Code, methods & papers

Projects & publications

Large language models, differentiable physics simulation, scientific computing, and compilers. Project figures link to their full-size originals; papers link to the published source.

Selected projects

Publications

Full CV ↗
  1. Learning, Solving and Optimizing PDEs with TensorGalerkin: an efficient high-performance Galerkin assembly algorithm ↗

    Shizheng Wen, Mingyuan Chi, Tianwei Yu, Ben Moseley, Mike Yan Michelis, Pu Ren, Hao Sun, Siddhartha Mishra

    arXiv:2602.05052

  2. Multi-Head RAG: Solving Multi-Aspect Problems with LLMs ↗

    Maciej Besta, Ales Kubicek, Robert Gerstenberger, Marcin Chrapek, Roman Niggli, Patrik Okanovic, Yi Zhu, Patrick Iff, Michal Podstawski, Lucas Weitzendorf, Mingyuan Chi, Joanna Gajda, Piotr Nyczyk, Jürgen Müller, Hubert Niewiadomski, Torsten Hoefler

    arXiv:2406.05085

  3. Bi-Encoder Cascades for Efficient Image Search ↗

    Robert Hönig, Jan Ackermann, Mingyuan Chi

    ICCV Workshops · pp. 1358–1363

  4. Mining World Indicators for Analyzing and Modeling the Development of Countries ↗

    Mingyuan Chi, Hong Huang, Yu Song, Hai Jin

    ACM/IMS Transactions on Data Science · DOI: 10.1145/3488059

Technical reports

Tiga: Compiling Graph Message Passing at Scale ↗

Mingyuan Chi · Technical report / manuscript · Compiler design, automatic differentiation, memory hierarchy and evaluation.

Master’s thesis

Semantic Chunk Sparse Attention for Large Language Models ↗

Mingyuan Chi · ETH Zürich · 2024