Chao Du

Senior Research Scientist, Sea AI Lab
Email: duchao0726 at gmail dot com

I am a senior research scientist at Sea AI Lab, Singapore. I finished my Ph.D. in 2019 at TSAIL Group in the Department of Computer Science and Technology at Tsinghua University, advised by Prof. Jun Zhu and Prof. Bo Zhang. And I received my B.Eng. from the Yao Class in Institute for Interdisciplinary Information Sciences at Tsinghua University in 2014.

My primary research interests lie at the intersection of probabilistic inference and generative modeling. I focus on developing fundamental probabilistic tools to enhance the capabilities of generative AI—making it more powerful, interpretable, and controllable.

We are hiring Research Scientist and Research Intern to work on generative models (e.g., diffusion models, LLMs). Please feel free to contact me if you are interested.

Publications (* denotes equal contribution; † denotes correspondence.) [Google Scholar]

  • Continual Reinforcement Learning by Planning with Online World Models
    Zichen Liu, Guoji Fu, Chao Du, Wee Sun Lee, Min Lin
    International Conference on Machine Learning (ICML), Vancouver, Canada, 2025
    (Spotlight, Acceptance rate~2.6%)
  • Improving Your Model Ranking on Chatbot Arena by Vote Rigging
    Rui Min, Tianyu Pang, Chao Du, Qian Liu, Minhao Cheng, Min Lin
    International Conference on Machine Learning (ICML), Vancouver, Canada, 2025
    [Paper] [Codes]
  • BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
    Yunlong Hou, Fengzhuo Zhang, Cunxiao Du, Xuan Zhang, Jiachun Pan, Tianyu Pang, Chao Du, Vincent Y. F. Tan, Zhuoran Yang
    International Conference on Machine Learning (ICML), Vancouver, Canada, 2025
  • Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models
    Zehan Wang, Ziang Zhang, Tianyu Pang, Chao Du, Hengshuang Zhao, Zhou Zhao
    International Conference on Machine Learning (ICML), Vancouver, Canada, 2025
    [Paper] [Codes] [Project Page]
  • Weak-to-Strong Jailbreaking on Large Language Models
    Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei Li, Yu-Xiang Wang, William Yang Wang
    International Conference on Machine Learning (ICML), Vancouver, Canada, 2025
    [Paper] [Codes]
  • Improving Long-Text Alignment for Text-to-Image Diffusion Models
    Luping Liu, Chao Du†, Tianyu Pang, Zehan Wang, Chongxuan Li, Dong Xu
    International Conference on Learning Representations (ICLR), Singapore, 2025
    [Paper] [Codes]
  • Scaling up Masked Diffusion Models on Text
    Shen Nie, Fengqi Zhu, Chao Du, Tianyu Pang, Qian Liu, Guangtao Zeng, Min Lin, Chongxuan Li
    International Conference on Learning Representations (ICLR), Singapore, 2025
    [Paper] [Codes]
  • Bootstrapping Language Models with DPO Implicit Rewards
    Changyu Chen, Zichen Liu, Chao Du†, Tianyu Pang, Qian Liu, Arunesh Sinha†, Pradeep Varakantham†, Min Lin
    International Conference on Learning Representations (ICLR), Singapore, 2025
    [Paper] [Codes]
  • Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates
    Xiaosen Zheng, Tianyu Pang, Chao Du, Qian Liu, Jing Jiang, Min Lin
    International Conference on Learning Representations (ICLR), Singapore, 2025
    (Oral, Acceptance rate~1.9%)
    [Paper] [Codes]
  • When Attention Sink Emerges in Language Models: An Empirical View
    Xiangming Gu, Tianyu Pang, Chao Du, Qian Liu, Fengzhuo Zhang, Cunxiao Du, Ye Wang, Min Lin
    International Conference on Learning Representations (ICLR), Singapore, 2025
    [Paper] [Codes]
  • Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
    Xiaojun Jia, Tianyu Pang, Chao Du, Yihao Huang, Jindong Gu, Yang Liu, Xiaochun Cao, Min Lin
    International Conference on Learning Representations (ICLR), Singapore, 2025
    [Paper] [Codes]
  • A Closer Look at Machine Unlearning for Large Language Models
    Xiaojian Yuan, Tianyu Pang, Chao Du, Kejiang Chen, Weiming Zhang, Min Lin
    International Conference on Learning Representations (ICLR), Singapore, 2025
    [Paper] [Codes]
  • Towards Learning on Vertically Partitioned Data with Distributed Differential Privacy
    Ergute Bao, Fei Wei, Yin Yang, Xiaokui Xiao, Tianyu Pang, Chao Du
