PeopleofSuperintelligence

Researcher

Tian Xie

Tian Xie researches AI for materials discovery and simulation. He coauthored CGCNN during doctoral study at MIT and CDVAE during a postdoctoral role at MIT CSAIL, then joined Microsoft Research AI for Science in 2022. His work at Microsoft includes MOFDiff, MatterGen and MatterSim; he shared the 2024 Frontier of Science Award with his PhD adviser Jeffrey Grossman. He coauthored the 2025 Nature paper on MatterGen and joined MIT Technology Review’s 2025 Innovators Under 35 list; since February 2026, he is a founding member of technical staff at Project Prometheus.

Works
49
Citations
5,070
h-index
18
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2018–2020

    CGCNN during an MIT PhD

    While pursuing doctoral studies in materials science and engineering at MIT, he coauthors CGCNN in 2018, a graph neural network designed specifically for materials. In 2020, he is a fifth-year PhD candidate there, advised by Jeffrey C. Grossman.

  2. 2021–2022

    CDVAE and Microsoft Research

    At MIT CSAIL, he coauthors CDVAE in 2021 during a two-year postdoctoral role; the model learns from stable material structures and generates new materials. He joins Microsoft Research AI for Science in 2022.

  3. October 2023

    MOFDiff for carbon capture

    In October 2023, his team releases MOFDiff, a coarse-grained diffusion model for designing MOFs for carbon capture.

  4. December 2023

    Property-guided MatterGen

    He coauthors MatterGen in December 2023, a generative model for inorganic materials that enables broad property-guided design.

  5. May 2024

    MatterSim for materials simulation

    His team announces MatterSim in May 2024, an emulator for accurate and efficient materials simulation and property prediction across a broad range of elements, temperatures, and pressures.

  6. July 2024

    A Frontier of Science Award

    With his PhD adviser Jeffrey Grossman, he shares the International Congress of Basic Science’s Frontier of Science Award in July 2024 for their work on CGCNN.

  7. 2025

    MatterGen in Nature

    Nature publishes his MatterGen paper in 2025, presenting a diffusion model that generates stable, diverse inorganic materials under property constraints. MIT Technology Review names him to its 2025 Innovators Under 35 list.

  8. Since February 2026

    Founding staff at Project Prometheus

    In February 2026, he joins Project Prometheus as a founding member of technical staff, helping build a new team.

Career

  1. Since 2026Project PrometheusFounding Member of Technical Staff
  2. 2022–2025Microsoft Research
  3. 2021–2022MIT CSAILPostdoctoral Researcher

Education

  1. Massachusetts Institute of TechnologyPhD

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Tian Xie. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  2. Among employers with 30+ full-time cases, OpenAI leads primary technical role H-1B pay at $310,000, and Amazon, Google and Microsoft file 57% of all casesIncludes Microsoft. Across 440,669 certified US H-1B filings from 44 employers (FY2020–FY2026), OpenAI leads primary technical role base pay at $310,000 and xAI leads overall base pay at $290,000.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Massachusetts Institute of Technology. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  4. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Massachusetts Institute of Technology. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Tian Xie yet. Send us a free-licensed photo.

  1. Tian Xie txie.me. Checked 22 October 2026.
  2. Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties arxiv.org. Checked 22 October 2026.
  3. Physics Guided Neural Networks for the Design and Understanding of Materials idss.mit.edu. Checked 22 October 2026.
  4. AI meets materials discovery: The vision behind MatterGen and MatterSim microsoft.com. Checked 22 October 2026.
  5. Crystal Diffusion Variational Autoencoder for Periodic Material Generation arxiv.org. Checked 22 October 2026.
  6. Materials - Microsoft Research: News And Awards microsoft.com. Checked 22 October 2026.
  7. news | Tian Xie txie.me. Checked 22 October 2026.
  8. A generative model for inorganic materials design | Nature nature.com. Checked 22 October 2026.
  9. Microsoft Research AI scientist joins Bezos-backed Project Prometheus edtechinnovationhub.com. Checked 22 October 2026.