9 papers
Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting
Chen Su, Yuanhe Tian, Yan Song
Diffusion models have become a widely used framework for probabilistic time series forecasting, modeling the distribution of future values given an observed history. In time series…
SURGE: An Event-Centric Social Media Sentiment Time Series Benchmark with Interaction Structure
Chen Su, Pengsen Cheng, Yuanhe Tian +1
Public events on social media generate large volumes of discussion whose collective dynamics carry direct value for opinion forecasting and crisis response. Capturing how these dyn…
Chain-of-thought Reviewing and Correction for Time Series Question Answering
Chen Su, Yuanhe Tian, Yan Song
With the advancement of large language models (LLMs), diverse time series analysis tasks are reformulated as time series question answering (TSQA) through a unified natural languag…
LogICL: Demonstration Retrieval to Bridge the Semantic Gap in Cross-Domain Log Anomaly Detection
Jingwei Ye, Zhi Wang, Chenbin Su +4
Effective log anomaly detection is critical to sustaining reliability in large-scale IT infrastructures. Transformer-based language models have advanced the field but require subst…
Text Reinforcement for Multimodal Time Series Forecasting
Chen Su, Yuanhe Tian, Yan Song +1
Recent studies in time series forecasting (TSF) use multimodal inputs, such as text and historical time series data, to predict future values. These studies mainly focus on develop…
Diffusion Models for Time Series Forecasting: A Survey
Chen Su, Zhengzhou Cai, Yuanhe Tian +3
Diffusion models, initially developed for image synthesis, demonstrate remarkable generative capabilities. Recently, their application has expanded to time series forecasting (TSF)…
Fusing Large Language Models with Temporal Transformers for Time Series Forecasting
Chen Su, Yuanhe Tian, Qinyu Liu +2
Recently, large language models (LLMs) have demonstrated powerful capabilities in performing various tasks and thus are applied by recent studies to time series forecasting (TSF) t…
Computed Tomography Visual Question Answering with Cross-modal Feature Graphing
Yuanhe Tian, Chen Su, Junwen Duan +1
Visual question answering (VQA) in medical imaging aims to support clinical diagnosis by automatically interpreting complex imaging data in response to natural language queries. Ex…
Multimodal Conditioned Diffusive Time Series Forecasting
Chen Su, Yuanhe Tian, Yan Song
Diffusion models achieve remarkable success in processing images and text, and have been extended to special domains such as time series forecasting (TSF). Existing diffusion-based…