    IEEE International Conference on Data Engineering (ICDE), Hong Kong, China, 2025
  • On Memorization in Diffusion Models
    Xiangming Gu, Chao Du†, Tianyu Pang†, Chongxuan Li, Min Lin, Ye Wang†
    Transactions on Machine Learning Research (TMLR), February 2025
    [Paper] [Codes]
  • When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
    Haonan Wang, Qian Liu, Chao Du, Tongyao Zhu, Cunxiao Du, Kenji Kawaguchi, Tianyu Pang
    Transactions on Machine Learning Research (TMLR), February 2025
    [Paper] [Codes]
  • Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
    Siyuan Liang, Jiawei Liang, Tianyu Pang, Chao Du, Aishan Liu, Mingli Zhu, Xiaochun Cao, Dacheng Tao
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, USA, 2025
    [Paper]
  • Graph Diffusion Policy Optimization
    Yijing Liu*, Chao Du*†, Tianyu Pang, Chongxuan Li, Min Lin, Wei Chen
    Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024
    [Paper] [Codes]
  • Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
    Xuan Zhang, Chao Du†, Tianyu Pang, Qian Liu, Wei Gao, Min Lin
    Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024
    [Paper] [Codes]
  • Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
    Xiaosen Zheng, Tianyu Pang, Chao Du, Qian Liu, Jing Jiang, Min Lin
    Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024
    [Paper] [Codes]
  • LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
    Chengsong Huang, Qian Liu, Bill Yuchen Lin, Tianyu Pang, Chao Du, Min Lin
    Conference on Language Modeling (COLM), Philadelphia, USA, 2024
    [Paper] [Codes]
  • Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
    Xiangming Gu*, Xiaosen Zheng*, Tianyu Pang*, Chao Du, Qian Liu, Ye Wang, Jing Jiang, Min Lin
    International Conference on Machine Learning (ICML), Vienna, Austria, 2024
    [Paper] [Codes] [Project Page]
  • Finetuning Text-to-Image Diffusion Models for Fairness
    Xudong Shen, Chao Du†, Tianyu Pang†, Min Lin, Yongkang Wong, Mohan Kankanhalli†
    International Conference on Learning Representations (ICLR), Vienna, Austria, 2024
    (Oral, Acceptance rate~1.2%)
    [Paper] [Codes] [Project Page]
  • Intriguing Properties of Data Attribution on Diffusion Models
    Xiaosen Zheng, Tianyu Pang†, Chao Du†, Jing Jiang†, Min Lin
    International Conference on Learning Representations (ICLR), Vienna, Austria, 2024
    [Paper] [Codes]
  • Locality Sensitive Sparse Encoding for Learning World Models Online
    Zichen Liu, Chao Du, Wee Sun Lee, Min Lin
    International Conference on Learning Representations (ICLR), Vienna, Austria, 2024
    [Paper] [Codes]
  • BAFFLE: A Baseline of Backpropagation-Free Federated Learning
    Haozhe Feng, Tianyu Pang, Chao Du, Wei Chen, Shuicheng Yan, Min Lin
    The 18th European Conference on Computer Vision (ECCV), Milano, Italy, 2024
    [Paper] [Codes]
  • On Evaluating Adversarial Robustness of Large Vision-Language Models
    Yunqing Zhao*, Tianyu Pang*†, Chao Du†, Xiao Yang, Chongxuan Li, Ngai-man Cheung†, Min Lin
    Annual Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023
    [Paper] [Codes] [Project Page]
  • Gaussian Mixture Solvers for Diffusion Models
    Hanzhong Guo, Cheng Lu, Fan Bao, Tianyu Pang, Shuicheng Yan, Chao Du†, Chongxuan Li†
    Annual Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023
    [Paper] [Codes]
  • On Calibrating Diffusion Probabilistic Models
    Tianyu Pang, Cheng Lu, Chao Du, Min Lin, Shuicheng Yan, Zhijie Deng
    Annual Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023
    [Paper] [Codes]
  • Efficient Diffusion Policies For Offline Reinforcement Learning
    Bingyi Kang, Xiao Ma, Chao Du, Tianyu Pang, Shuicheng Yan
    Annual Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023
    [Paper] [Codes]
  • Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
    Chao Du, Tianbo Li, Tianyu Pang, Shuicheng Yan, Min Lin
    International Conference on Machine Learning (ICML), Hawaii, USA, 2023
    [Paper] [Codes] [Slides] [Poster]
  • Better Diffusion Models Further Improve Adversarial Training
    Zekai Wang*, Tianyu Pang*, Chao Du, Min Lin, Weiwei Liu, Shuicheng Yan
    International Conference on Machine Learning (ICML), Hawaii, USA, 2023
