368 citations · 582 across the 18 of their papers we have counts for
20 papers
PathFM: Fast Generative Forecasting of Multivariate Trajectories
Jiachen Yao, Xiyuan Zhang, Annan Yu +5
Time series foundation models are becoming increasingly popular for general-purpose forecasting. However, most leading models predict marginal quantiles, leaving the dependence str…
TCSAlgBench: Benchmarking Automated Proving for Research-Level Theoretical Computer Science
Chutong Yang, Xiyuan Zhang, Yu Huang +7
Large language models perform strongly on competition mathematics, but their research-level reasoning remains difficult to evaluate systematically. Theoretical computer science (TC…
Mitra-v2 Technical Report
Yefan Tao, Xiyuan Zhang, Xinyi Liu +13
We introduce Mitra-v2, a tabular foundation model that delivers state-of-the-art performance on real-world classification and regression problems, from credit-risk scoring and clin…
Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning
Nathanaël Carraz Rakotonirina, Ren Pang, Neha Anna John +2
The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known a…
Multi-layer Stack Ensembles for Time Series Forecasting
Nathanael Bosch, Oleksandr Shchur, Nick Erickson +2
Ensembling is a powerful technique for improving the accuracy of machine learning models, with methods like stacking achieving strong results in tabular tasks. In time series forec…
Chronos-2: From Univariate to Universal Forecasting
Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken +20
Pretrained time series models have enabled inference-only forecasting systems that produce accurate predictions without task-specific training. However, existing approaches largely…
Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting
Mert Kayaalp, Caner Turkmen, Oleksandr Shchur +4
Is bigger always better for time series foundation models? With the question in mind, we explore an alternative to training a single, large monolithic model: building a portfolio o…
fev-bench: A Realistic Benchmark for Time Series Forecasting
Oleksandr Shchur, Abdul Fatir Ansari, Caner Turkmen +5
Benchmark quality is critical for meaningful evaluation and sustained progress in time series forecasting, particularly with the rise of pretrained models. Existing benchmarks ofte…
Zero-Shot Time Series Forecasting with Covariates via In-Context Learning
Andreas Auer, Raghul Parthipan, Pedro Mercado +5
Pretrained time series models, capable of zero-shot forecasting, have demonstrated significant potential in enhancing both the performance and accessibility of time series forecast…
ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables
Sebastian Pineda Arango, Pedro Mercado, Shubham Kapoor +10
Covariates provide valuable information on external factors that influence time series and are critical in many real-world time series forecasting tasks. For example, in retail, co…
Chronos: Learning the Language of Time Series
Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen +15
We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a f…
Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
Marcel Kollovieh, Abdul Fatir Ansari, Michael Bohlke-Schneider +3
Diffusion models have achieved state-of-the-art performance in generative modeling tasks across various domains. Prior works on time series diffusion models have primarily focused…
Adaptive Sampling for Probabilistic Forecasting under Distribution Shift
Luca Masserano, Syama Sundar Rangapuram, Shubham Kapoor +3
The world is not static: This causes real-world time series to change over time through external, and potentially disruptive, events such as macroeconomic cycles or the COVID-19 pa…
Criteria for Classifying Forecasting Methods
Tim Januschowski, Jan Gasthaus, Yuyang Wang +4
Classifying forecasting methods as being either of a "machine learning" or "statistical" nature has become commonplace in parts of the forecasting literature and community, as exem…
Intrinsic Anomaly Detection for Multi-Variate Time Series
Stephan Rabanser, Tim Januschowski, Kashif Rasul +6
We introduce a novel, practically relevant variation of the anomaly detection problem in multi-variate time series: intrinsic anomaly detection. It appears in diverse practical sce…
Resilient Neural Forecasting Systems
Michael Bohlke-Schneider, Shubham Kapoor, Tim Januschowski
Industrial machine learning systems face data challenges that are often under-explored in the academic literature. Common data challenges are data distribution shifts, missing valu…
PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series
Jeha Paul, Bohlke-Schneider Michael, Mercado Pedro +5
Realistic synthetic time series data of sufficient length enables practical applications in time series modeling tasks, such as forecasting, but remains a challenge. In this paper…
Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
Konstantinos Benidis, Syama Sundar Rangapuram, Valentin Flunkert +10
Deep learning based forecasting methods have become the methods of choice in many applications of time series prediction or forecasting often outperforming other approaches. Conseq…
High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes
David Salinas, Michael Bohlke-Schneider, Laurent Callot +2
Predicting the dependencies between observations from multiple time series is critical for applications such as anomaly detection, financial risk management, causal analysis, or de…
GluonTS: Probabilistic Time Series Models in Python
Alexander Alexandrov, Konstantinos Benidis, Michael Bohlke-Schneider +10
We introduce Gluon Time Series (GluonTS, available at https://gluon-ts.mxnet.io), a library for deep-learning-based time series modeling. GluonTS simplifies the development of and…