction of forecast bias and agent forecast-reactivity are more strongly associated with downstream outcomes than forecast accuracy. Vendster is fully customizable and released under CC BY-NC 4.0 at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.38292
PDF
-
Measuring Deep Learning Performance - An Empirical Study of Performance Distributions Across Architectures and Tasks
2026-10-27 22:47:10Kevin L Coakley, Odd Erik GundersenAbstract
Context: Non-determinism in deep learning algorithm design and implementation leads to performance variation, meaning model performance is not a single value, but rather a distribution. These model performance distributions are underexplored despite their impact on robustness. Objective: We investigate the robustness of deep learning performance to sources of non-determinism, specifically focusing on how performance distributions differ across various architectures and tasks. Method: We conducted 186 experiments on image classification and time series forecasting architectures. Each experiment was run 100 times with different random seeds to generate performance distributions, resulting in 18,600 runs. Robustness was quantified using metrics for spread, symmetry, and tail risk. Results: Performance distributions are frequently non-Gaussian, particularly in time series forecasting. Model size does not systematically affect robustness -- larger image classification models show fewer outliers but not lower spread, while smaller time series models show lower spread but more extreme underperformers. Training duration does not scale linearly; early stopping effectively balances performance and robustness. Mean performance does not predict robustness - time series forecasting shows moderate correlation while image classification shows none. Time series models produce nearly three times more underperforming outliers than image classification models, indicating substantially higher tail risk. Conclusions: Tail risk poses serious concerns for Trustworthy AI in high-stakes applications. Models performing well on average may exhibit long tails and extreme outliers revealed only through distributional analysis. Mean performance alone should not guide model selection; assessment of spread, symmetry, and tail risk is essential for reliable model assessment where consistent performance is critical.
Abstract (translated)
URL
https://arxiv.org/abs/2610.38037
PDF
-
Self-Supervised Latent Action-Conditioned World Modeling for Time Series
2026-10-27 20:49:21Chia-Han Kuo, Chengshuai Zhao, Huan Liu, Lo Pang-Yun TingAbstract
Time-series data play an important role in various tasks, such as weather forecasting, web traffic analysis, and speech recognition. Recently, pioneering studies have increasingly adopted Joint-Embedding Predictive Architecture (JEPA) based encoders to learn time-series representations through latent-space prediction. However, they often overlook the underlying factors governing transitions between time-series observations. In this work, we hypothesize that explicitly modeling the information behind changes in time series can facilitate time-series modeling. Building on this hypothesis, we propose ACTS-WM, a self-supervised latent action-conditioned world model framework for time-series analysis. First, we introduce a latent action modeling approach that infers the underlying information behind time-series transitions as latent actions, without requiring explicit action annotations. We then develop a JEPA-based encoder and an action-conditioned world model to predict target time-series representations conditioned on the learned latent actions and task information. We evaluate ACTS-WM across 4 representative tasks on 22 datasets from diverse domains, covering univariate and multivariate forecasting and classification. Comprehensive experiments demonstrate that ACTS-WM can improve downstream performance over pretrained JEPA-based encoders by learning complementary representations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37963
PDF
-
Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons
2026-10-27 19:45:43Aurora Micheli, Claudio Gallicchio, Nergis TomenAbstract
