Pith. sign in

REVIEW 41 cited by

MOMENT: A Family of Open Time-series Foundation Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.03885 v3 pith:22PYNDU6 submitted 2024-02-06 cs.LG cs.AI

MOMENT: A Family of Open Time-series Foundation Models

Mononito Goswami , Konrad Szafer , Arjun Choudhry , Yifu Cai , Shuo Li , Artur Dubrawski This is my paper
classification cs.LG cs.AI
keywords timeseriesmodelslargediversefoundationpre-trainedautonlab
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce MOMENT, a family of open-source foundation models for general-purpose time series analysis. Pre-training large models on time series data is challenging due to (1) the absence of a large and cohesive public time series repository, and (2) diverse time series characteristics which make multi-dataset training onerous. Additionally, (3) experimental benchmarks to evaluate these models, especially in scenarios with limited resources, time, and supervision, are still in their nascent stages. To address these challenges, we compile a large and diverse collection of public time series, called the Time series Pile, and systematically tackle time series-specific challenges to unlock large-scale multi-dataset pre-training. Finally, we build on recent work to design a benchmark to evaluate time series foundation models on diverse tasks and datasets in limited supervision settings. Experiments on this benchmark demonstrate the effectiveness of our pre-trained models with minimal data and task-specific fine-tuning. Finally, we present several interesting empirical observations about large pre-trained time series models. Pre-trained models (AutonLab/MOMENT-1-large) and Time Series Pile (AutonLab/Timeseries-PILE) are available on Huggingface.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 41 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification

    cs.LG 2026-07 conditional novelty 7.0

    A multi-vehicle naturalistic benchmark finds learned driving embeddings retain driver identity under condition matching, while descriptors collapse and video re-ID is mostly route leakage.

  2. Beyond IID: How General Are Tabular Foundation Models, Really?

    cs.LG 2026-06 unverdicted novelty 7.0

    Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 1...

  3. Why Do Time Series Models Need Long Context Windows?

    cs.LG 2026-06 unverdicted novelty 7.0

    Long input windows are required to identify the generative process in time series forecasting even for short-memory processes, and decoupling identification from forecasting improves scalability.

  4. Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density

    cs.LG 2026-05 unverdicted novelty 7.0

    Olivia harmonizes time series datasets via normalized power spectral density using a Harmonizer module and resonator-based HarmonicAttention, achieving state-of-the-art zero-shot, few-shot, and full-shot forecasting o...

  5. NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces

    cs.LG 2026-05 unverdicted novelty 7.0

    NeuroAtlas benchmarks foundation models on 42 EEG datasets and reports that EEG-specific models do not consistently outperform generic time-series models, standard metrics miss clinical utility, and rankings vary by domain.

  6. TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning

    cs.AI 2026-05 unverdicted novelty 7.0

    TimeClaw is an exploratory execution learning system that turns multiple valid tool-use paths into hierarchical distilled experience for improved time-series reasoning without test-time adaptation.

  7. GAFSV-Net: A Vision Framework for Online Signature Verification

    cs.CV 2026-04 unverdicted novelty 7.0

    GAFSV-Net encodes online signatures as asymmetric Gramian Angular Field images and processes them with dual-branch ConvNeXt plus cross-attention to outperform sequence-based baselines on DeepSignDB and BiosecurID.

  8. Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring

    cs.LG 2026-04 unverdicted novelty 7.0

    A model-agnostic adaptive conformal anomaly detection approach uses weighted quantile bounds learned from past foundation model predictions to deliver interpretable p-value scores with stable calibration under shifts ...

  9. TempusBench: An Evaluation Framework for Time-Series Forecasting

    cs.LG 2026-04 unverdicted novelty 7.0

    TempusBench is a new evaluation framework for time-series forecasting models that supplies fresh non-overlapping datasets, tasks beyond horizon and domain, consistent tuning across models, and visualization tools.

  10. TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale

    cs.AI 2026-04 conditional novelty 7.0

    TimeSeriesExamAgent combines templates and LLM agents to generate scalable time series reasoning benchmarks, demonstrating that current LLMs have limited performance on both abstract and domain-specific tasks.

