6 papers
TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering
Liying Han, Kang Yang, Oliver Wang +9
Large language models (LLMs) and time-series language models (TSLMs) are increasingly applied to time-series question answering (TSQA). Unlike text-only QA, TSQA requires models to…
Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges
Pengrui Quan, Brian Wang, Kang Yang +2
Spatiotemporal reasoning plays a key role in Cyber-Physical Systems (CPS). Despite advances in Large Language Models (LLMs) and Large Reasoning Models (LRMs), their capacity to rea…
Spectral Predictability as a Fast Reliability Indicator for Time Series Forecasting Model Selection
Oliver Wang, Pengrui Quan, Kang Yang +1
Practitioners deploying time series forecasting models face a dilemma: exhaustively validating dozens of models is computationally prohibitive, yet choosing the wrong model risks p…
Can Time-Series Foundation Models Perform Building Energy Management Tasks?
Ozan Baris Mulayim, Pengrui Quan, Liying Han +4
Building energy management (BEM) tasks require processing and learning from a variety of time-series data. Existing solutions rely on bespoke task- and data-specific models to perf…
SensorBench: Benchmarking LLMs in Coding-Based Sensor Processing
Pengrui Quan, Xiaomin Ouyang, Jeya Vikranth Jeyakumar +3
Effective processing, interpretation, and management of sensor data have emerged as a critical component of cyber-physical systems. Traditionally, processing sensor data requires p…
Foundation Models for CPS-IoT: Opportunities and Challenges
Ozan Baris, Yizhuo Chen, Gaofeng Dong +9
Methods from machine learning (ML) have transformed the implementation of Perception-Cognition-Communication-Action loops in Cyber-Physical Systems (CPS) and the Internet of Things…