• A Survey on Bayesian Deep Learning.
  Hao Wang, Dit-Yan Yeung.
  ACM Computing Surveys (CSUR), 53(5), Article 108, 2020.
  [journal version] [healthcare application (Nature Medicine '21)] [arXiv version] [blog] [github (updating)]

  Bayesian Deep Learning

('Underline' indicates students I (co-)advise/mentor. '*' indicates equal contribution.)

• Detecting Text from Large Language Models via Rewriting.
  Chengzhi Mao, Carl Vondrick, Hao Wang, Junfeng Yang.
  Twelfth International Conference on Learning Representations (ICLR), 2024.
  [pdf] [code and data] [talk] [slides]
  

  Natural Language Processing / Large Language Models Safe & Trustworthy AI

• Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations.
  Xinyue Xu, Yi Qin, Lu Mi, Hao Wang, Xiaomeng Li.
  Twelfth International Conference on Learning Representations (ICLR), 2024.
  [pdf] [code and data] [talk] [slides]
  

  Bayesian Deep Learning Interpretability Safe & Trustworthy AI

• Continuous Invariance Learning.
  Yong Lin, Fan Zhou, Lu Tan, Lintao Ma, Jianmeng Liu, Yansu He, Yuan Yuan, Yu Liu, James Y. Zhang, Yujiu Yang, Hao Wang.
  Twelfth International Conference on Learning Representations (ICLR), 2024.
  [pdf] [code and data] [talk] [slides]
  

  Safe & Trustworthy AI Domain Adaptation

• Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees.
  Guang-Yuan Hao, Hengguan Huang, Haotian Wang, Jie Gao, Hao Wang.
  Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024.
  [pdf] [code and data] [talk]
  

  Domain Adaptation

• Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing.
  Ziyan Wang, Hao Wang.
  Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS), 2023.
  [pdf] [code and data] [talk] [slides (pptx)] [slides (pdf)]
  

  Bayesian Deep Learning Safe & Trustworthy AI Bias & Fairness Vision

• A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm.
  Haizhou Shi, Hao Wang.
  Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS), 2023.
  [pdf] [code and data] [talk] [slides (pptx)] [slides (pdf)]
  

  Domain Adaptation

• Self-Interpretable Time Series Prediction with Counterfactual Explanations.
  Jingquan Yan, Hao Wang.
  Fortieth International Conference on Machine Learning (ICML), 2023. (Oral)
  [pdf] [code and data] [talk] [slides]
  

  Bayesian Deep Learning Safe & Trustworthy AI Interpretability Causality Health

• Taxonomy-Structured Domain Adaptation.
  Tianyi Liu*, Zihao Xu*, Hao He, Guang-Yuan Hao, Guang-He Lee, Hao Wang.
  Fortieth International Conference on Machine Learning (ICML), 2023.
  [pdf] [code and data] [talk] [slides]
  

  Domain Adaptation Interpretability Safe & Trustworthy AI

• Robust Perception through Equivariance.
  Chengzhi Mao, Lingyu Zhang, Abhishek Vaibhav Joshi, Junfeng Yang, Hao Wang, Carl Vondrick.
  Fortieth International Conference on Machine Learning (ICML), 2023.
  [pdf] [code and data] [project page] [talk] [slides]
  

  Safe & Trustworthy AI Vision

• Identifying Regional Driving Risks via Transductive Cross-City Transfer Learning under Negative Transfer.
  Hua Yan, Hao Wang, Desheng Zhang, Yu Yang.
  The Conference on Information and Knowledge Management (CIKM), 2023.
  [pdf] [code and data] [talk] [slides]
  

  Safe & Trustworthy AI Domain Adaptation

• Landscape Learning for Neural Network Inversion.
  Ruoshi Liu, Chengzhi Mao, Purva Tendulkar, Hao Wang, Carl Vondrick.
  International Conference on Computer Vision (ICCV), 2023.
  [pdf] [code and data] [blog] [talk] [slides] [Bayesian interpretation]
  