  11. LoRM: Learning the Language of Rotating Machinery for Self-Supervised Condition Monitoring

    cs.CL 2026-04 unverdicted novelty 7.0

    LoRM is a self-supervised framework that models multi-modal rotating machinery signals as token sequences for prediction with fine-tuned language models, using prediction errors to monitor machine health in real time.

  12. Discrete Prototypical Memories for Federated Time Series Foundation Models

    cs.LG 2026-04 unverdicted novelty 7.0

    FeDPM learns and aligns local discrete prototypical memories across domains to create a unified discrete latent space for LLM-based time series foundation models in a federated setting.

  13. AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection

    cs.LG 2026-02 conditional novelty 7.0

    New RL approach (TimerPO) with ground-truth-generated expert reasoning traces lets 3B-7B multimodal LLMs outperform GPT-4o on time-series anomaly detection and explanation.

  14. TS-Arena -- A Live Forecast Pre-Registration Platform

    cs.LG 2025-12 conditional novelty 7.0

    TS-Arena is a live pre-registration platform that evaluates time series forecasts on future data streams to eliminate information leakage.

  15. Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting

    cs.LG 2025-09 unverdicted novelty 7.0

    Super-Linear introduces a pretrained MoE architecture using frequency-specialized linear experts and spectral gating for efficient general time series forecasting.

  16. Sundial: A Family of Highly Capable Time Series Foundation Models

    cs.LG 2025-02 conditional novelty 7.0

    Sundial uses TimeFlow Loss for native pre-training of Transformers on continuous time series from TimeBench, achieving SOTA point and probabilistic forecasting with millisecond inference.

  17. TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis

    cs.LG 2024-10 unverdicted novelty 7.0

    TS-Reasoner is a domain-oriented agent using LLMs, computational tools, and error feedback for multi-step time series inference, showing better performance than general LLMs on understanding and reasoning benchmarks.

  18. Chronos: Learning the Language of Time Series

    cs.LG 2024-03 conditional novelty 7.0

    Chronos pretrains transformer models on tokenized time series to deliver strong zero-shot forecasting across diverse domains.

  19. LithoFormer: A Robust Framework for Stratigraphic Inference via Transformers

    cs.LG 2026-07 conditional novelty 6.0

    A whole-log transformer with a geology-aware loss predicts stratigraphic zones and marker depths, beating sliding-window baselines on three well-log datasets.

  20. Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics

    cs.LG 2026-07 unverdicted novelty 6.0

    Compares foundation models for probabilistic low-voltage load forecasting on 200 real feeders and introduces a grid-planning metric that scores peak prediction by its effect on asset cost-risk decisions.

  21. Trend strength predicts when generative foundation models win: a power-controlled benchmark, a mechanism, and an actionable selection rule

    stat.AP 2026-07 conditional novelty 6.0

    Zero-shot Chronos wins time-series benchmarks by under-extrapolating trend, and trend strength computed before forecasting predicts when it will beat classical models.

  22. Relational and Sequential Conformal Inference for Energy Time Series over Graphs via Foundation Models

    cs.LG 2026-06 unverdicted novelty 6.0

    STOIC integrates STGNN point forecasting with tabular foundation model in-context learning for conformal prediction to quantify uncertainty in graph-structured energy time series.

  23. Learning Spatio-Temporal Foundation Models from Pure Synthetic Data

    cs.LG 2026-06 conditional novelty 6.0

    A spatio-temporal foundation model pre-trained exclusively on synthetic stochastic graph dynamics outperforms real-data-pretrained STFMs in zero-shot traffic forecasting, according to the paper's benchmarks.

  24. LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data

    cs.LG 2026-06 unverdicted novelty 6.0

    LakeFM pre-trains on large ecological datasets to forecast irregular lake time series and reports competitive or superior performance with physically plausible outputs.

  25. TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models

    cs.AI 2026-06 unverdicted novelty 6.0

    TRACE proposes a temporal conditional estimation paradigm for multimodal time series foundation models that infers incomplete target modalities from auxiliary ones, outperforming prior fusion methods on clinical and s...

  26. Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning

    cs.LG 2026-04 unverdicted novelty 6.0

    CondI applies conditional diffusion models in a two-phase federated pipeline to impute within-modality missing data, then trains extractors on the completed inputs for downstream tasks on clinical datasets.

