AINeutralarXiv – CS AI · May 116/10
🧠TSRBench introduces a comprehensive benchmark with 4,125 problems across 14 domains to evaluate how well AI models perform at time series reasoning tasks. Testing 30+ leading models reveals that current LLMs and multimodal models struggle with numerical forecasting despite strong semantic understanding, and fail to effectively combine textual and visual data inputs.
AINeutralarXiv – CS AI · May 96/10
🧠Researchers introduce CatNet, an algorithm that controls False Discovery Rate (FDR) in LSTM neural networks by combining SHAP feature importance derivatives with a Gaussian Mirror statistical approach. The method addresses overfitting and model interpretability challenges in time-series deep learning through improved feature selection and a novel kernel-based independence measure.
AINeutralarXiv – CS AI · May 76/10
🧠Researchers applied mechanistic interpretability tools to analyze how transformer models process time series data, discovering that these models don't rely on superposition—a complex representational technique crucial to their NLP success. The findings explain why simpler linear models remain competitive for forecasting and suggest transformers may be overengineered for standard time series benchmarks.
AI × CryptoBullisharXiv – CS AI · Apr 206/10
🤖Researchers propose using Conditional Generative Adversarial Networks (CGANs) to generate synthetic cryptocurrency price data, addressing privacy and access concerns in financial research. The approach combines LSTM generators with MLP discriminators to produce statistically consistent synthetic time series that preserve market dynamics, offering a computationally efficient alternative for financial modeling and analysis.
AIBearisharXiv – CS AI · Mar 176/10
🧠Researchers introduce HEARTS, a comprehensive benchmark for evaluating large language models' ability to reason over health time series data across 16 datasets and 12 health domains. The study reveals that current LLMs significantly underperform compared to specialized models and struggle with multi-step temporal reasoning in healthcare applications.
AIBearisharXiv – CS AI · Mar 96/10
🧠Researchers conducted a controlled study examining the effectiveness of large language models (LLMs) for time series forecasting, finding that existing approaches often overfit to small datasets. Despite some promise, LLMs did not consistently outperform models specifically trained on large-scale time series data.
AINeutralarXiv – CS AI · Mar 45/103
🧠Researchers have developed FinTexTS, a new large-scale dataset that pairs financial news with stock price data using semantic matching and multi-level categorization. The framework uses embedding-based matching and LLMs to classify news into four levels (macro, sector, related company, and target company) for improved stock price forecasting accuracy.
AINeutralarXiv – CS AI · Mar 36/107
🧠Researchers developed an event-based evaluation framework for LLM-generated clinical summaries of remote monitoring data, revealing that models with high semantic similarity often fail to capture clinically significant events. A vision-based approach using time-series visualizations achieved the best clinical event alignment with 45.7% abnormality recall.
$NEAR
AINeutralarXiv – CS AI · Mar 37/106
🧠Researchers introduce StaTS, a new diffusion model for time series forecasting that learns adaptive noise schedules and uses frequency-guided denoising. The model addresses limitations of fixed noise schedules in existing diffusion models by incorporating spectral regularization and data-adaptive scheduling for improved structural preservation.
$NEAR
AIBullisharXiv – CS AI · Mar 36/107
🧠Researchers have developed Thoth, the first family of Large Language Models specifically designed to understand and reason about time series data through a mid-training approach. The model uses a specialized corpus called Book-of-Thoth to bridge the gap between temporal data and natural language, significantly outperforming existing LLMs in time series analysis tasks.
AIBullisharXiv – CS AI · Mar 36/108
🧠Researchers developed a deep learning framework using Continuous Wavelet Transform and CNNs for heat demand forecasting in district heating systems. The model achieved 36-43% reduction in forecasting errors compared to existing methods, reaching up to 95% accuracy in predicting day-ahead heat demand across multiple European cities.
AIBullisharXiv – CS AI · Mar 36/104
🧠Researchers have developed RawMed, the first framework to generate synthetic multi-table time-series Electronic Health Records (EHR) that closely resembles raw medical data. The system addresses privacy concerns in healthcare data sharing while maintaining fidelity and utility, outperforming baseline models in validation tests.
