- Erdun Gao, Liang Zhang, Jake Fawkes, Aoqi Zuo, Wenqin Liu, Haoxuan Li, Mingming Gong, Dino Sejdinovic. Observationally Informed Adaptive Causal Experimental Design. Preprint, 2026.
- Yuhang Liu, Erdun Gao, Dong Gong, Anton van den Hengel, Javen Qinfeng Shi. Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs. Preprint, 2026.
- Yuhang Liu, Zhen Zhang, Dong Gong, Erdun Gao, Biwei Huang, Mingming Gong, Anton van den Hengel, Kun Zhang, Javen Qinfeng Shi. Towards Identifiable Latent Additive Noise Models. Preprint, 2026.
- Erdun Gao, Jake Fawkes, Dino Sejdinovic. Causal-EPIG: Causally Aligned Active CATE Estimation. International Conference on Machine Learning (ICML), 2026.
- Wenqin Liu, Weizhi Quan, Aoqi Zuo, Erdun Gao†, Vu Nguyen, Dino Sejdinovic, Howard Bondell, Mingming Gong. TimeLAVA: Learning-Agnostic Valuation for Time Series Data. International Conference on Machine Learning (ICML), 2026.
- Haoxiang Wang, Haoxuan Li, Ziyan Wang, Zhiheng Zhang, Aoqi Zuo, Erdun Gao, Kun Zhang, Mingming Gong. Treatment Responder Classification with Abstention. International Conference on Machine Learning (ICML), Spotlight, 2026.
- Wenkang Jiang, Yuhang Liu, Yichao Cai, Erdun Gao, Jiayi Dong, Ehsan Abbasnejad, Lina Yao, Javen Qinfeng Shi. What Makes a Good Representation for Single-Cell Perturbation Prediction? International Conference on Machine Learning (ICML), 2026.
- Erdun Gao, Dino Sejdinovic. ActiveCQ: Active Estimation of Causal Quantities. International Conference on Learning Representations (ICLR), 2026.
- Yuhang Liu, Zhen Zhang, Dong Gong, Erdun Gao, Biwei Huang, Mingming Gong, Anton van den Hengel, Kun Zhang, Javen Qinfeng Shi. Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning. International Conference on Learning Representations (ICLR), 2026.
- Yuhang Liu, Dong Gong, Yichao Cai, Erdun Gao, Zhen Zhang, Biwei Huang, Mingming Gong, Anton van den Hengel, Javen Qinfeng Shi. I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? International Conference on Learning Representations (ICLR), 2026.
- Erdun Gao, Howard Bondell, Shaoli Huang, Mingming Gong. Domain Generalization via Content Factors Isolation: A Two-level Latent Variable Modeling Approach. Machine Learning (MLJ), 2025.
- Wenqin Liu, Haoze Hou, Erdun Gao, Biwei Huang, Qiuhong Ke, Howard Bondell, Mingming Gong. MissScore: High-Order Score Estimation in the Presence of Missing Data. International Conference on Machine Learning (ICML), 2025.
- Xinshu Li, Ruoyu Wang, Erdun Gao, Mingming Gong, Lina Yao. Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation. ACM International Conference on Multimedia (ACMMM), 2025.
- Zuopeng Yang, Jiluan Fan, Anli Yan, Erdun Gao, Xin Lin, Tao Li, Kanghua Mo, Changyu Dong. Distraction is All You Need for Multimodal Large Language Model Jailbreaking. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Highlight, 2025.
- Yichao Cai, Yuhang Liu, Erdun Gao, Tianjiao Jiang, Zhen Zhang, Javen Qinfeng Shi. On the Value of Cross-Modal Misalignment in Multimodal Representation Learning. Advances in Neural Information Processing Systems (NeurIPS), Spotlight, 2025.
- Erdun Gao. Causal Inference with Imperfect Data. Ph.D. Thesis, The University of Melbourne, 2024.
- Erdun Gao, Howard Bondell, Wei Huang, Mingming Gong. A Variational Framework for Estimating the Treatment Effects with Measurement Error. International Conference on Learning Representations (ICLR), 2024.
- Wenqin Liu, Biwei Huang, Erdun Gao, Qiuhong Ke, Howard Bondell, Mingming Gong. Causal Discovery with Mixed Linear and Nonlinear Additive Noise Models: A Scalable Approach. Conference on Causal Learning and Reasoning (CLeaR), 2024.
- Erdun Gao, Junjia Chen, Li Shen, Tongliang Liu, Mingming Gong, Howard Bondell. FedDAG: Federated DAG Structure Learning. Transactions on Machine Learning Research (TMLR), 2023.
- Zuopeng Yang, Tianshu Chu, Xin Lin, Erdun Gao, Daqing Liu, Jie Yang, Chaoyue Wang. Eliminating Contextual Prior Bias for Semantic Image Editing via Dual-Cycle Diffusion. IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2023.
- Xiaoran Zhang, Zhibin Pan, Quan Zhou, Erdun Gao, Xinyi Gao, Guojun Fan. A novel two-level embedding pattern for grayscale-invariant reversible data hiding. Multimedia Tools and Applications (MTA), 2023.
- Erdun Gao, Ignavier Ng, Mingming Gong, Li Shen, Wei Huang, Tongliang Liu, Kun Zhang, Howard Bondell. MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models. Advances in Neural Information Processing Systems (NeurIPS), 2022.
- Guojun Fan, Zhibin Pan, Erdun Gao, Xinyi Gao, Xiaoran Zhang. Reversible data hiding method based on combining IPVO with bias-added Rhombus predictor by multi-predictor mechanism. Signal Processing (SP), 2021.
- Xinyi Gao, Zhibin Pan, Erdun Gao, Guojun Fan. Reversible data hiding for high dynamic range images using two-dimensional prediction-error histogram of the second time prediction. Signal Processing (SP), 2020.
- Zhibin Pan, Xinyi Gao, Erdun Gao, Guojun Fan. Adaptive complexity for pixel-value-ordering based reversible data hiding. IEEE Signal Processing Letters (SPL), 2020.
- Zhibin Pan, Xinyi Gao, Lingfei Wang, Erdun Gao. Effective reversible data hiding using dynamic neighboring pixels prediction based on prediction-error histogram. Multimedia Tools and Applications (MTA), 2020.
- Erdun Gao, Zhibin Pan, Xinyi Gao. Reversible data hiding based on novel pairwise PVO and annular merging strategy. Information Sciences (INS), 2019.
- Zhibin Pan, Erdun Gao, Ruoxin Zhu, Lingfei Wang. A low bit-rate SOC-based reversible data hiding algorithm by using new encoding strategies. Multimedia Tools and Applications (MTA), 2019.
- Zhibin Pan, Erdun Gao. Reversible data hiding based on novel embedding structure PVO and adaptive block-merging strategy. Multimedia Tools and Applications (MTA), 2019.