Guan-Horng Liu

Research Scientist @ FAIR (Meta AI)

Hi, I am Guan-Horng Liu (I go by "Guan"), a Research Scientist in FAIR, NYC.

I study fundamental algorithms for learning diffusion models with optimality structures. I’m actively contributing to nonlinear diffusion models—mainly Schrödinger Bridge and Mirror Diffusion— and large-scale methods for applications in generative modeling, image restoration, unpaired image translation, watermarked generation, opinion depolarization, and single-cell RNA sequencing.

I’m generally interested in integrating optimality/domain structures into diffusion and flow models, with the goals of enhancing theoretical understanding and developing large-scale algorithms for novel applications. In terms of fundamental research, I combine dynamic optimal transport, stochastic optimal control, and statistical physics. I enjoy applying these tools to a variety of scientific and machine learning problems.

See my full CV here (updated in Sep 2025).

Contact: ghliu [at] meta [dot] com
Follow: Google Scholar | LinkedIn | ghliu | @guanhorng_liu

Updates
[09/2025] Adjoint Schrödinger Bridge Sampler (ASBS) accepted to NeurIPS (Oral 0.3%).
[09/2025] Four papers— ASBS, NAAS, 3MSBM, and MDNS— accepted to NeurIPS.
[07/2025] I will give a talk at MSR Generative Modeling & Sampling Seminar and Flatiron Institute.
[04/2024] I co-organize NeurIPS Workshop on Frontiers in Probabilistic Inference.
[09/2024] I have joined FAIR, Meta AI as a Research Scientist at NYC.
[04/2024] I co-organize ICML Workshop on Structured Probabilistic Inference & Generative Modeling.
[04/2023] I co-organize ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems.
Selected Publications
(∗ Equal contribution, * Core contributors, † Equal advising, ‡ Alphabetical order. See Google Scholar for the full list.)
  1. Adjoint Schrödinger Bridge Sampler
    Guan-Horng Liu*, Jaemoo Choi*, Yongxin Chen, Benjamin K. Miller, Ricky T. Q. Chen*
    Advances in Neural Information Processing Systems (NeurIPS), 2025   [Oral 0.3%]
    arxiv
  2. Non-equilibrium Annealed Adjoint Sampler
    Jaemoo Choi*, Yongxin Chen, Molei Tao, Guan-Horng Liu*
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    arxiv
  3. Momentum Multi-Marginal Schrödinger Bridge Matching
    Panagiotis Theodoropoulos, Augustinos D. Saravanos, Evangelos A. Theodorou†, Guan-Horng Liu†
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    arxiv
  4. Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
    Aaron Havens*, Benjamin Kurt Miller*, Bing Yan*, Carles DomingoEnrich, Anuroop Sriram, Brandon Wood, Daniel Levine, Bin Hu, Brandon Amos, Brian Karrer, Xiang Fu*, Guan-Horng Liu*, Ricky T. Q. Chen*
    International Conference on Machine Learning (ICML), 2025
    arxiv
  5. React-OT: Optimal Transport for Generating Transition State in Chemical Reactions
    Chenru Duan∗, Guan-Horng Liu∗, Yuanqi Du∗, Tianrong Chen, Qiyuan Zhao, Haojun Jia, Carla P. Gomes, Evangelos Theodorou, Heather J. Kulik
    Nature Machine Intelligence, 2025
    arxiv
  6. Improving Generative Model-based Unfolding with Schrödinger Bridges
    Sascha Diefenbacher‡, Guan-Horng Liu‡, Vinicius Mikuni‡, Benjamin Nachman‡, Weili Nie‡
    Physical Review D, 2024
    arxiv | code
  7. Generalized Schrödinger Bridge Matching
    Guan-Horng Liu, Yaron Lipman, Maximilian Nickel, Brian Karrer, Evangelos Theodorou, Ricky T. Q. Chen
    International Conference on Learning Representations (ICLR), 2024
    arxiv | code
  8. Mirror Diffusion Models for Constrained and Watermarked Generation
    Guan-Horng Liu, Tianrong Chen, Evangelos Theodorou†, Molei Tao†
    Advances in Neural Information Processing Systems (NeurIPS), 2023
    arxiv | code
  9. I²SB: Image-to-Image Schrödinger Bridge
    Guan-Horng Liu, Arash Vahdat, De-An Huang, Evangelos Theodorou, Weili Nie, Anima Anandkumar
    International Conference on Machine Learning (ICML), 2023
    arxiv | code | project
  10. Deep Generalized Schrödinger Bridge
    Guan-Horng Liu, Tianrong Chen, Oswin So, Evangelos Theodorou
    Advances in Neural Information Processing Systems (NeurIPS), 2022   [Oral 1.9%]
    arxiv | code
  11. Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
    Tianrong Chen∗, Guan-Horng Liu∗, Evangelos Theodorou
    International Conference on Learning Representations (ICLR), 2022
    arxiv | code
  12. Second-order Neural ODE Optimizer
    Guan-Horng Liu, Tianrong Chen, Evangelos Theodorou
    Advances in Neural Information Processing Systems (NeurIPS), 2021   [Spotlight 3.0%]
    arxiv | code
  13. Dynamic Game Theoretic Neural Optimizer
    Guan-Horng Liu, Tianrong Chen, Evangelos Theodorou
    International Conference on Machine Learning (ICML), 2021   [Long talk 3.0%]
    arxiv
  14. DDPNOpt: Differential Dynamic Programming Neural Optimizer
    Guan-Horng Liu, Tianrong Chen, Evangelos Theodorou
    International Conference on Learning Representations (ICLR), 2021   [Spotlight 3.8%]
    arxiv