Xingjian Bai

Undergraduate @ Oxford

PhD student @ MIT

Email: xbai AT mit.edu

Xingjian Bai

Hello! I am a first-year Ph.D. student at MIT. I received my master's and bachelor's degree in Mathematics and Computer Science from the University of Oxford. My research has focused on the intersection of classic algorithms and deep learning, covering topics such as learning-augmented algorithms and the theoretical foundations of machine learning models. I am broadly driven by research that is scientifically impactful and intellectually stimulating.

During my time at Oxford, I had the privilege of working with Prof. Jan Obloj, Prof. Christian Coester, Prof. Christian Rupprecht, and Luke Melas-Kyriazi. I also spent a rewarding summer at Stanford, collaborating with Prof. Jiajun Wu, Dr. Weiyu Liu, and Joy Hsu. Outside of my academic pursuits, I enjoy jogging and playing tennis. I also engage in algorithmic programming competitions.

Collaborators: I am eager to learn from and collaborate with individuals from diverse backgrounds. If you would like to discuss something, I would be grateful to hear from you. Please feel free to contact me via email or schedule a time to chat through Chatting Time.

News:

Oct 2024: Our paper, Unweighted Layered Graph Traversal, is accepted at SODA'25!

Jun 2024: My dissertation, Efficient and Adaptive Image Generation with Fixed Point Diffusion Models, has won the Oxford Departmental Prize for the best Computer Science project!

Feb 2024: Our paper, Fixed Point Diffusion Models, is accepted at CVPR'24!

Unweighted Layered Graph Traversal

Xingjian Bai, Christian Coester, Romain Cosson

(alphabetical order)

Symposium on Discrete Algorithms (SODA), 2025

arXiv

@misc{bai2024unweighted,
      title={Unweighted Layered Graph Traversal}, 
      author={Xingjian Bai and Christian Coester and Romain Cosson},
      year={2024},
      eprint={2404.16176},
      archivePrefix={arXiv},
      primaryClass={cs.DS}
}

Fixed Point Diffusion Models

Xingjian Bai*, Luke Melas-Kyriazi*

(*equal contribution)

Computer Vision and Pattern Recognition (CVPR), 2024

page

arXiv

code

@InProceedings{bai2024fixed,
    title={Fixed Point Diffusion Models},
    author={Xingjian Bai and Luke Melas-Kyriazi},
    booktitle = {CVPR},
    year = {2024}
}

Goodhart's Law in Reinforcement Learning

Jacek Karwowski, Oliver Hayman, Xingjian Bai, Charlie Griffin, Joar Skalse

International Conference on Learning Representations (ICLR), 2023

arXiv

@InProceedings{karwowski2023goodharts,
    title={Goodhart's Law in Reinforcement Learning}, 
    author={Jacek Karwowski and Oliver Hayman and Xingjian Bai and Klaus Kiendlhofer and Charlie Griffin and Joar Skalse},
    year={2024},
    booktitle = {ICLR},
}

Sorting with Predictions

Xingjian Bai, Christian Coester

(alphabetical order)

Conference on Neural Information Processing Systems (NeurIPS), 2023

arXiv

poster

code

@InProceedings{bai2023sorting,
    title={Sorting with Predictions}, 
    author={Xingjian Bai and Christian Coester},
    booktitle = {NeurIPS},
    year = {2023}
}

Wasserstein Distributional Robustness of Neural Networks

Xingjian Bai, Guangyi He, Yifan Jiang, Jan Obloj

(alphabetical order)

Conference on Neural Information Processing Systems (NeurIPS), 2023

arXiv

poster

code

@InProceedings{bai2023wasserstein,
    title={Wasserstein distributional robustness of neural networks}, 
    author={Xingjian Bai and Guangyi He and Yifan Jiang and Jan Obloj},
    year={2023},
    booktitle = {NeurIPS},
}

Xingjian Bai

PUBLICATIONS

Unweighted Layered Graph Traversal

Fixed Point Diffusion Models

Goodhart's Law in Reinforcement Learning

Sorting with Predictions

Wasserstein Distributional Robustness of Neural Networks

CHATTING TIME