AI Briefing#time-series
The latest AI and developer news about #time-series, with the original source and a short summary.
The latest AI and developer news about #time-series, with the original source and a short summary.
The pre-release project provides a unified TimeF format and API to standardize the discovery, building, and loading of time-series datasets for AI models.
The method corrects posterior probabilities at test time without retraining, maintaining performance on balanced data while fixing recall collapse in imbalanced scenarios.
IBM has unveiled Granite Timeseries Ensemble R1, which combines four time series models.
The open-source model uses a MOMENT-1-large backbone and DARR mode to blend direct predictions with k-nearest-neighbor retrieval from historical data.
The NeurIPS 2026 paper provides a library of synthetic time series generators and augmentations for training a DeltaProduct based linear RNN.
The open-source release includes 5M to 209M parameter checkpoints supporting zero-shot forecasting with up to 32,768 historical time steps.
The new Cassandra-based cold tier stores over 15 PB of data and reduces disk usage from 80% to 7% while maintaining sub-500ms p99 latency.
The paper demonstrates that a piecewise affine map with a single parameter and a context selector can reproduce major dynamical regimes and outperform larger foundation models in zero-shot settings.
IBM has released Granite PatchTST-FM-r2, a time series foundation model licensed under Apache 2.0.
IBM and Confluent have released the IBM Granite time-series foundation model in Early Access, operating within real-time streaming environments based on Apache Flink.
Amazon Connect Decisions introduces an agentic demand forecasting approach that automates everything from SKU-level pattern diagnosis to model orchestration.
Bidirectional diffusion models estimate rollout errors using forward-backward round-trip discrepancies.
This introduces deep learning-based anomaly detection technology and the latest research that learns complex patterns in time series data to detect abnormal data.
This piece examines the concept of foundation models for handling time series data and their classification based on how they utilize LLMs.
This introduces the latest research methodologies of Foundation models for tackling time series data, classified according to how they utilize LLMs.
Datadog announced Toto-2.0, a new time-series forecasting model capable of parallel processing and highly scalable.
A research paper has been published arguing that a Dynamical Systems Reconstruction (DSR) perspective should be adopted to overcome the limitations of time series modeling.
Forgis Labs has unveiled a world model framework that understands and predicts the dynamics of physical systems using time series sensor data.
To solve the wide partition problem that occurs in Cassandra when processing time-series data, Netflix introduced a technique to dynamically split partitions.
Different temporal resolutions of PPG better predict different health outcomes.
This explains the structure of PatchTST, a model that improves time-series forecasting performance, and how to use it with the Hugging Face library.
IBM Research's lightweight time series model PatchTSMixer has been integrated into the HuggingFace Transformers library.
The transformer-based model Autoformer has proven superior to the simple linear model DLinear in time series forecasting performance.
Kurly's Data Science Team shared operational principles for demand forecasting models and leakage prevention techniques.