10 papers
Dynamical Parameters: An Interpretability Framework for Time-Series Foundation Models
Kang Yang, Gaofeng Dong, Liying Han +1
This work studies a central gap in interpreting time-series foundation models (TSFMs): a dynamical property may be accessible in a hidden state even when the forecast fails to resp…
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…
RxGS: Receiver-Generalizable 3D Gaussian Splatting for Radio-Frequency Data Synthesis
Kang Yang, Mani Srivastava
Radio-frequency (RF) data synthesis predicts the received signal given transmitter and receiver positions, and is essential for wireless applications. Recent 3D Gaussian Splatting…
FuseFi: Combining Irregularly Sampled CSI from Diverse Communication Packets and Frequency Bands for Wi-Fi Sensing
Gaofeng Dong, Kang Yang, Mani Srivastava
Existing Wi-Fi sensing systems rely on injecting high-rate probing packets to extract channel state information (CSI), leading to communication degradation and limited deployment f…
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…
CarbonX: An Open-Source Tool for Computational Decarbonization Using Time Series Foundation Models
Diptyaroop Maji, Kang Yang, Prashant Shenoy +2
Computational decarbonization aims to reduce carbon emissions in computing and societal systems such as data centers, transportation, and built environments. This requires accurate…
Surya: Foundation Model for Heliophysics
Sujit Roy, Johannes Schmude, Rohit Lal +30
Heliophysics is central to understanding and forecasting space weather events and solar activity. Despite decades of high-resolution observations from the Solar Dynamics Observator…
An Efficient Private GPT Never Autoregressively Decodes
Zhengyi Li, Yue Guan, Kang Yang +5
The wide deployment of the generative pre-trained transformer (GPT) has raised privacy concerns for both clients and servers. While cryptographic primitives can be employed for sec…
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…
ADMN: A Layer-Wise Adaptive Multimodal Network for Dynamic Input Noise and Compute Resources
Jason Wu, Yuyang Yuan, Kang Yang +2
Multimodal deep learning systems are deployed in dynamic scenarios due to the robustness afforded by multiple sensing modalities. Nevertheless, they struggle with varying compute r…