    [Paper] [Codes]
  • Bag of Tricks for Training Data Extraction from Language Models
    Weichen Yu, Tianyu Pang, Qian Liu, Chao Du, Bingyi Kang, Yan Huang, Min Lin, Shuicheng Yan
    International Conference on Machine Learning (ICML), Hawaii, USA, 2023
    [Paper] [Codes]
  • Exploring Model Dynamics for Accumulative Poisoning Discovery
    Jianing Zhu, Xiawei Guo, Jiangchao Yao, Chao Du, Li He, Shuo Yuan, Tongliang Liu, Liang Wang, Bo Han
    International Conference on Machine Learning (ICML), Hawaii, USA, 2023
    [Paper] [Codes]
  • Exploring Incompatible Knowledge Transfer in Few-shot Image Generation
    Yunqing Zhao, Chao Du, Milad Abdollahzadeh, Tianyu Pang, Min Lin, Shuicheng Yan, Ngai-man Cheung
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 2023
    [Paper] [Codes] [Project Page]
  • Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning
    Haozhe Wang, Chao Du, Panyan Fang, Li He, Liang Wang, Bo Zheng
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD), Long Beach, USA, 2023
    [Paper]
  • ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning
    Haozhe Wang, Chao Du, Panyan Fang, Shuo Yuan, Xuming He, Liang Wang, Bo Zheng
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD), Washington DC, USA, 2022
    [Paper]
  • Exploration in Online Advertising Systems with Deep Uncertainty-Aware Learning
    Chao Du, Zhifeng Gao, Shuo Yuan, Lining Gao, Ziyan Li, Yifan Zeng, Xiaoqiang Zhu, Jian Xu, Kun Gai, Kuang-Chih Lee
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD), Virtual Conference, 2021
    [Paper] [Codes]
  • A Bayesian Approach for Subset Selection in Contextual Bandits
    Jialian Li, Chao Du, Jun Zhu
    Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), Virtual Conference, 2021
    [Paper]
  • Learning Implicit Generative Models by Teaching Density Estimators
    Kun Xu*, Chao Du*, Chongxuan Li, Jun Zhu, Bo Zhang
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), Ghent, Belgium, 2020
    [Paper] [Codes]
  • Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness
    Tianyu Pang, Kun Xu, Yinpeng Dong, Chao Du, Ning Chen, Jun Zhu
    International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, 2020
    [Paper] [Codes]
  • To Relieve Your Headache of Training an MRF, Take AdVIL
    Chongxuan Li, Chao Du, Kun Xu, Max Welling, Jun Zhu, Bo Zhang
    International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, 2020
    [Paper] [Codes]
  • Improving Adversarial Robustness via Promoting Ensemble Diversity
    Tianyu Pang, Kun Xu, Chao Du, Ning Chen, Jun Zhu
    International Conference on Machine Learning (ICML), Long Beach, USA, 2019
    [Paper] [Codes]
  • Towards Robust Detection of Adversarial Examples
    Tianyu Pang, Chao Du, Yinpeng Dong, Jun Zhu
    Annual Conference on Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2018
    [Paper] [Codes]
  • Max-Mahalanobis Linear Discriminant Analysis Networks
    Tianyu Pang, Chao Du, Jun Zhu
    International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018
    [Paper] [Codes]
  • Collaborative Filtering with User-Item Co-Autoregressive Models
    Chao Du, Chongxuan Li, Yin Zheng, Jun Zhu, Bo Zhang
    Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), New Orleans, USA, 2018
    [Paper] [Codes]
  • Learning Deep Generative Models with Doubly Stochastic Gradient MCMC
    Chao Du, Jun Zhu, Bo Zhang
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2018, 29(7): 3084-3096.
    [Paper] [Codes]
  • Composite Quantization for Approximate Nearest Neighbor Search
    Ting Zhang, Chao Du, Jingdong Wang
    International Conference on Machine Learning (ICML), Beijing, China, 2014
    [Paper]

Workshop Papers and Preprints

  • Learning Implicit Generative Models by Teaching Explicit Ones
    Chao Du*, Kun Xu*, Chongxuan Li, Jun Zhu, Bo Zhang
    ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models, Stockholm, Sweden, 2018.
    [Paper] [Codes]
  • Inner Product Similarity Search using Compositional Codes
    Chao Du, Jingdong Wang
    [Paper]

Services

  • Reviewer: ICML, NeurIPS, ICLR, AISTATS, CVPR, ICCV, COLM, AAAI, SIGKDD, TPAMI, TNNLS

Contact Me

duchao0726 at gmail dot com