  Vision Bayesian Deep Learning

• Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation.
  Zihao Xu*, Guang-Yuan Hao*, Hao He, Hao Wang.
  Eleventh International Conference on Learning Representations (ICLR), 2023. (Spotlight)
  [pdf] [openreview] [code and data] [talk] [slides]
  

  Bayesian Deep Learning Domain Adaptation Interpretability Safe & Trustworthy AI

• FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation.
  Xueyang Wu*, Hengguan Huang*, Youlong Ding, Hao Wang, Ye Wang, Qian Xu.
  Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023.
  [pdf] [code and data] [talk]
  

  Bayesian Deep Learning

• Counterfactual Collaborative Reasoning.
  Jianchao Ji, Zelong Li, Shuyuan Xu, Max Xiong, Juntao Tan, Yingqiang Ge, Hao Wang, Yongfeng Zhang.
  Sixteenth ACM International Conference on Web Search and Data Mining (WSDM), 2023.
  [pdf] [code and data] [talk] [slides]
  

  Causality Recommender Systems Interpretability

• Extrapolative Continuous-Time Bayesian Neural Network for Fast Training-Free Test-Time Adaptation.
  Hengguan Huang, Xiangming Gu, Hao Wang, Chang Xiao, Hongfu Liu, Ye Wang.
  Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.
  [pdf] [code and data] [talk] [slides]
  

  Bayesian Deep Learning Domain Adaptation

• Earthformer: Exploring Space-Time Transformers for Earth System Forecasting.
  Zhihan Gao, Xingjian Shi, Hao Wang, Yi Zhu, Yuyang Wang, Mu Li, Dit-Yan Yeung.
  Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.
  [pdf] [code and data] [talk] [spotlight] [slides]
  

  Vision

• Domain Adaptation for Time Series Forecasting via Attention Sharing.
  Xiaoyong Jin, Youngsuk Park, Danielle Maddix, Hao Wang, Yuyang Wang.
  Thirty-Ninth International Conference on Machine Learning (ICML), 2022.
  [pdf] [code and data] [talk] [slides]
  

  Domain Adaptation

• On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond.
  Yuzhe Yang, Hao Wang, Dina Katabi.
  Seventeenth European Conference on Computer Vision (ECCV), 2022.
  [pdf] [code and data] [project page] [healthcare application (Nature Medicine '22)] [blog post] [talk] [slides]
  

  Domain Adaptation Bias & Fairness Vision Safe & Trustworthy AI

• Social ODE: Multi-Agent Trajectory Forecasting with Neural Ordinary Differential Equations.
  Song Wen, Hao Wang, Dimitris Metaxas.
  Seventeenth European Conference on Computer Vision (ECCV), 2022.
  [pdf] [code and data] [talk] [slides]
  

  Safe & Trustworthy AI Bayesian Deep Learning Graph & Relational Learning

• “My Nose Is Running.” “Are You Also Coughing?”: Building a Medical Diagnosis Agent with Interpretable Inquiry Logics.
  Wenge Liu, Yi Cheng, Hao Wang, Jianheng Tang, Yafei Liu, Ruihui Zhao, Wenjie Li, Yefeng Zheng, Xiaodan Liang.
  Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI), 2022.
  [pdf] [code and data] [talk]
  

  Bayesian Deep Learning Interpretability Health Natural Language Processing Safe & Trustworthy AI

• Causal Transportability for Visual Recognition.
  Chengzhi Mao, James Wang, Kevin Xia, Hao Wang, Junfeng Yang, Elias Bareinboim, Carl Vondrick.
  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  [pdf] [supplementary] [code and data] [talk]
  

  Bayesian Deep Learning Vision Causality

• OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks.
  Wanyu Lin, Hao Lan, Hao Wang, Baochun Li.
  Best paper finalist 33 / 8161 = 0.4%.
  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (Oral)
  [pdf] [code and data] [talk]
  

  Bayesian Deep Learning Interpretability Safe & Trustworthy AI Graph & Relational Learning Causality

• Bayesian Invariant Risk Minimization.
  Yong Lin, Hanze Dong, Hao Wang, Tong Zhang.
  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (Oral)
  [pdf] [code and data] [talk]
  