Spiking reservoir computing combines the training efficiency of fixed recurrent reservoirs with the energy efficiency of event-driven inference, where computation is triggered by sparse spikes rather than executed densely at every timestep. However, existing spiking reservoirs almost exclusively rely on Leaky Integrate-and-Fire (LIF) neurons, whose low-pass dynamics limit their ability to distinguish information encoded at different temporal frequencies. We introduce HRF-Res, a liquid state machine in which LIF neurons are replaced by a heterogeneous population of Harmonic Resonate-and-Fire (HRF) neurons. These neurons exhibit intrinsic oscillatory dynamics and selectively respond to input frequencies, enabling the reservoir to capture frequency-specific temporal patterns. The result is more discriminative representations and higher classification accuracy than LIF-based reservoirs, achieved without sacrificing the energy efficiency of spiking computation, with up to 19x lower energy consumption than an equivalent non-spiking oscillatory reservoir. Evaluated on ten benchmarks spanning time series, sequential images, audio spike trains, and neuromorphic vision, HRF-Res achieves state-of-the-art accuracy among spiking reservoir methods. These results demonstrate that introducing frequency-selective dynamics into spiking reservoirs improves representational quality and classification performance while preserving their inherent energy efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37906
PDF
-
Timestral
2026-10-27 17:25:43Adrien Petralia, Alexandre Gavaudan, Artjom Joosen, Etienne Goffinet, Richard Kurle, Yassine El Ouahidi, Yassir Bendou, Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra, Adrian Valente, Adrien Sad\'e, Ahmed Djermani, Alan Jeffares, Albert Jiang, Alberto Bietti, Aleksandr Timashov, Alexandre Cahill, Alexandre Laval, Alexandre Sablayrolles, Alexandros Sanchez Vassopoulos, Am\'elie H\'eliou, Amos You, Andr\'e Jonasson, Andreas F\"urst, Andrew Bai, Andrew Ehrenberg, Andrew Zhao, Andy Lo, Angele Lenglemetz, Anmol Agarwal, Antonia Calvi, Arata Suzuki, Arjun Majumdar, Arthur Fournier, Ashwani Kumar, Augustin Lombard, Avinash Sooriyarachchi, Aylin Guliz Akkus, Aysenur Karaduman, Baptiste Bout, Baptiste Rozi\`ere, Barna P\'asztor, Baudouin De Monicault, Benjamin Holzschuh, Benjamin Tibi, Benno Stein, Bernhard Stadlbauer, Bhargavi Bhaskar, Binbing Hou, B{\l}a\.zej Osi\'nski, Boris van Breugel, Camille Le Scao, Chaoran Yu, Charlotte Cronj\"ager, Chen-Yo Sun, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Cl\'emence Lanfranchi, Colin Bonatti, Corentin Barreau, Corentin Sautier, Cristiana-Diana Diaconu, Cyprien Courtot, Daniel Lopes, Daniel Marczak, Darius Dabert, Diego de las Casas, Dominik Nuss, Dylan Rubini, Dzmitry Soupel, Elizaveta Demyanenko, Elliot Chane-Sane, Emilien Fugier, Emmanuel Gottlob, Erik Aas, Etienne Duchesne, Fabian Paischer, Fabian Schlager, Faruk Ahmed, Federico Baldassarre, F\'elix Rosseeuw, Filip Szatkowski, Filippo Vicentini, Florian Wiesner, Gabrielle Berrada, Ga\"etan Ecrepont, Gaspard Blanchet, Gaspard Donada-Vidal, Gaurav Mahajan, Gauthier Guinet, Genevieve Hayes, Georgii Novikov, Georgios Christoglou, Giada Pistilli, Gonzague de Carpentier, Graeme Nail, Guillaume Breton, Guillaume Kunsch, Guillaume Lample, Guillaume Martin, Guillaume Raille, Guillaume Richard, Guillem Simeon, Gunjan Dhanuka, Gunshi Gupta, Hamza Senhaji Rhazi, Han Zhou, H\'edi Hadiji, Himanshu Jaju, Hope McGovern, Hubert de Parseval, Hugo Cisneros, Hugo Germain, Hugo Thimonier, Hugo Venturini, Hyeonju Lee, Hyunwoo Oh, Iliass Lasri, Ilyas Oulkadda, Jacques Sun, Jan Ludziejewski, Jason Rute, Jean de Becdeli\`evre, Jean Quentin, Jean-Malo Delignon, Jessica Chudnovsky, Jianchao Li, Jie Zhang, Jin Bin Ou, Joachim Studnia, Joep Barmentlo, Johannes Brandstetter, John Harvill, Jonas Amar, Jonas Schweizer, Jonathan Roberts, Jos\'ephine Delas, Josselin Somerville, Jules Depersin, Julien Denize, Julien Tauran, Julien Verlaguet, Kartik Khandelwal, Khyathi Raghavi Chandu, Kilian Tep, Konstantin Mishchenko, Kris Szczepaniak, Kush Jain, Larissa Laich, Laura Calem, Laurence Aitchison, Laurent Callot, Laurent Fainsin, L\'eo Cotteleer, L\'eonard Blier, Lo\"ic Chadoutaud, Lo\"ick Chambon, Lorenzo Proietti, Louis Faucon, Louis Martin, Louis Serrano, Lu Li, Luc Boudier, Lucas Fernandes Martins, Lucas Mebille, Lucile Saulnier, Ludovic Ho Fuh, Luis Montero, {\L}ukasz Borchmann, Maarten Buyl, Malik Hassan Raza, Manon Chossegros, Marcin Mo\.zejko, Margaret Jennings, Markus Hennerbichler, Martin Alexandre, Mathieu Poir\'ee, Mathieu Schmitt, Mathilde Guillaumin, Mathis Felardos, Matthieu Andr\'e, Matthieu Dinot, Matthieu Futeral, Maurits Bleeker, Mauro Comi, Max Mynter, Maxim Berman, Maxime Darrin, Maxime Langelier, Maxime Louis, Maximilian Augustin, Maximilian M\"uller, Mehdi Bouaziz, Melina Jingting Laimon, Mert Unsal, Mia Chiquier, Michael Pilcer, Micha{\l} Pietruszka, Micha{\l} Zaj\k{a}c, Micka\"el Seznec, Mikhail Biriuchinskii, Minh-Quang Pham, Minwoo Kang, Mircea Lica, Morgane Rivi\`ere, Namit Katariya, Natasha {\O}rregaard Klingenbrunn, Nathan Bout, Nathan