Ming Yin

Welcome to my homepage!

prof_real.jpeg

mingyin0312 at gmail dot com

Incoming Assistant Professor at Georgia Tech CSE

Senior Research Scientist at Snowflake AI

Postdoctoral Associate at Princeton ECE with Mengdi Wang

Ph.D.s in Computer Science & Statistics with Yu-Xiang Wang

B.S., University of Science and Technology of China, Mathematics

I have also spent time at Amazon AWS AI during the summers. My research focuses on understanding the foundations of sequential decision-making and applying them to real-world challenges in AI and science. For an overview, visit my Research page! I also (very occasionally) share insights and summarize key ideas from my research, along with topics of personal interest, on the Blog page. For a full list of my publications, check out the Publications page.

Always excited to exchange ideas at the frontier of AI :)

News

Aug 19, 2025 See my posts on implementing DPO and GRPO from scratch! :sparkles:
Apr 13, 2025 CRISPR-GPT is accepted to Nature Biomedical Engineering :sparkles::sparkles:
Mar 14, 2025 I delievered a presentation at the nsf cps annual pi meeting!
Feb 17, 2025 Invited as an Area Chair for NeurIPS-25.
Feb 12, 2025 Invited to speak at the prestigious 8th Workshop on Cognition & Control in March at Gainesville!
Feb 10, 2025 I will attend NSF Cyber Physical Systems PI Meeting Mar 13-14 at Nashville!
Jan 21, 2025 Excited to receive the Rising Star Award at CPAL! :sparkles::sparkles: See you at Stanford!!
Jan 19, 2025 Excited to receive the Rising Star Award at AI Symposium at KAUST! :sparkles::sparkles:
Jan 14, 2025 Our MMMU benchmark is featured by Nature news article on AI testing/evaluation! :sparkles:
Jan 7, 2025 A personal thought on Reinforcement Learning for LLMs! :sparkles::sparkles:
Jan 6, 2025 Call for Workshop&Tutorial at UMAP! Topics on User Modeling in the Era of GenAI welcomed!!
Dec 30, 2024 My RL review literature is finally out — just in time to close out 2024 on a high note :sparkles:
Dec 12, 2024 Invited as an Area Chair for ICML-25.
Oct 28, 2024 I will give a tutorial at AAAI-25 on “Essential Theories and Techniques for Offline RL”.
Oct 3, 2024 Happy to serve as the Workshop&Tutorial Co-chair for ACM UMAP, Aera Chair for AISTATS-25.
Sep 26, 2024 Four papers + One Dataset paper accetped to NeurIPS-24 :sparkles: :sparkles:
Sep 18, 2024 Invited to talk at Young Research Workshop at Cornell ORIE!
Sep 1, 2024 A new blog explaining Flow macthing for Generative AI!
May 6, 2024 Happy to serve as an Area Chair for NeurIPS-24.
May 1, 2024 Two papers accepted to icml 2024!
Apr 9, 2024 Two papers accepted to (ISIT24) IEEE International Symposium on Information Theory!
Mar 20, 2024 '’General Function Approximation in Nonstationary RL’’ accepted to IEEE Journal of JSAIT!
Feb 28, 2024 MMMU has been selected as CVPR-24 Oral & Best Paper Finalist (top 0.2%)!
Feb 12, 2024 Happy to review for the first Conference on Language Modeling.
Dec 1, 2023 Releasing MMMU, a Massive Multimodal Understand&Reasoning Benchmark for Expert AGI!:sparkles:
Oct 7, 2023 Invited review for Journal of ASA and Conference on Learning Theory [COLT-24].
Oct 7, 2023 TheoremQA accepted to EMNLP-23 main :sparkles: :sparkles:
Sep 21, 2023 Posterior Sampling with Delayed Feedback RL accpeted to NeurIPS-23 :sparkles: :sparkles:
Sep 11, 2023 Invited to join Young Researchers Workshop at Cornell University Oct 1 - Oct 3.
Aug 10, 2023 Happy to be part of the PC for MATH-AI WS, AI4science WS and review for EMNLP23, ICLR24.
Jul 1, 2023 Invited review for Machine Learning by Springer.
Jun 2, 2023 Excited to release TheoremQA to eval LLMs’ capabilities in Math, Physics, EE&CS and Finance!
Jun 1, 2023 Happy to serve for IL with Implicit Human Feedback Workshop @ ICML-23 as part of the PC.
May 16, 2023 Invited for a community committee choice session talk at 2023 Informs Annual Meeting.
May 16, 2023 Invited to join the Review Board for ACM/IMS Journal of Data Science (3-year appointment).
May 15, 2023 Happy to serve for the Neural Compression Workshop @ ICML-23 as part of the PC.
May 8, 2023 The new non-uniform misspecified linear bandit paper accepted to UAI-23! :sparkles::sparkles:
Apr 24, 2023 Two papers accepted to icml 2023!
Feb 27, 2023 Happy to serve as an Area Chair for NeurIPS-23.
Feb 15, 2023 Excited to receive Graduation Day Award at ITA-23:sparkles::sparkles: Thanks for recognizing my work!
Jan 22, 2023 Parametric Differentiable Offline RL paper accpted to ICLR-23! :sparkles::sparkles:
Jan 20, 2023 I will participate in the ITA2023 in SD! Looking forward to meeting old and new friends!
Jan 18, 2023 Happy to be a reviewer for ICML-2023, UAI-2023.
Nov 21, 2022 Instance-dependent Offline RL paper accpted to AAAI-23! Congrats to my JHU coauthors :sparkles:
Sep 16, 2022 Had a wonderful summer at AWS AI with Rasool Fakoor (and also Alex Smola) :smile:
Aug 29, 2022 Happy to be part of the PC for the 3rd (Launchpad) Offline RL Workshop at NeurIPS 2022.
Aug 16, 2022 Happy to be a reviewer for ICLR-2023, AAAI-23 and AISTATS-23.
May 15, 2022 Low-switching RL paper accepted to ICML22 and Offline SSP paper accepted to UAI22!
Mar 31, 2022 Find this thought-provoking blog by John Schulman! Great attitude!!
Mar 30, 2022 Happy to be a reviewer for NeurIPS-2022.
Feb 13, 2022 Happy to review for the new venue Transactions on Machine Learning Research (TMLR)!
Jan 21, 2022 Optimal Offline Linear Representation RL paper accepted to ICLR-2022! :sparkles: :sparkles:
Dec 19, 2021 Happy to be a reviewer for ICML-2022.
Sep 29, 2021 Three papers accepted to neurips 2021!
Aug 20, 2021 I participate in the 2nd Offline DeepRL workshop (NeurIPS 21) as part of the PC.
Jul 12, 2021 Happy to be a reviewer for ICLR-2022, AISTATS-2022.
Jun 25, 2021 There is a new blog to explain the new Optimal Uniform OPE paper!
May 13, 2021 I participate in the RL theory workshop (ICML 21) as part of the PC.
Apr 5, 2021 Happy to be a reviewer for NeurIPS-2021.
Jan 28, 2021 Oral acceptance of Uniform OPE paper to AISTATS-2021! :sparkles: :smile:

Selected publications

  1. Preprint
    MedOS: AI-XR-Cobot World Model for Clinical Perception and Action
    Yingcheng Wu, Ming Yin, Baiyu Shi, Zaixi Zhang, Di Yin, Xiaotong Wang, Youjuan Wang, Jigang Fan, Ruofan Jin, Hanchen Wang, Kejun Ying, Kuan Pang, Rebecca Rojansky, Christina Curtis, Zhenan Bao, Mengdi Wang, and Le Cong
    medRxiv preprint, 2026
    HTML
  2. Preprint
    Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning
    Ming Yin, Yuanhao Qu, Yang Ling, Le Cong, and Wang Mengdi
    arXiv preprint arXiv:2505.19501, 2025
    arXiv
  3. STS
    On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures
    Ming Yin, Mengdi Wang, and Yu-Xiang Wang
    Statistical Science Journal, 2025
    arXiv
  4. NBME
    CRISPR-GPT: LLM Agents for Automated Design of Gene-Editing Experiments
    Yuanhao Qu*, Kaixuan Huang*, Ming Yin, Kanghong Zhan, Dyllan Liu, Di Yin, William A Johnson, Xiaotong Wang, Denny Zhou, Russ Altman, Mengdi Wang*, and Le Cong*
    Nature Biomedical Engineering, 2025
    HTML
  5. NeurIPS
    A Theoretical Perspective for Speculative Decoding Algorithm
    Ming Yin, Minshuo Chen, Kaixuan Huang, and Mengdi Wang
    Advances in Neural Information Processing Systems, 2024
    arXiv
  6. NeurIPS
    NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
    Momin Haider, Ming Yin, Menglei Zhang, Arpit Gupta, Jing Zhu, and Yu-Xiang Wang
    Advances in Neural Information Processing Systems (Datasets and Benchmarks Track), 2024
    arXiv
  7. NeurIPS
    Transfer Q*: Principled Decoding for LLM Alignment
    Souradip Chakraborty, Soumya Ghosal, Ming Yin, Dinesh Manocha, Mengdi Wang, Amrit Singh Bedi, and Furong Huang
    Advances in Neural Information Processing Systems, 2024
    arXiv
  8. CVPR Best Paper Finalist
    MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
    Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen
    The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
    arXiv HTML
  9. NeurIPS
    Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
    Ming Yin*, Nikki Kuang*, Mengdi Wang, Yu-Xiang Wang, and Yian Ma
    Advances in Neural Information Processing Systems, 2023
    arXiv HTML
  10. EMNLP
    TheoremQA: A Theorem-driven Question Answering dataset
    Wenhu Chen, Ming Yin, Max Ku, Elaine Wan, Xueguang Ma, Jianyu Xu, Tony Xia, Xinyi Wang, and Pan Lu
    Conference on Empirical Methods in Natural Language Processing, 2023
    arXiv HTML
  11. ICLR
    Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient
    Ming Yin, Mengdi Wang, and Yu-Xiang Wang
    International Conference on Learning Representations, 2023
    arXiv HTML
  12. ICLR
    Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism
    Ming Yin, Yaqi Duan, Mengdi Wang, and Yu-Xiang Wang
    International Conference on Learning Representations, 2022
    arXiv HTML
  13. UAI Spotlight
    Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality
    Ming Yin*, Wenjing Chen*, Mengdi Wang, and Yu-Xiang Wang
    Uncertainty in Artificial Intelligence, 2022
    arXiv HTML
  14. NeurIPS
    Towards Instance-optimal Offline Reinforcement Learning with Pessimism
    Ming Yin, and Yu-Xiang Wang
    Advances in Neural Information Processing Systems, 2021
    arXiv HTML
  15. NeurIPS
    Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings
    Ming Yin, and Yu-Xiang Wang
    Advances in Neural Information Processing Systems (Short version at ICML RL Theory Workshop), 2021
    arXiv HTML
  16. NeurIPS
    Near-Optimal Offline Reinforcement Learning via Double Variance Reduction
    Ming Yin, Yu Bai, and Yu-Xiang Wang
    Advances in Neural Information Processing Systems (Short version at ICML RL Theory Workshop), 2021
    arXiv HTML
  17. AISTATS Oral Presentation
    Near-optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning
    Ming Yin, Yu Bai, and Yu-Xiang Wang
    International Conference on Artificial Intelligence and Statistics (Short version at Neurips 2020 Offline RL Workshop), 2021
    arXiv HTML
  18. AISTATS
    Asymptotically Efficient Off-policy Evaluation for Tabular Reinforcement Learning
    Ming Yin, and Yu-Xiang Wang
    International Conference on Artificial Intelligence and Statistics, 2020
    arXiv HTML