  Bayesian Deep Learning Causality Safe & Trustworthy AI

• Graph-Relational Domain Adaptation.
  Zihao Xu, Hao He, Guang-He Lee, Yuyang Wang, Hao Wang.
  Tenth International Conference on Learning Representations (ICLR), 2022.
  [pdf] [code and data] [TPT-48 dataset] [talk] [slides]
  

  Domain Adaptation Graph & Relational Learning

• Context Uncertainty in Contextual Bandits with Applications to Recommender Systems.
  Hao Wang, Yifei Ma, Hao Ding, Yuyang Wang.
  Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022.
  [pdf] [supplementary] [code and data] [talk] [slides]
  

  Bayesian Deep Learning Recommender Systems Safe & Trustworthy AI

• Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate.
  Lu Mi, Hao Wang, Yonglong Tian, Hao He, Nir Shavit.
  Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022.
  (Short Version Presented at the ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning, 2021.)
  [pdf] [code and data] [slides]
  

  Safe & Trustworthy AI Bayesian Deep Learning Vision

• Adversarial Attacks are Reversible with Natural Supervision.
  Chengzhi Mao, Mia Chiquier, Hao Wang, Junfeng Yang, Carl Vondrick.
  International Conference on Computer Vision (ICCV), 2021.
  [pdf] [code and data] [talk] [slides]
  

  Bayesian Deep Learning Safe & Trustworthy AI Vision

• Paint Transformer: Feed Forward Neural Painting with Stroke Prediction.
  Songhua Liu*, Tianwei Lin*, Dongliang He, Fu Li, Ruifeng Deng, Xin Li, Errui Ding, Hao Wang.
  International Conference on Computer Vision (ICCV), 2021. (Oral)
  [pdf] [code and data] [talk (short version)] [slides]
  

  Vision

• STRODE: Stochastic Boundary Ordinary Differential Equation.
  Hengguan Huang, Hongfu Liu, Hao Wang, Chang Xiao, Ye Wang.
  Thirty-Eighth International Conference on Machine Learning (ICML), 2021.
  [pdf] [code and data] [talk] [slides]
  

  Bayesian Deep Learning

• Correcting Exposure Bias for Link Recommendation.
  Shantanu Gupta, Hao Wang, Zachary Lipton, Yuyang Wang.
  Thirty-Eighth International Conference on Machine Learning (ICML), 2021.
  [pdf] [code and data] [talk] [slides]
  

  Safe & Trustworthy AI Bias & Fairness Recommender Systems Graph & Relational Learning Causality

• Delving into Deep Imbalanced Regression.
  Yuzhe Yang, Kaiwen Zha, Yingcong Chen, Hao Wang, Dina Katabi.
  Thirty-Eighth International Conference on Machine Learning (ICML), 2021. (Oral)
  [pdf] [healthcare application (Nature Medicine '22)] [code and data] [blog] [project page] [talk] [slides]
  

  Bias & Fairness Safe & Trustworthy AI Health Vision Natural Language Processing

• Generative Interventions for Causal Learning.
  Chengzhi Mao, Augustine Cha*, Amogh Gupta*, Hao Wang, Junfeng Yang, Carl Vondrick.
  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  [pdf] [code and data] [talk]
  

  Bayesian Deep Learning Safe & Trustworthy AI Causality Vision

• Continuously Indexed Domain Adaptation.
  Hao Wang*, Hao He*, Dina Katabi.
  Thirty-Seventh International Conference on Machine Learning (ICML), 2020. (Oral)
  [pdf] [healthcare application (Nature Medicine '22)] [code and data] [project page] [blog] [talk] [slides]
  

  Domain Adaptation Health

• Deep Graph Random Process for Relational-Thinking-Based Speech Recognition.
  Hengguan Huang, Fuzhao Xue, Hao Wang, Ye Wang.
  Thirty-Seventh International Conference on Machine Learning (ICML), 2020. (Oral)
  [pdf] [code and data]
  

  Bayesian Deep Learning

• BodyCompass: Monitoring Sleep Posture with Wireless Signals.
  Shichao Yue, Yuzhe Yang, Hao Wang, Hariharan Rahul, Dina Katabi.
  ACM International Joint Conference on Pervasive and Ubiquitous Computing (Ubicomp), 2020.
  [pdf] [project page] [slides] [talk] [MIT News]
  