Grinsztajn, Nathan Simpson, Neeraj Aggarwal, Neil Ashton, Neil Mallinar, Nick B\"uhrer, Nicolas Moreau, Nicol\`o Lucchesi, Ola Mysiak, Oliver Leicht, Olivier Bousquet, Olivier Koch, Parag Jain, Patricia Wang, Patrick Blies, Patrick von Platen, Patryk Saffer, Paul Jacob, Paul Teiletche, Paul Wambergue, Paula Kurylowicz, Pavan Kumar Reddy, Pavel Kuksa, Philippe Formont, Philippe Pinel, Philom\`ene Chagniot, Pierre Glandon, Pierre Stock, Pierre-Andr\'e Savalle, Piotr Mi{\l}o\'s, Poojan Shah, Prateek Gupta, Pravesh Agrawal, Pui Ki Chan, Quentin Desreumaux, Quentin Selle, Quentin Torroba, Quentin Wargnier, Quercus Hernandez, Ram Ramrakhya, Randall Isenhour, Ranjit Parva, Rapha\"el Balouka, Rapha\"el Rialland, Raul Perez Pelaez, Reinhard Sonnleitner, Remi Delacourt, Rishi Shah, Rob Romijnders, Rohan Shah, Rohin Arora, Romain Sauvestre, Roman Soletskyi, Ronan Riochet, Rosalie Millner, Rupert Menneer, Sagar Vaze, Samuel Barry, Samuel Belkadi, Samuel Humeau, Samuele Papa, Sanchit Gandhi, Sandeep Cranganore, Sandeep Subramanian, Sarthak Mittal, Saskia Adaime, Scott Matthews, Sean Cha, Sebastian Kaltenbach, Seungjae Jung, Shashwat Verma, Sherif Waly, Shrimai Prabhumoye, Siddhant Waghjale, Siddharth Gandhi, Simon Lepage, Simon Sorg, Soham Ghosh, Sophie Marbach, Srijan Mishra, Stanislas Lange, Steve Hong, Sumukh Aithal, Szymon Antoniak, Tarun Kumar Vangani, Teddy Turquet, Teven Le Scao, Th\'eo Cachet, Thibaut Lavril, Thomas Chabal, Thomas Coste, Thomas Defard, Thomas Foubert, Thomas Loux, Thomas Robert, Thomas Wang, Tianyu Zhang, Tim Lawson, Timoth\'ee Lacroix, Timothy Wallis, Tobias Kronlachner, Tom Bewley, Tom Edwards, Tomas Hodan, Triantafyllos Afouras, Tuhin Das, Tyler Wang, Udit Saxena, Ulrick Bl\'e, Umar Jamil, Umberto Tomasini, Valentin Mac\'e, Van Phung, Venkata Reddy, Vibha Masti, Victor Jouault, Victor Letzelter, Victor Paltz, Victor Poucheret, Vincent Maladi\`ere, Vincent Pfister, Virgile Richard, Vladislav Bataev, Wassim Bouaziz, Wen Ding Li, William Flanagan, William Havard, William Marshall, Witold J\k{e}drzejewski, Xinghui Li, Xingran Guo, Xinyu Yang, Xuanyu Zhang, Yann Dreze, Yann Viegas, Yannic Neuhaus, Yassine Turki, Yessin Moakher, Yi He, Yihan Wang, Yimu Pan, Yuying Zhu, Yves Martin des Taillades, Zaccharie Ramzi, Zhenlin Xu, Zs\'ofia Cs\'ak\'anyAbstract
We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and Timestral-123M take the top two places on every metric. We achieve this with three ingredients: Decoupled Horizon Forecasting (DHF), which separates prediction tokens from the causally encoded context, so that longer horizons are trained without masking context and each observed value is both a forecast target and context for later forecasts; a covariate framework that natively supports known-future covariates within a causal architecture; and a two-stage pipeline that pretrains exclusively on a diverse, large-scale synthetic corpus before post-training on a mix of real and synthetic data with extended context. This report describes the model design and its benchmark results. Weights for all four models are available on Hugging Face and inference code on GitHub.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37585
PDF
-
Ground-to-Satellite Knowledge Distillation for Crop Classification under Temporal and Geographic Shift
2026-10-27 10:57:49Miro Miranda, Rocco Sedona, Valerio Marsocci, Gabriele Cavallaro, Claudia ParisAbstract
Continuous and up-to-date crop type mapping is essential for agricultural monitoring but is often hampered by limited reference data. The growing availability of ground-level field photographs offers a promising way to address this challenge. When combined with satellite time series, these images provide complementary perspectives on the same parcel, capturing crop characteristics from distinctly different perspectives. However, field photographs are not always available for each satellite pixel at inference time, limiting their potential in scalable crop type mapping. We investigate whether ground photographs can provide privileged supervision for crop classification built on pretrained satellite embeddings. A photo teacher based on frozen CLIP features supervises classifiers trained on AlphaEarth and TESSERA representations; photographs are used only during training. On a paired field photo and satellite imagery dataset with 17 crop classes, knowledge distillation consistently improves over satellite-only classification; for frozen embeddings the margin grows under temporal shift, reaching up to +5.5 macro-F1 points, and widens in geographic holdouts (+3.7 vs +3.0 in-distribution). These results show that ground-view supervision can complement satellite embeddings and improve their robustness without changing inference requirements.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37021
