PeopleofSuperintelligence

Researcher

Ricky T. Q. Chen

Also known as Ricky Tian Qi Chen

Ricky Chen is a machine learning researcher who works on continuous-time and flow-based generative models, including Neural ODEs and flow matching. With David Duvenaud and colleagues at the University of Toronto and the Vector Institute, he co-wrote Neural Ordinary Differential Equations, which won a NeurIPS 2018 Best Paper award. In 2022 he co-wrote Flow Matching for Generative Modeling with Yaron Lipman and colleagues. Flow Matching on General Geometries, written with Lipman, received an Outstanding Paper Honorable Mention at ICLR 2024, and he presented a NeurIPS 2024 tutorial on flow matching with Lipman and Heli Ben-Hamu. He is a research scientist at Meta in Menlo Park, working on Muse Image and Muse Video.

Now at
Meta

Timeline

  1. 2018

    Neural ODEs win Best Paper

    As a University of Toronto student at the Vector Institute, he writes Neural Ordinary Differential Equations with Yulia Rubanova, Jesse Bettencourt and David Duvenaud; the models parameterize the derivative of the hidden state with a neural network and compute outputs with a black-box differential equation solver. The paper receives a Best Paper award at NeurIPS 2018, and he shares the Best Student Paper award at the Advances in Approximate Bayesian Inference workshop for FFJORD with Will Grathwohl and Jesse Bettencourt.

  2. 2019–2021

    Residual flows and event functions

    In 2019, he co-writes Residual Flows for Invertible Generative Modeling with Jens Behrmann, David Duvenaud and Jörn-Henrik Jacobsen, a NeurIPS spotlight. In 2021, he publishes Neural Spatio-Temporal Point Processes and Learning Neural Event Functions for Ordinary Differential Equations at ICLR with Brandon Amos and Maximilian Nickel of Facebook AI Research; the first paper is work done while he is at Facebook AI Research.

  3. 2022–2023

    Flow Matching for Generative Modeling

    In October 2022, he and Yaron Lipman, Heli Ben-Hamu, Maximilian Nickel and Matt Le post Flow Matching for Generative Modeling, a simulation-free approach for training continuous normalizing flows by regressing vector fields of fixed conditional probability paths. The paper is a spotlight at ICLR 2023.

  4. 2024

    An ICLR honorable mention

    Flow Matching on General Geometries, written with Yaron Lipman, receives an Outstanding Paper Honorable Mention at ICLR 2024. The paper proposes Riemannian Flow Matching, a framework for training continuous normalizing flows on manifolds.

  5. December 2024

    A flow matching tutorial and guide

    He presents the 2024 NeurIPS tutorial Flow Matching for Generative Modeling with Yaron Lipman and Heli Ben-Hamu. In December 2024, he is one of ten authors of Flow Matching Guide and Code, a review of flow matching with a PyTorch package.

  6. 2025

    Generator, adjoint and edit flows

    At ICLR 2025, he co-authors Generator Matching, which covers generative modeling with arbitrary Markov processes, and Adjoint Matching, a method for fine-tuning flow and diffusion models. At NeurIPS 2025, he co-authors Edit Flows: Flow Matching with Edit Operations.

  7. As of October 2026

    Muse Image and Muse Video

    He is a research scientist at Meta in Menlo Park, where he works from data to post-training for Muse Image and Muse Video, Meta Superintelligence Labs' 2026 models, using multimodal reinforcement learning. His earlier research there covers foundations of generative modeling, including scaling laws and new capabilities for multimodal generation.

Career

  1. NowMetaResearch Scientist

Education

  1. University of Toronto

From the biography.

  1. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Meta. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  2. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Meta. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.
  3. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Meta. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.
  4. 22 of 133 people shaping AI with a former OpenAI role now work at AnthropicIncludes Meta. Our estimates of where OpenAI recruits came from and where 133 people with former OpenAI roles work now, including the companies and labs they founded.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Ricky T. Q. Chen yet. Send us a free-licensed photo.

  1. Ricky T. Q. Chen rtqichen.github.io. Checked 22 October 2026.
  2. Vector Researchers Win Top Honours at NeurIPS 2018 vectorinstitute.ai. Checked 22 October 2026.
  3. Neural Ordinary Differential Equations papers.neurips.cc. Checked 22 October 2026.
  4. Neural Spatio-Temporal Point Processes ar5iv.labs.arxiv.org. Checked 22 October 2026.
  5. Flow Matching for Generative Modeling arxiv.org. Checked 22 October 2026.
  6. ICLR 2024 Awards iclr.cc. Checked 22 October 2026.
  7. Flow Matching on General Geometries arxiv.org. Checked 22 October 2026.
  8. Flow Matching for Generative Modeling (NeurIPS 2024 tutorial) neurips.cc. Checked 22 October 2026.
  9. Flow Matching Guide and Code arxiv.org. Checked 22 October 2026.