TSFM
PulseAugur coverage of TSFM — every cluster mentioning TSFM across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New CoCo framework merges LLMs and TSFMs for improved time series forecasting
Researchers have developed a novel forecasting framework called Context as Covariates (CoCo) that integrates Large Language Models (LLMs) with Time Series Foundation Models (TSFMs). This approach addresses the limitatio…
-
TSFM carbon footprint analyzed; pruning offers emissions reduction
A new research paper explores the sustainability of Time Series Foundation Models (TSFMs), specifically analyzing their carbon footprint during pretraining and deployment. The study found that while TSFMs like Chronos-2…
-
Covariance-Aware Transformers Tackle Quadratic Programming for Decision Making
Researchers have developed a novel approach using transformers to solve quadratic programming (QP) problems, which are crucial for decision-making tasks involving covariance matrices. The proposed method, called Time2De…
-
New benchmark GIFT-Eval-CTX boosts LLM forecasting accuracy
Researchers have introduced GIFT-Eval-CTX, a new benchmark designed to evaluate contextual forecasting models by assessing their ability to use verified future information. This benchmark, built upon GIFT-Eval, includes…
-
ChronoScribe system separates LLM interpretation from time series forecasting
Researchers have developed ChronoScribe, a novel system for instruction-driven time series forecasting that separates natural language understanding from numerical prediction. The system uses a LoRA-adapted LLM to inter…
-
Align-RAG method enhances TSFMs without training, outperforming fusion modules
Researchers have introduced Align-RAG, a novel training-free method for enhancing Time Series Foundation Models (TSFMs) through retrieval-augmented forecasting. Unlike previous approaches that relied on learned fusion m…
-
TelcoAgent framework enhances 5G network forecasting with explainable AI
Researchers have developed TelcoAgent, a novel framework designed to improve the forecasting of Key Performance Measurements (KPMs) in 5G and future telecom networks. This foundation model-based system addresses limitat…
-
New AI methods enhance time series forecasting accuracy and interpretability
Researchers have introduced several new methods for time-series forecasting, aiming to improve accuracy and generalization. MeLISA, a latent-free autoregressive model, enhances rollout efficiency and long-horizon statis…
-
Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models
Researchers have developed a method to make Time Series Foundation Models (TSFMs) more transparent for critical infrastructure applications like power grids. Their approach uses Shapley Additive Explanations (SHAP) to e…
-
AI models forecast university enrollments even with sparse data
This paper introduces a framework using zero-shot Time Series Foundation Models (TSFMs) to forecast university enrollments, particularly when historical data is scarce or disrupted by structural changes. The researchers…