PatchTST
PulseAugur coverage of PatchTST — every cluster mentioning PatchTST across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
Deep learning architectures rigorously benchmarked for financial forecasting · 2 sources tracked
Two research papers explore the application and evaluation of deep learning models for financial forecasting. The first paper introduces FinForesight, a diagnostic benchmark designed to rigorously test deep research sys…
-
GateTS model simplifies time-series forecasting with efficient MoE architecture
Researchers have introduced GateTS, a novel architecture for time-series forecasting that simplifies training and enhances efficiency. This model utilizes a sparse Mixture-of-Experts (MoE) approach with an attention-ins…
-
Spectral Predictability Insufficient for Synthetic Pretraining Under Distribution Shift
A new research paper explores the effectiveness of spectral predictability ($\Omega$) matching for synthetic pretraining in machine learning models, particularly under distribution shift. While $\Omega$-matched pretrain…
-
New DRiC method improves online residual correction for forecasters
Researchers have developed DRiC (DCT Ridge Corrector), a novel method for online residual correction of frozen multivariate forecasters, particularly effective under label delay conditions. DRiC aims to minimize retaine…
-
Mistral AI releases Timestral time-series models outperforming Google
Mistral AI has launched Timestral, a new family of four time-series foundation models, with the largest boasting 209 million parameters. These models achieve state-of-the-art performance on key benchmarks like GIFT-Eval…
-
FANTF: Fuzzy attention enhances transformer models for time series analysis
Researchers have introduced FANTF, a novel approach that integrates fuzzy logic with transformer architectures for enhanced time series analysis. This method employs a fuzzy attention mechanism, inspired by Type-2 fuzzy…
-
Deep learning models outperform statistical methods in used electronics price forecasting
A new benchmark study systematically compares deep learning and statistical models for forecasting the resale prices of used electronics. Researchers found that the N-BEATS deep learning architecture significantly outpe…
-
Univariate Deep Learning Models Show Diminishing Returns for Wave Height Forecasting
A new arXiv paper explores the limitations of univariate deep learning models for forecasting significant wave height (Hs). The study found that while models like DLinear, LSTM, PatchTST, ResAttLstm, and Mamba2 can outp…
-
New EPOC method improves time series forecasting with compressed state
Researchers have developed a new method called Endpoint-Preserving Online Correction (EPOC) for multi-horizon time series forecasting. EPOC addresses the challenge of retaining residual feedback without excessive state …
-
New MoE framework enhances time series forecasting with integrated expert losses
Researchers have developed a new Mixture-of-Experts (MoE) framework for time series forecasting that improves training efficiency and predictive performance. This framework integrates expert-specific losses directly int…
-
Foundation models show mixed results for pedestrian crowd forecasting
A new study published on arXiv evaluates the effectiveness of time-series foundation models (FMs) for pedestrian crowd count forecasting. The research compares seven different forecasting approaches, including tradition…
-
New JEPA model tackles cross-machine industrial AI transfer
Researchers have developed a Schema-Adaptive Action-Conditioned JEPA (SAAC-JEPA) designed for transferring industrial world models between different CNC machines. This model addresses challenges like differing dynamics,…
-
Foundation models require fine-tuning for diabetes glucose forecasting
A new study published on arXiv evaluates the effectiveness of time-series foundation models for continuous glucose monitoring (CGM) forecasting, particularly for individuals with type 1 and type 2 diabetes. The research…
-
New augmentation technique boosts multivariate forecasting models
Researchers have developed a novel time-domain augmentation technique for multivariate forecasting models. This method, called Sliding-Window Reordering with Overlap Averaging, involves unfolding sequences into overlapp…
-
New research details online adaptation for edge time-series forecasting
A new research paper published on arXiv explores the effectiveness of online adaptation techniques for time-series forecasting on edge devices. The study highlights how evaluation methodologies, such as warmup budgets a…
-
Neuro-symbolic framework predicts academic risk with interpretable AI
Researchers have developed EduRiskX, a novel neuro-symbolic framework designed to predict academic risk in online education. This system combines a Transformer-based neural network for analyzing student activity sequenc…
-
New benchmark improves AI-driven anomaly detection for research networks
Researchers have developed a new forecasting framework to improve anomaly detection in research networks, which often struggle with distinguishing legitimate high-traffic scientific bursts from malicious attacks. Using …
-
New ESN techniques boost time-series forecasting efficiency and accuracy
Researchers have developed new methods for improving Echo State Networks (ESNs), a type of reservoir computing model efficient for time-series forecasting. One approach, Dynamical Mode Pruning (DMP), refines ESNs by ran…
-
LithoFormer uses transformers for robust geological stratigraphic inference
Researchers have developed LithoFormer, a novel framework for stratigraphic inference in geological well log data. This system utilizes a Seq2Seq transformer model, specifically a PatchTST backbone with rotary positiona…
-
New research tackles explainability and adaptation in continual time series forecasting
Two new research papers explore the challenges and solutions for continual learning in time series forecasting models. The first paper introduces an attention-based experience replay framework to help models adapt to ch…