Scholar
Guan-Horng Liu
Google Scholar ID: 2Dt0VJ4AAAAJ
Fundamental AI Research (FAIR), Meta
Citations & Impact
Citations
1,146
H-index
14
i10-index
18
Publications
20
Co-authors
15
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Adjoint Schrödinger Bridge Sampler (ASBS)' accepted to NeurIPS 2025 with Oral presentation (top 0.3%).
- Four papers—ASBS, NAAS, 3MSBM, and MDNS—accepted to NeurIPS 2025.
- Co-organized NeurIPS 2024 Workshop on Frontiers in Probabilistic Inference.
- Co-organized ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling.
- Co-organized ICML 2023 Workshop on New Frontiers in Learning, Control, and Dynamical Systems.
Background
- Research Scientist at FAIR (Meta AI), NYC.
- Studies fundamental algorithms for learning diffusion models with optimality structures.
- Actively contributes to nonlinear diffusion models, mainly Schrödinger Bridge and Mirror Diffusion.
- Interested in integrating optimality/domain structures into diffusion and flow models to enhance theoretical understanding and develop large-scale algorithms for novel applications.
- Combines dynamic optimal transport, stochastic optimal control, and statistical physics in foundational research.
- Applications include generative modeling, image restoration, unpaired image translation, watermarked generation, opinion depolarization, and single-cell RNA sequencing.
