collaborators

6 papers

cs.LG2026

SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning

Zelin He, Boran Han, Xiyuan Zhang +10

Time-series diagnostic reasoning is essential for many applications, yet existing solutions face a persistent gap: general reasoning large language models (GRLMs) possess strong re…

cs.LG2026

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…

cs.LG2025

Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models

Xiyuan Zhang, Danielle C. Maddix, Junming Yin +11

Since the seminal work of TabPFN, research on tabular foundation models (TFMs) based on in-context learning (ICL) has challenged long-standing paradigms in machine learning. Withou…

cs.CL2025

When Does Multimodality Lead to Better Time Series Forecasting?

Xiyuan Zhang, Boran Han, Haoyang Fang +11

Recently, there has been growing interest in incorporating textual information into foundation models for time series forecasting. However, it remains unclear whether and under wha…

cs.LG2025

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…

cs.LG2025

Gradient-Free Generation for Hard-Constrained Systems

Chaoran Cheng, Boran Han, Danielle C. Maddix +4

Generative models that satisfy hard constraints are critical in many scientific and engineering applications, where physical laws or system requirements must be strictly respected.…