  Domain Adaptation Health

• Learning Guided Electron Microscopy with Active Acquisition.
  Lu Mi, Hao Wang, Yaron Meirovitch, Richard Schalek, Srinivas Turaga, Jeff Lichtman, Samuel Aravinthan, Nir Shavit.
  Medical Image Computing and Computer Assisted Interventions (MICCAI), 2020.
  [pdf] [code and data]
  

  Health Vision

• Rethinking Knowledge Graph Propagation for Zero-Shot Learning.
  Michael C. Kampffmeyer*, Yinbo Chen*, Xiaodan Liang, Hao Wang, Yujia Zhang, Eric P. Xing.
  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  [pdf] [code and data]
  

  Domain Adaptation Vision

• ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees.
  Hao He, Hao Wang, Guang-He Lee, Yonglong Tian.
  Seventh International Conference on Learning Representations (ICLR), 2019.
  (Short Version Presented at the ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models, 2018.)
  [pdf] [code and data]
  

  Bayesian Deep Learning

• Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling.
  Hao Wang, Chengzhi Mao, Hao He, Mingmin Zhao, Tommi S. Jaakkola, Dina Katabi.
  Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019.
  [pdf] [supplementary] [code and data] [slides] [MIT News]
  

  Bayesian Deep Learning Health

• Recurrent Poisson Process Unit for Speech Recognition.
  Hengguan Huang, Hao Wang, Brian Mak.
  Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019.
  [pdf] [code and data] [slides]
  

  Bayesian Deep Learning

• Bayesian Modelling and Monte Carlo Inference for GAN.
  Hao He, Hao Wang, Guang-He Lee, Yonglong Tian.
  International Conference on Machine Learning (ICML) Workshop on Theoretical Foundations and Applications of Deep Generative Models, 2018.
  [pdf]
  

  Bayesian Deep Learning

• Extracting Multi-Person Respiration from Entangled RF Signals.
  Shichao Yue, Hao He, Hao Wang, Hariharan Rahul, Dina Katabi.
  ACM International Joint Conference on Pervasive and Ubiquitous Computing (Ubicomp), 2018.
  [pdf] [project page]
  

  Health

• Deep Learning for Precipitation Nowcasting: A Benchmark and a New Model.
  Xingjian Shi, Zhihan Gao, Leonard Lausen, Hao Wang, Dit-Yan Yeung, Wai-kin Wong, and Wang-chun Woo.
  Thirty-First Annual Conference on Neural Information Processing Systems (NIPS), 2017. (Spotlight)
  [pdf] [code and data] [project page]
  

  Vision

• Relational Deep Learning: A Deep Latent Variable Model for Link Prediction.
  Hao Wang, Xingjian Shi, Dit-Yan Yeung.
  Thirty-First AAAI Conference on Artificial Intelligence (AAAI), 2017. (Oral)
  [pdf] [supplementary] [code and data] [slides]
  

  Bayesian Deep Learning Graph & Relational Learning

• Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks.
  Hao Wang, Xingjian Shi, Dit-Yan Yeung.
  Thirtieth Annual Conference on Neural Information Processing Systems (NIPS), 2016.
  [pdf] [supplementary] [spotlight video] [code and data]
  

  Bayesian Deep Learning Recommender Systems

• Natural Parameter Networks: A Class of Probabilistic Neural Networks.
  Hao Wang, Xingjian Shi, Dit-Yan Yeung.
  Thirtieth Annual Conference on Neural Information Processing Systems (NIPS), 2016.
  [pdf] [project page] [supplementary] [spotlight video] [code] [PyTorch code]
  

  Bayesian Deep Learning Safe & Trustworthy AI

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting.
  Xingjian Shi, Zhourong Chen, Hao Wang, Dit-Yan Yeung, Wai-kin Wong, Wang-chun Woo.
  Twenty-Ninth Annual Conference on Neural Information Processing Systems (NIPS), 2015.
  [pdf] [code and data]
  