PDF
-
Multi-task Disentangling Fusion Mamba-CNN for MODIS Spectral-Temporal Unmixing with Endmember Variability Modeling
2026-10-27 07:07:54Motasem Alkayid, Yimin Zhu, Naser El-Sheimy, Lincoln Linlin XuAbstract
Spectral-temporal unmixing of MODIS time series is essential for applications such as abundance mapping and spectral library construction, yet it remains challenging due to (i) spectral-temporal information coupling in MODIS data, (ii) intra-class endmember spectral variability and inter-class signature ambiguity, and (iii) the instability of naively fusing multiple expert representations. This paper presents the Multi- task Disentangling Fusion Mamba (MDF-Mamba) to address these limitations. To resolve spectral-temporal coupling, we design a disentangling architecture that pairs per-channel spectral experts with a dedicated bidirectional state-space (Mamba) temporal branch. Convolutional modules each process a single spectral channel, while the Mamba branch encodes the cross-channel seasonal trajectory, forming a multi-branch expert ensemble with soft inter-expert reweighting based on squeeze-and-excitation. For the integration of these spectral and temporal expert outputs, we introduce mHCFusion, adapting the manifold-constrained hyper-connection framework to merge the outputs in a stable and interpretable manner. Endmember variability is addressed by extending the linear mixing model with pixel-wise learnable spectral variability weights that capture intra-class endmember variation. Finally, we design a multi-task training objective that combines supervised abundance estimation with self-supervised spectral reconstruction and endmember regularization terms on the same training data, yielding a highly efficient framework for spectral-temporal unmixing. Experiments on MODIS time series covering the Alberta and Saskatchewan provinces show that MDF-Mamba achieves the best performance on 12 of 14 evaluation metrics across both datasets (7 of 7 on Alberta; 5 of 7 on Saskatchewan), ranking second on the remaining two.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36750
PDF
-
ATEMPO: Amortized Transfer Entropy Model Per-lag Over-Time
2026-10-27 02:49:07Emma Andrews, Konstantinos Kontras, Keane Ong, Maarten De Vos, Gianmarco MengaldoAbstract
When one time series informs another, the delay at which that information arrives determines if models can utilize this relationship effectively. A source may be strongly predictive at one delay but uninformative at neighboring lags. Therefore, fixed input windows may obscure this structure by bundling informative and irrelevant history together. Transfer entropy (TE) can recover these delays by measuring how much a source's past tells us about a target beyond the target's own history. However, existing TE estimators require separate fits across source and conditioning depths, with further estimation on local windows to track delays over time. We introduce ATEMPO, a diffusion-based transfer entropy estimator amortized over lags and time. ATEMPO samples source and conditioning depths during training and conditions explicitly on temporal position, allowing a single score network to estimate the full TE surface without refitting. Differencing this surface recovers when information arrives. Across synthetic datasets with ground-truth TE, ATEMPO achieves the lowest mean relative error among baselines, and on datasets with known lags, ATEMPO achieves $0.98\pm0.04$ lag-detection accuracy. ATEMPO requires a single fit across source depths $K=6$ and target depths $L=3$, whereas existing estimators require 18 separate fits to evaluate the same $K \times L$ grid. On three systems with time-varying lag, ATEMPO is the only estimator to maintain perfect lag-detection accuracy across all evaluated window lengths. These recovered delays improve downstream forecasting: ATEMPO-selected inputs reduce MSE on WEATHER-5K by 7.25%, while 120 selected inputs outperform the benchmark's 240-feature default by 4.6%. Across three brain-computer interface tasks, using ATEMPO-selected lags achieves the highest or equal-best $R^2$, improving mean $R^2$ by 4.1% relative to the strongest competing baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36536
PDF
-
CLOSURE: Cross-Channel Closure for Multivariate Time Series Anomaly Detection
2026-10-26 17:02:10Fan Xu, Hao Wu, Zhi Song, Hanbo Huang, Wenzhuo Ma, Nan Wang, Wei Gong, Xibin ZhaoAbstract