  27. GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation

    cs.AI 2026-04 unverdicted novelty 6.0

    GeoMind applies an agentic workflow with tool-augmented modules and process supervision to outperform static models on lithology classification from well logs while producing traceable decisions.

  28. Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling

    cs.AI 2026-03 unverdicted novelty 6.0

    Timer-S1 is a released 8.3B-parameter MoE time series model that achieves state-of-the-art MASE and CRPS scores on GIFT-Eval using serial scaling and Serial-Token Prediction.

  29. TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models

    cs.LG 2026-01 conditional novelty 6.0

    TimeSAE trains a sparse autoencoder with counterfactual and consistency losses to explain black-box time series predictions, claiming better faithfulness and out-of-distribution robustness than eight baselines.

  30. Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis

    cs.LG 2026-07 unverdicted novelty 5.0

    Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.

  31. LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning

    cs.LG 2026-07 unverdicted novelty 5.0

    LeNEPA proposes a no-augmentation next-latent prediction recipe that maintains frozen-probe performance across ECG and synthetic diagnostic time-series datasets under fixed-recipe conditions where a tuned JEPA baselin...

  32. EVOTS: Evolutionary Transformer Search for Time Series Forecasting

    cs.LG 2026-06 unverdicted novelty 5.0

    EVOTS evolves modular Transformer-like architectures for multivariate time-series forecasting and reports competitive or improved MSE versus a fixed Transformer baseline on ETT datasets across multiple settings and horizons.

  33. Are Time-Series Foundation Models Ready for E-Nose Data? An Empirical Assessment of Their Embeddings

    cs.LG 2026-06 unverdicted novelty 5.0

    Empirical tests show TSFMs like Chronos-2 and MOMENT need fine-tuning for E-Nose data, with fusion to specialized models further improving gas identification and concentration prediction.

  34. AION: Next-Generation Tasks and Practical Harness for Time Series

    cs.AI 2026-05 unverdicted novelty 5.0

    AION is a time series harness using agents, skills, rules, memory, evaluation, and protocols with temporal grounding, shown in a Kaggle Store Sales case study to produce more artifacts and reviews than direct agent use.

  35. Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs

    cs.LG 2026-05 unverdicted novelty 5.0

    StockR1 unifies LLM-based financial reasoning and time-series forecasting by emitting verifiable forecast actions that condition a decoder, optimized via consistency-grounded RL to improve accuracy on QA and prediction tasks.

  36. Escaping Plato's Cave: JAM for Aligning Independently Trained Vision and Language Models

    cs.LG 2025-07 unverdicted novelty 5.0

    JAM aligns frozen vision and language models via joint autoencoders and multimodal Spread Loss, reliably inducing cross-modal alignment across layer depths, objectives, and model scales.

  37. Towards Intrusion Detection Systems for RPL-based IoT Networks using Foundation Models

    cs.CR 2026-06 unverdicted novelty 4.0

    Fine-tuning the MOMENT foundation model on simulated RPL statistics enables multi-class attack identification with performance comparable to state-of-the-art methods.

  38. Empirical Assessment of Time-Series Foundation Models For Power System Forecasting Applications

    eess.SY 2026-04 unverdicted novelty 4.0

    The paper benchmarks foundation models like TimesFM and Chronos against baselines on eight forecasting capabilities for power system time series.

  39. Cross-Machine Anomaly Detection Leveraging Pre-trained Time-series Model

    cs.LG 2026-04 unverdicted novelty 4.0

    A cross-machine anomaly detection framework disentangles MOMENT embeddings using random forests to create machine-invariant condition features that improve generalization to unseen machines on industrial data.

  40. Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition

    cs.LG 2026-01 conditional novelty 4.0

    Test-time adaptation—adaptive batch norm, replay-regularized feature alignment, and few-shot meta-learning—improves NinaPro DB6 inter-session EMG gesture accuracy from ~57% baseline to ~69–70% unsupervised and ~80% wi...

  41. Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification

    stat.ML 2026-06 unverdicted novelty 3.0

    Dual-stream statistical plus deep-embedding pipeline with rehearsal yields competitive accuracy and low forgetting on five time-series benchmarks for class-incremental classification.