  Vision

• Collaborative Deep Learning for Recommender Systems.
  Hao Wang, Naiyan Wang, Dit-Yan Yeung.
  Twenty-First ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2015. (Oral)
  Most cited paper among all papers at KDD 2015.
  [pdf] [project page] [code] [data] [MXNet code] [TensorFlow code] [third-party TensorFlow/Keras/Python code] [third-party PyTorch code] [ipynb] [slides] [slides (long)]
  

  Bayesian Deep Learning Recommender Systems

• Relational Stacked Denoising Autoencoder for Tag Recommendation.
  Hao Wang, Xingjian Shi, Dit-Yan Yeung.
  Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2015.
  [pdf] [supplementary] [code] [data] [slides]
  

  Bayesian Deep Learning Recommender Systems Graph & Relational Learning

• Online Egocentric Models for Citation Networks.
  Hao Wang, Wu-Jun Li.
  Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI), 2013.
  [pdf]
  

  Recommender Systems Graph & Relational Learning

• Collaborative Topic Regression with Social Regularization for Tag Recommendation.
  Hao Wang, Binyi Chen, Wu-Jun Li.
  Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI), 2013.
  [pdf] [data] [citeulike-a] [citeulike-t]
  

  Recommender Systems Graph & Relational Learning

• Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization.
  Wei Wei, Hengguan Huang, Xiangming Gu, Hao Wang, Ye Wang.
  Transactions on Machine Learning Research (TMLR), 2022.
  [pdf] [data and code]
  

  Bayesian Deep Learning

• Artificial Intelligence-Enabled Detection and Assessment of Parkinson’s Disease Using Nocturnal Breathing Signals.
  Yuzhe Yang, Yuan Yuan, Guo Zhang, Hao Wang, Ying-Cong Chen, Yingcheng Liu, Christopher G. Tarolli, Daniel Crepeau, Jan Bukartyk, Mithri R. Junna, Aleksandar Videnovic, Terry D. Ellis, Melissa C. Lipford, Ray Dorsey, Dina Katabi.
  Nature Medicine, 2022.
  Selected as one of the Ten Notable Advances in 2022 by Nature Medicine.
  [pdf] [nature medicine page] [project page] [talk (45 min)] [talk (15 min)] [MIT News] [Forbes] [Washington Post] [NVDIA blog] [details on imbalanced regression (ICML version)] [details on multi-domain learning (ECCV version)]
  

  Domain Adaptation Health Bayesian Deep Learning

• Assessment of Medication Self-Administration Using Artificial Intelligence.
  Mingmin Zhao*, Kreshnik Hoti*, Hao Wang, Aniruddh Raghu, Dina Katabi.
  Nature Medicine, 2021.
  [pdf] [nature medicine page] [MIT News] [model details]
  

  Bayesian Deep Learning Health

• A Survey on Bayesian Deep Learning.
  Hao Wang, Dit-Yan Yeung.
  ACM Computing Surveys (CSUR), 53(5), Article 108, 2020.
  [pdf] [healthcare application (Nature Medicine '21)] [blog] [github (updating)]
  

  Bayesian Deep Learning

• Towards Bayesian Deep Learning: A Framework and Some Existing Methods.
  Hao Wang, Dit-Yan Yeung.
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 28(12):3395-3408, 2016.
  [pdf] [healthcare application (Nature Medicine '21)] [blog] [github (updating)]
  

  Bayesian Deep Learning Recommender Systems

• Relational Collaborative Topic Regression for Recommender Systems.
  Hao Wang, Wu-Jun Li.
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 27(5): 1343-1355, 2015.
  [pdf] [data]
  

  Recommender Systems Graph & Relational Learning

• Deep Learning and the Weather Forecasting Problem -- Precipitation Nowcasting.
  Zhihan Gao, Xingjian Shi, Hao Wang, Dit-Yan Yeung, Wang-chun Woo, and Wai-Kin Wong.
  Deep Learning for the Earth Sciences: A Comprehensive Approach to Remote Sensing, Climate Science and Geosciences, G. Camps-Valls, D. Tuia, X.X. Zhu, and M. Reichstein (eds.), Wiley & Sons, 2021.
  [pdf]
  

  Vision