Multivariate time series produced by industrial installations and server clusters are under continuous monitoring, and anomaly detection is the first line of defense before a local fault escalates into a system-wide failure. In the absence of labels, the dominant paradigm trains a reconstruction model on normal data and scores the residual to reach a verdict. Recent work has steadily enriched the expressiveness of the recovery map through Transformers, diffusion models, and cross-scale associations. A residual, however, only certifies that an observation can be recovered; it does not certify that the variables still explain one another as they do under normal operation. A coordinated yet unfamiliar operating transition inflates the residual without breaking any relationship, whereas a sensor drifting away from its peers may leave the residual silent. Methods that fold inter-variable dependencies into the reconstruction objective inherit this ambiguity, because their relational evidence is ultimately supervised by the same recovery loss. We therefore propose CLOSURE, which evaluates recoverability and cross-channel consistency as two normal-data prediction tasks learned in separation. The recoverability task is solved by a diffusion reconstructor conditioned on a discrete memory of normal temporal bases. The consistency task is solved by a relation-closure operator that predicts every channel exclusively from the others, where the target's own trajectory is withheld and sparse signed gates decide which peers are actually used. The two scores are reconciled only through calibration on normal data. Extensive experiments show that CLOSURE consistently outperforms recent reconstruction-, frequency-, and topology-based detectors on public benchmark streams, confirming the value of examining consistency alongside recoverability.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35753
PDF
-
ExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess Calibration
2026-10-26 15:06:39Kadir-Kaan \"Ozer, Ren\'e Ebeling, Markus EnzweilerAbstract
We introduce ExCal, a normal-only multivariate time series anomaly detector that combines raw state retrieval, a signal/derivative subspace, and robust statistics across temporal scales. Each expert map receives a high normality floor from the training prefix. During scoring, positive excess is retained, attenuated for broadly firing maps, and combined with a small rank term. The method fits reference memories and projections without gradient optimization or anomaly labels. Prevalence and ranks depend on the complete scored sequence, making inference batch and transductive rather than online. On 180 series from 17 TSB-AD-M families, ExCal obtains AUC-PR $0.421\pm0.37$ and VUS-PR $0.452\pm0.37$ over three seeds, ranking second among 24 methods. Holm-adjusted paired tests detect no significant difference from AxonAD or StreamVAE, which are the two leading non-pretrained methods on TSB-AD-M, on either primary metric, while finding significant positive differences against the other 21 baselines. A separate single-run probe over three series measures median model-wrapper time of $0.0662$ s. Ablations associate the largest primary-metric changes with raw retrieval and excess-magnitude preservation. The evaluated score is decomposable by expert, but its diagnostic utility and online suitability remain untested.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35568
PDF
-
AdaTrendLike: Adaptive Hierarchical Detrending and Trend Likelihood Scoring for Time Series Anomaly Detection
2026-10-26 13:14:23Van Kwan Zhi Koh, Songnan Lin, Rongmo Luo, Zhiping Lin, Bihan WenAbstract
The rapid proliferation of Industrial Internet of Things devices has led to increasingly large-scale and non-stationary time-series data, posing significant challenges for time-series anomaly detection (TSAD). Existing approaches often focus on reconstructing or forecasting observations while overlooking the role of trend dynamics, which constitute a major source of non-stationarity and contain valuable information for anomaly identification. To address this limitation, we propose AdaTrendLike, a TSAD framework that directly estimates trend likelihoods for anomaly detection. Specifically, we introduce Standardization Embedding to capture local statistical characteristics as latent representations and AdaDetrending to adaptively decompose input series into trend and detrended components. The detrended component is processed through a Fast Fourier Transform and a complex-valued convolutional neural network to learn normal periodic patterns, while TrendEst models the distribution of the trend component. Based on the estimated distribution, TrendLike computes anomaly scores by measuring the likelihood of observed trends, enabling effective detection of deviations from normal behavior. In addition to improving detection performance, the proposed framework provides feature-level interpretability by identifying anomalies through deviations in the estimated trend distribution. Extensive experiments on five public benchmark datasets demonstrate that AdaTrendLike consistently outperforms state-of-the-art TSAD methods, validating its effectiveness and robustness across diverse application scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35400
