Wenbo Hu's Homepage – Publications

Revisiting PCA for time series reduction in temporal dimension.
Jiaxin Gao, Wenbo Hu, Yuntian Chen
[arXiv]

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage.
Xiaoning Dong, Wenbo Hu, Wei Xu, Tianxing He
[arXiv]

Deep Ensembles Meets Quantile Regression: Uncertainty-aware Imputation for Time Series.
Ying Liu, Peng Cui, Wenbo Hu, Richang Hong
[arXiv]

Uncertainty Calibration for Counterfactual Propensity Estimation in Recommendation.
Wenbo Hu+, Xin Sun+, Qiang liu, Le Wu, Liang Wang.
[arXiv] [Code]

Dynamic Window-level Granger Causality of Multi-channel Time Series
Zhiheng Zhang, Wenbo Hu and Jun Zhu.
[arXiv]

Revealing Security Flaws in Cross-Modal Retrieval Models through Video Poisoning.
Ming Jin+, Wenbo Hu+, Richang Hong, Lei Zhu.
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.
[paper]

Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-training Models with Contrastive Learning.
Youze Wang, Wenbo Hu, Yinpeng Dong, Hanwang Zhang, Hang Su, Richang Hong.
To appear in IEEE Transactions on Multimedia(TMM), 2025.
[arXiv]

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
Youze Wang, Wenbo Hu, Yinpeng Dong, Jing Liu, Hanwang Zhang, Richang Hong.
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.
[paper] [code]

Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models
Zijun Chen+, Wenbo Hu+, Guande He, Zhijie Deng, Zheng Zhang and Richang Hong.
The 31st International Conference on Computational Linguistics (Coling), 2025.
[arxiv] [Code]

Making strides Security in Multimodal Fake News Detection Models: A Comprehensive Analysis of Adversarial Attacks
Jiahua Si, Youze Wang, Wenbo Hu, Qiang Liu, Richang Hong.
International Conference on MultiMedia Modeling (MMM), 2025.
[paper]

Conformalized Graph Learning for Molecular ADMET Property Prediction and Reliable Uncertainty Quantification
Peiyao Li, Lan Hua, Zhechao Ma, Wenbo Hu, Ye Liu, Jun Zhu.
Journal of Chemical Information and Modeling, 2024.
[paper] [Code]

Accurate and Reliable Forecasting using Stochastic Differential Equations
Peng Cui, Zhijie Deng, Wenbo Hu and Jun Zhu.
ACM Transactions on Knowledge Discovery from Data (TKDD), in press.
[paper]

AtomTool: Empowering Large Language Models with Tool Utilization Skills.
Yongle Li, Zheng Zhang, Junqi Zhang, Wenbo Hu, Yongyu Wu, Richang Hong
Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2024.

Based on Spatial and Temporal Implicit Semantic Relational Inference for Cross-Modal Retrieval.
Ming Jin, Wenbo Hu, Lei Zhu, Xiang Wang, Richang Hong
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024.
[paper]

A dilated convolution based method with time series fine tuning for data-driven crack length estimation.
Jiaxin Gao+, Wenbo Hu+, Qinan Han, Yuntian Chen, Richang Hong, Huiji Shi
Fatigue & Fracture of Engineering Materials & Structures, 2024.
[paper]

Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting.
Guande He, Peng Cui, Jianfei Chen, Wenbo Hu, Jun Zhu
ICLR 2024 Workshop ME-FoMo
[arXiv]

How to Use Language Expert to Assist Inference for Visual Commonsense Reasoning.
Zijie Song+, Wenbo Hu+, Hao Ye, and Richang Hong.
ICDM 2023 International Workshop on Learning with Knowledge Graphs.
[paper]

Client: Cross-variable Linear Integrated Enhanced Transformer for Multivariate Long-Term Time Series Forecasting.
Jiaxin Gao, Wenbo Hu, Yuntian Chen.
KDD 2023 Workshop on Mining and Learning from Time Series (KDD’23-MiLeTS)
[arXiv] [Code]

Iterative Adversarial Attack on Image-guided Story Ending Generation.
Youze Wang, Wenbo Hu, Richang Hong.
IEEE Transactions on Multimedia, 2023.
[paper] [arXiv] [Code]

Physics-Guided Discovery of Highly Nonlinear Parametric Partial Differential Equations .
Yingtao Luo, Qiang Liu, Yuntian Chen, Wenbo Hu, Tian Tian, Jun Zhu.
ACM SIGKDD conference on data science and data mining (KDD), 2023.
[paper] [arXiv]
A preliminary version presented in NeurIPS 2022 Workshop AI4Science.

An Adaptive Deep-learning Load Forecasting Framework by Integrating Transformer and Domain Knowledge.
Jiaxin Gao, Yuntian Chen, Wenbo Hu, Dongxiao Zhang.
Advances in Applied Energy, 2023.
[paper] [Code]

Stacking VAE with Graph Neural Networks for Effective and Interpretable Time Series Anomaly Detection.
Wenkai Li, Wenbo Hu, Ting Chen, Ning Chen, Cheng Feng. AI Open, 2022.
[paper] [arXiv] [Code]

TgDLF2.0: Theory-guided deep-learning for electrical load forecasting via Transformer and transfer learning.
Jiaxin Gao, Wenbo Hu, Dongxiao Zhang, Yuntian Chen.
The 14th International Conference on Applied Energy (ICAE), 2022.
[arXiv]

Two Birds with One Stone: Series Saliency for Accurate and Interpretable Multivariate Time Series Forecasting
Qingyi Pan, Wenbo Hu and Ning Chen. The 30th International Joint Conference on Artificial Intelligence (IJCAI), 2021.
[paper]

Calibrated Reliable Regression using Maximum Mean Discrepancy
Peng Cui, Wenbo Hu and Jun Zhu. Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020.
[paper] [arXiv]