DC
Defu Cao
cs.LGcs.AIcs.CLstat.MLcs.CYDeep LearningAnomaly detectionArtificial IntelligenceAttentionBenchmarking
On Valency
published · living versionsW_sp6hm735·v1 · currentpublished
PersonaChatBench: Evaluating Chat Assistants with Diverse Simulated Users
with Zheyuan Deng, Taoran Li, Jingwen Zhang, Yuante Li +26
1 version
Preprints & journals
31 papers in the corpus · 2020–2026PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas2610.22990v1 · Haoming Li, Defu Cao, Xu Hu et al.2026 · 0 citationsarXiv
Measuring Effective Data Resolution in Guided Diffusion Posteriors2610.04422v1 · Ridham Patel, Defu Cao, Jiacheng Pang et al.2026 · 0 citationsarXiv
Trustworthy Protein-Ligand Binding Affinity Prediction via Reliability-Aware Multi-Engine Fusion2607.17601v1 · Yongchan Hong, Defu Cao, Wenjin Liu et al.2026 · 0 citationsKDD '2026: Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2
TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks2602.13272v1 · Muyan Weng, Defu Cao, Wei Yang et al.2026 · 1 citationarXiv
Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs2512.04668v4 · Jinbo Liu, Defu Cao, Yifei Wei et al.2025 · 0 citationsarXiv
A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models2509.11575v3 · Ching Chang, Yidan Shi, Defu Cao et al.2025 · 0 citationsarXiv
When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference2509.01822v1 · Wen Ye, Jinbo Liu, Defu Cao et al.2025 · 0 citationsarXiv
M3OOD: Automatic Selection of Multimodal OOD Detectors2508.11936v2 · Yuehan Qin, Li Li, Defu Cao et al.2025 · 0 citationsarXiv
An Electrocardiogram Multi-Task Benchmark with Comprehensive Evaluations and Insightful Findings.40776054 · Xu, Yuhao, Lu, Jiaying, Ding, Sirui et al.2025 · 0 citationsStudies in health technology and informatics. 2025;329:1235-1240
MultiverseAD: Enhancing spatial-temporal synchronous attention networks with causal knowledge for multivariate time series anomaly detection.40773781 · Jia, Xudong, Cao, Defu, Zhuang, Niangxi et al.2025 · 7 citationsNeural networks : the official journal of the International Neural Network Society. 2025;192:107903
Creating a Cooperative AI Policymaking Platform through Open Source Collaboration2412.06936v1 · Aiden Lewington, Alekhya Vittalam, Anshumaan Singh et al.2024 · 1 citationarXiv
Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based Inference2412.05590v1 · Sam Griesemer, Defu Cao, Zijun Cui et al.2024 · 3 citationsarXiv
TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis2410.04047v6 · Wen Ye, Wei Yang, Defu Cao et al.2024 · 0 citationsarXiv
TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model2409.02322v2 · Defu Cao, Wen Ye, Yizhou Zhang et al.2024 · 3 citationsarXiv
An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series2408.08815v1 · Qiang Huang, Chuizheng Meng, Defu Cao et al.2024 · 0 citationsarXiv
MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification2406.19832v1 · Tianjun Yao, Jiaqi Sun, Defu Cao et al.2024 · 12 citationsarXiv
Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning2404.09403v2 · Xiongye Xiao, Gengshuo Liu, Gaurav Gupta et al.2024 · 10 citationsarXiv
Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models2402.09099v7 · Xiongye Xiao, Heng Ping, Chenyu Zhou et al.2024 · 1 citationarXiv
An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models2402.05359v6 · Yizhou Zhang, Lun Du, Defu Cao et al.2024 · 2 citationsarXiv
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting2310.04948v3 · Defu Cao, Furong Jia, Sercan O Arik et al.2023 · 59 citationsarXiv
Neuro-Inspired Hierarchical Multimodal Learning2309.15877v3 · Xiongye Xiao, Gengshuo Liu, Gaurav Gupta et al.2023 · 1 citationarXiv
Interpretable Detection of Out-of-Context Misinformation with Neural-Symbolic-Enhanced Large Multimodal Model2304.07633v2 · Yizhou Zhang, Loc Trinh, Defu Cao et al.2023 · 15 citationsarXiv
Coupled Multiwavelet Neural Operator Learning for Coupled Partial Differential Equations2303.02304v5 · Xiongye Xiao, Defu Cao, Ruochen Yang et al.2023 · 3 citationsarXiv
Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders2303.02320v1 · Defu Cao, James Enouen, Yujing Wang et al.2023 · 12 citationsarXiv
Estimating Treatment Effects in Continuous Time with Hidden Confounders2302.09446v2 · Defu Cao, James Enouen, Yan Liu2023 · 0 citationsarXiv
DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift2211.11513v1 · Defu Cao, Yousef El-Laham, Loc Trinh et al.2022 · 1 citationarXiv
Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media2210.07518v1 · Yizhou Zhang, Defu Cao, Yan Liu2022 · 8 citationsarXiv
When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning2203.16797v1 · Chuizheng Meng, Sungyong Seo, Defu Cao et al.2022 · 282 citationsarXiv
Spectral Temporal Graph Neural Network for Trajectory Prediction2106.02930v1 · Defu Cao, Jiachen Li, Hengbo Ma et al.2021 · 79 citationsarXiv
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting2103.07719v1 · Defu Cao, Yujing Wang, Juanyong Duan et al.2021 · 388 citationsarXiv
Multivariate Time-series Anomaly Detection via Graph Attention Network2009.02040v1 · Hang Zhao, Yujing Wang, Juanyong Duan et al.2020 · 845 citationsarXiv
Career total: 46 works. 31 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.