PDF
-
Self-Supervised Pretraining for PHM: What Transfers, What Does Not, and What Federating It Costs
2026-10-26 11:50:33Jos\'e Sanz-Dur\'an, David Sol\'is-Mart\'inAbstract
Self-supervised pretraining has produced capable time-series foundation models, but its value for Prognostics and Health Management (PHM) has not been measured under leakage-controlled conditions. We measure it on a corpus of 47 public PHM datasets, harmonized to a single tensor contract and partitioned so that 11 datasets are withheld from pretraining in full. Transfer turns out to be task-dependent: a compact channel-independent Transformer encoder (801,808 parameters) pretrained with masked patch prediction raises fault-classification macro-F1 from 0.350 to 0.812 on CWRU and from 0.569 to 0.951 on HSG18, yet on CMAPSS remaining-useful-life estimation no pretrained checkpoint reliably improves upon a from-scratch baseline. We pretrain under two regimes---centralized, and simulated cross-silo federated with ten clients grouped by physical domain---holding architecture, objective, source data and optimization budget fixed. Two further findings are negative. At matched budget the centralized encoder leads by 15.5--20.2 macro-F1 points in four of four comparisons, although the comparison is confounded by a learning-rate schedule that favours the centralized arm and rests on a single pretraining run per regime; on RUL the two regimes are indistinguishable. And the intrinsic SSL loss is not a valid selection criterion: the centralized encoder more than halves the federated reconstruction loss without a corresponding gap on RUL, and a server-momentum sweep moves downstream validation macro-F1 by up to 0.29 while the SSL loss varies by 0.021. Transfer also hinges on the backbone learning rate: the same checkpoint yields 0.169 or 0.829 macro-F1 on CWRU depending on a single order of magnitude. We release the corpus pipeline, the protocol and the code.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35280
PDF
-
Dynamic Multi-Step Decoding for Time-Series Foundation Models
2026-10-25 16:10:01Birmjune Kim, Hyungju Lee, Hyun Oh SongAbstract
Time-series forecasting models typically use a fixed decoding strategy at inference time: either one-shot prediction of the full horizon or autoregressive rollout over atomic chunks. While one-shot decoding reduces error accumulation, it can discard useful sequential structure; conversely, autoregressive decoding preserves temporal dependencies but may compound errors. We argue that the optimal decoding strategy is not fixed across inputs, but should be selected adaptively for each forecasting instance. We propose a dynamic strategy selector that treats the forecast rollout schedule as an inference-time decision problem for frozen pretrained time-series foundation models. The selector is a learned network that ranks candidate rollout schedules using hidden states of the backbone, and is trained on historical windows of the evaluated tasks for each backbone. To make the candidate set tractable over the exponentially large space of horizon partitions, we use dynamic programming that reduces candidate evaluation to quadratic complexity while preserving much of the oracle gain. At deployment, five independently trained selectors vote on each decision, and the policy follows their consensus, falling back to the backbone's one-shot forecast where they disagree. The construction requires only the backbone's hidden states and lightweight selectors, with no fine-tuning of the forecasting backbone. On fev-bench with a frozen Chronos-2 backbone, agreement-gated selection improves point-forecast skill (MASE) over one-shot decoding with statistical significance, mostly on longer horizons. It recovers about 6-8% of the gain that the same dynamic program attains with ground-truth selection. With a frozen Moirai-1.1-R-small backbone, the improvement is also significant on the full benchmark, and for both backbones we claim gains in point accuracy only.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34409
PDF
