Meihua Dang

mh.jpeg

Hi, I’m Meihua Dang (党美华, とう・みか). I’m a second year Ph.D. student at Stanford Computer Science advised by Professor Stefano Ermon.

Before that, I received my M.S. from UCLA advised by Professor Guy Van den Broeck.

My research interests include probabilistic methods in machine learning and deep generative models. My goal is to design generative models that not only capture the uncertainty and structures of real-world data, but also support efficient and reliable probabilistic reasoning.

publications

  1. Wallace23_preview.png
    Diffusion Model Alignment Using Direct Preference Optimization
    Bram Wallace, Meihua Dang, Rafael Rafailov, Linqi Zhou, Aaron Lou, Senthil Purushwalkam, Stefano Ermon, Caiming Xiong, Shafiq Joty, and Nikhil Naik
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
  2. Zhang2023_preview.png
    Tractable Control for Auto-regressive Language Generation
    Honghua Zhang*, Meihua Dang*, Nanyun Peng, and Guy Van den Broeck
    In Proceedings of the 40th International Conference on Machine Learning (ICML), 2023
    Oral full presentation, acceptance rate 155/6538 = 2.4%
  3. ZhuICML2023_preview.png
    Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RL
    Baiting Zhu, Meihua Dang, and Aditya Grover
    In International Conference on Learning Representations, 2023
  4. DangNeurIPS22_preview.png
    Sparse Probabilistic Circuits via Pruning and Growing
    Meihua Dang, Anji Liu, and Guy Van den Broeck
    In Advances in Neural Information Processing Systems 35 (NeurIPS), Dec 2022
    Oral full presentation, acceptance rate 201/10411 = 1.9%
  5. DangRECOMB22_preview.png
    Tractable and Expressive Generative Models of Genetic Variation Data
    Meihua Dang, Anji Liu, Xinzhu Wei, Sriram Sankararaman*, and Guy Van den Broeck*
    In Proceedings of the International Conference on Research in Computational Molecular Biology (RECOMB), May 2022
  6. DangPGM20_preview.png
    Strudel: A Fast and Accurate Learner of Structured-Decomposable Probabilistic Circuits
    Meihua Dang, Antonio Vergari, and Guy Van den Broeck
    International Journal of Approximate Reasoning, Jan 2022
  7. ChoiAAAI21_preview.png
    Group Fairness by Probabilistic Modeling with Latent Fair Decisions
    YooJung Choi, Meihua Dang, and Guy Van den Broeck
    In Proceedings of the 35th AAAI Conference on Artificial Intelligence, Feb 2021
  8. DangAAAI21_preview.png
    Juice: A Julia Package for Logic and Probabilistic Circuits
    Meihua Dang, Pasha Khosravi, Yitao Liang, Antonio Vergari, and Guy Van den Broeck
    In Proceedings of the 35th AAAI Conference on Artificial Intelligence (Demo Track), Feb 2021
  9. DangPGM20_preview.png
    Strudel: Learning Structured-Decomposable Probabilistic Circuits
    Meihua Dang, Antonio Vergari, and Guy Van den Broeck
    In Proceedings of the 10th International Conference on Probabilistic Graphical Models (PGM), Sep 2020