Jaemoo Choi

Postdoc @ Georgia Tech

Profile

Hi! I’m Jaemoo Choi, a postdoctoral researcher in the FLAIR Lab at Georgia Tech, mentored by Prof. Yongxin Chen.

My research focuses on fundamental algorithms for generative AI and their applications across vision, language, and scientific domains such as molecular generation. I am particularly interested in diffusion models, including discrete diffusion, flow-based methods, and large language models, as well as their connections to control and dynamical systems. These days, I am especially excited about Physical AI and world models, and about building practical systems that solve real-world problems.

Previously, I was jointly affiliated with the Graduate School of Data Science at Seoul National University, where I worked with Prof. Joonseok Lee and his group. I received my Ph.D. in Mathematical Sciences and B.S. in Mathematics Education from Seoul National University.

I’m actively seeking full-time opportunities.

Contact: jchoi843 [at] gatech [dot] edu
Follow: Google Scholar | jaemoo-choi

Updates
09/2026 Excited to share our new preprint on RL for diffusion models through direct reward-based velocity matching (RVM), with results across image and video generation. Thanks to our collaborators!
  • RVM: Scaling Reinforcement Learning for Diffusion Models via Velocity Matching
09/2026 2 papers are accepted to NeurIPS.
  • EAM (Spotlight 1.3%): Efficient Adjoint Matching for Fine-tuning Diffusion Models
  • CoFi: Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
04/2026 7 papers are accepted to ICML.
  • Rethinking RL4DM: Efficient fine-tuning of diffusion models through ELBO-based policy optimization
  • QUATRO: Reward-based fine-tuning of LLMs with exact trust-region-bounded policy optimization
  • DMPO (Spotlight 2.2%): Fine-tuning diffusion LLMs through cross-entropy policy optimization combined with ELBO estimation
  • DASBS: A discrete version of Adjoint Matching and ASBS. A first-order oracle for discrete diffusion sampler
  • GSBoG: Generalized Schr\"odinger Bridge Sampler on graphs
  • ASBM: Scalable diffusion-based generative modeling through ASBS
  • MetaDNS: Meta-dynamics Discrete Neural Sampler (preprint coming soon)
01/2026 PDNS is accepted to ICLR.
  • PDNS: Proximal Diffusion Neural Sampler, a proximal cross-entropy-based diffusion sampler for both continuous and discrete state spaces
09/2025 Three papers, ASBS (Oral 0.3%), NAAS, MDNS, accepted to NeurIPS.
  • ASBS: Adjoint Schrödinger Bridge Sampler, an efficient reward-based diffusion-based sampler framework. Generalization of Adjoint Sampler
  • NAAS: Non-equilibrium Annealed Adjoint Sampler. General Schr\"odinger Bridge Sampler with Annealed Dynamics
  • MDNS: Mask Diffusion Neural Sampler, masked diffusion neural sampler via stochastic optimal control
05/2025 Two papers, OTP, UOT-UPC, accepted to ICML.
01/2025 Two papers, U-NOTB, DIOTM, accepted to ICLR.
09/2024 I have joined FLAIR, Georgia Tech as a Postdoc.
05/2024 Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport is accepted to ICML.
01/2024 Analyzing and Improving Optimal-Transport-based Adversarial Networks is accepted to ICLR.
09/2023 Unbalanced Optimal Transport Model (UOTM) is accepted to NeurIPS.
Selected Publications
(∗ Equal contribution, * Core contributors, † Equal advising. See Google Scholar for the full list.)
  1. Efficient Adjoint Matching for Fine-tuning Diffusion Models
    Jeongwoo Shin∗, Dongsoo Shin∗, Wei Guo, Yuchen Zhu, Yongxin Chen, Joonseok Lee†, Jaewoong Choi†, Jaemoo Choi†
    Advances in Neural Information Processing Systems (NeurIPS), 2026   [Spotlight 1.3%]
    arxiv
  2. Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
    Jaemoo Choi∗, Yuchen Zhu∗, Wei Guo, Petr Molodyk, Bo Yuan, Jinbin Bai, Yi Xin, Molei Tao, Yongxin Chen
    International Conference on Machine Learning (ICML), 2026
    arxiv | code
  3. QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
    Doyeon Lee, Eunyi Lyou, Hyunsoo Cho†, Sookyung Kim†, Joonseok Lee†, Jaemoo Choi†
    International Conference on Machine Learning (ICML), 2026
    arxiv
  4. Discrete Adjoint Schrödinger Bridge Sampler
    Wei Guo∗, Yuchen Zhu, Xiaochen Du, Juno Nam, Yongxin Chen†, Rafael Gómez-Bombarelli†, Guan-Horng Liu†, Molei Tao†, Jaemoo Choi∗
    International Conference on Machine Learning (ICML), 2026
    arxiv | code
  5. Generalized Schrödinger Bridge on Graphs
    Panagiotis Theodoropoulos, Juno Nam, Evangelos Theodorou†, Jaemoo Choi†
    International Conference on Machine Learning (ICML), 2026
    arxiv
  6. Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching
    Jeongwoo Shin, Jinhwan Sul, Joonseok Lee†, Jaewoong Choi†, Jaemoo Choi†
    International Conference on Machine Learning (ICML), 2026
    arxiv
  7. Proximal Diffusion Neural Sampler
    Wei Guo∗, Jaemoo Choi∗, Yuchen Zhu, Molei Tao, Yongxin Chen
    International Conference on Learning Representations (ICLR), 2026
    arxiv | code
  8. 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 | code
  9. Non-equilibrium Annealed Adjoint Sampler
    Jaemoo Choi*, Yongxin Chen, Molei Tao, Guan-Horng Liu*
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    arxiv
  10. Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan
    Jaemoo Choi, Jaewoong Choi†, Dohyun Kwon†
    International Conference on Machine Learning (ICML), 2025
    arxiv
  11. Robust barycenter estimation using semi-unbalanced neural optimal transport
    Milena Gazdieva∗, Jaemoo Choi∗, Alexander Kolesov, Jaewoong Choi, Petr Mokrov, Alexander Korotin
    International Conference on Learning Representations (ICLR), 2025
    arxiv | code
  12. Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport
    Jaemoo Choi∗, Jaewoong Choi∗, Myungjoo Kang
    International Conference on Machine Learning (ICML), 2024
    arxiv | code
  13. Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport
    Jaemoo Choi∗, Jaewoong Choi∗, Myungjoo Kang
    Advances in Neural Information Processing Systems (NeurIPS), 2023
    arxiv | code