AIBullisharXiv – CS AI · Mar 36/102
🧠Researchers present a systematic study of linear models for time series forecasting, focusing on characteristic roots in temporal dynamics and introducing two regularization strategies (Reduced-Rank Regression and Root Purge) to address noise-induced spurious roots. The work achieves state-of-the-art results by combining classical linear systems theory with modern machine learning techniques.
AIBullisharXiv – CS AI · Feb 276/106
🧠Researchers have developed PATRA, a new AI model that improves time series question answering by better understanding patterns like trends and seasonality. The model addresses limitations in existing LLM approaches that treat time series data as simple text or images, introducing pattern-aware mechanisms and balanced learning across tasks of varying difficulty.
AIBullishGoogle Research Blog · Sep 236/105
🧠The article discusses advancements in time series foundation models and their capability for few-shot learning in generative AI applications. These models can learn patterns from limited data samples, potentially improving forecasting and prediction tasks across various domains.
AIBullishHugging Face Blog · Jun 166/108
🧠The article appears to discuss the effectiveness of Transformer models for time series forecasting, specifically mentioning Autoformer architecture. However, the article body content was not provided in the input.
AIBullishHugging Face Blog · Dec 16/107
🧠The article discusses probabilistic time series forecasting using Hugging Face Transformers, a machine learning approach for predicting future data points with uncertainty estimates. This technique has applications in financial markets, including cryptocurrency price prediction and risk assessment.
AINeutralarXiv – CS AI · Apr 75/10
🧠Researchers propose FeDPM, a federated learning framework that addresses semantic misalignment issues when using Large Language Models for time series analysis. The system uses discrete prototypical memories to better handle cross-domain time-series data while preserving privacy in distributed settings.
AINeutralarXiv – CS AI · Mar 174/10
🧠Researchers have developed SyMPLER, an explainable AI model for time series forecasting that uses dynamic piecewise-linear approximations to handle nonstationary environments. The model automatically determines when to add new local models based on prediction errors using Statistical Learning Theory, achieving comparable performance to black-box models while maintaining interpretability.
AINeutralarXiv – CS AI · Mar 54/10
🧠Researchers introduce PatchDecomp, a new neural network method for time series forecasting that achieves high accuracy while providing interpretable explanations. The method divides time series into patches and shows how each patch contributes to predictions, offering both quantitative and visual insights into forecasting decisions.
AINeutralarXiv – CS AI · Mar 35/104
🧠Researchers developed UTICA, a new foundation model for time series classification that uses non-contrastive self-distillation methods adapted from computer vision. The model achieves state-of-the-art performance on UCR and UEA benchmarks by learning temporal patterns through a student-teacher framework with data augmentation and patch masking.
AINeutralarXiv – CS AI · Mar 34/104
🧠Researchers introduce HGTS-Former, a novel hierarchical hypergraph Transformer architecture for analyzing multivariate time series data. The system uses hypergraphs to model complex variable interactions and demonstrates state-of-the-art performance on multiple datasets, including a new nuclear fusion dataset for Edge-Localized Mode recognition.
AINeutralarXiv – CS AI · Feb 274/105
🧠Researchers developed TokEye, a self-supervised AI framework that can extract coherent signals from noisy time-series data in 0.5 seconds, initially designed for fusion reactor diagnostics. The system demonstrates applications beyond fusion research, including bioacoustics, suggesting broader potential for real-time signal processing across industries.
AINeutralHugging Face Blog · Mar 104/103
🧠The article discusses the Informer model for multivariate probabilistic time series forecasting, which is a machine learning approach designed to handle complex temporal data with multiple variables. This type of forecasting technology has potential applications in financial markets, including cryptocurrency trading and risk management.
AINeutralarXiv – CS AI · Mar 34/107
🧠A research study compares econometric methods versus causal machine learning algorithms for analyzing time-series data to inform policy decisions, using UK COVID-19 policies as a case study. The research evaluates four econometric methods against eleven causal ML algorithms, finding that econometric methods provide clearer temporal structure rules while causal ML algorithms explore broader graph structures to capture more causal relationships.
