Tian Xie

Researcher @ Microsoft Research. Previously @ MIT CSAIL & DMSE, DeepMind, Google X.

Find more about me in these platforms.

Welcome! I am a Senior Researcher at Microsoft Research working on AI for materials discovery. I am part of the newly founded ML for molecular simulation intiative.

Research interests: I am interested in solving the global sustainability challenges by combining machine learning and large scale molecular simulation. I believe it requires integrated innovations in three aspects: 1) designing physics motivated machine learning algorithms; 2) creating infrastructure for large scale molecular simulation; and 3) inventing new collaborative frameworks between computational and experimental experts. I work with a highly interdiscripnary team to rethink the paradigm for materials discovery, aiming for solving sustainability related problems with real-world impact.

Previously: I was a postdoc in the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT from 2020 to 2022, co-advised by Tommi Jaakkola and Regina Barzilay. I got my PhD in Materials Science and Engineering at MIT in 2020, advised by Jeffrey C. Grossman. I got my BS in Chemistry at Peking University in 2015. I was a research intern at DeepMind, working with Pushmeet Kohli and James Kirkpatrick in 2019/05. I was a research intern at Google X in 2019/02.

recent news [earlier]

2022/02 I joined Microsoft Research as a Senior Researcher. I will work on ML for materials in the newly founded molecular modeling intiative.
2021/12 I will give a contributed talk (top 2 %) about our latest CDVAE paper at the NeurIPS ML4Physics workshop on Dec. 13, 2021.
2021/10 Excited to share our latest preprint “Crystal Diffusion Variational Autoencoder for Periodic Material Generation” on arXiv. Update (2021/12): code and data are now available on our github repo.

selected publications [full list]

  1. Crystal Diffusion Variational Autoencoder for Periodic Material Generation
    Xie, Tian*†, Fu, Xiang*, Ganea, Octavian-Eugen*, Barzilay, Regina, and Jaakkola, Tommi (*: equal contribution, †: corresponding author)
    International Conference on Learning Representations (ICLR) 2021
    Contributed talk (top 2 %) at the NeurIPS 2021 ML4PS Workshop
  2. Charting Lattice Thermal Conductivity for Inorganic Crystals and Discovering Rare Earth Chalcogenides for Thermoelectrics
    Zhu, Taishan*, He, Ran*, Gong, Sheng*, Xie, Tian, Gorai, Prashun, Nielsch, Kornelius, and Grossman, Jeffrey C (*: equal contribution)
    Energy & Environmental Science 2021
  3. Accelerating the screening of amorphous polymer electrolytes by learning to reduce random and systematic errors in molecular dynamics simulations
    Xie, Tian, France-Lanord, Arthur, Wang, Yanming, Lopez, Jeffrey, Stolberg, Michael Austin, Hill, Megan, Leverick, Graham Michael, Gomez-Bombarelli, Rafael, Johnson, Jeremiah A., Shao-Horn, Yang, and Grossman, Jeffrey C.
    arXiv preprint arXiv:2101.05339 2021
    Spotlight Talk at NeurIPS 2020 ML4Molecules workshop
  4. Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials
    Xie, Tian, France-Lanord, Arthur, Wang, Yanming, Shao-Horn, Yang, and Grossman, Jeffrey C
    Nature communications 2019
  5. Machine learning enabled computational screening of inorganic solid electrolytes for suppression of dendrite formation in lithium metal anodes
    Ahmad, Zeeshan, Xie, Tian, Maheshwari, Chinmay, Grossman, Jeffrey C, and Viswanathan, Venkatasubramanian
    ACS central science 2018
  6. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties
    Xie, Tian, and Grossman, Jeffrey C
    Physical review letters 2018