Yuewen Sun

Yuewen Sun

MBZUAI and CMU

I am currently a postdoctoral researcher at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) and Carnegie Mellon University (CMU), collaborating with Prof. Kun Zhang. I received my Ph.D. from Southeast University under the supervision of Prof. Changyin Sun.

My research interests include causal representation learning and reinforcement learning, with publications at top AI conferences such as NeurIPS, ICLR, and AAAI. My recent work focuses on multimodal causal representation learning and its applications in healthcare to address challenges in identifiability.

🔥 News

  • 2025.01:  🎉🎉 One paper is accepted by ICLR’25.
  • 2024.12:  🎉🎉 Two papers are accepted by NeurIPS’24.
  • 2024.05: I gave an invited talk on DataFunSummit2024.
  • 2024.01:  🎉🎉 One paper is accepted by AAAI’24.
  • 2023.04: I started postdoctoral research at MBZUAI and CMU.
  • 2023.02:  🎉🎉 One paper is published in TNNLS.
  • 2022.08:  🎉🎉 I am a top reviewer of UAI’22.
  • 2022.05:  🎉🎉 One paper is accepted by ICLR’22.

📝 First Author Publications

NeurIPS 2024
sym

Identifying Latent State-Transition Processes for Individualized RL

Yuewen Sun, Biwei Huang, Yu Yao, Donghuo Zeng, Xinshuai Dong, Songyao Jin, Boyang Sun, Roberto Legaspi, Kazushi Ikeda, Peter Spirtes, Kun Zhang

Project

  • We aim to identify the latent state-transition processes from observed state-action trajectories, facilitating the learning of personalized RL policies.
  • Theoretical identifiability is guaranteed under both finite and infinite latent factor conditions, supporting the framework’s robustness.
AAAI 2024
sym

ACAMDA: Improving Data Efficiency in Reinforcement Learning Through Guided Counterfactual Data Augmentation

Yuewen Sun, Erli Wang, Biwei Huang, Chaochao Lu, Lu Feng, Changyin Sun, Kun Zhang

Project

  • We employ counterfactual reasoning to generate augmented datasets, enabling agents to make unbiased decisions, and model causal relationships within the system to ensure adaptability across heterogeneous environments.
ICLR 2022
sym

Learning Temporally Causal Latent Processes from General Temporal Data

Weiran Yao*, Yuewen Sun*, Alex Ho, Changyin Sun, Kun Zhang

(*Equal contribution)

Project

  • We propose two provable conditions under which temporally causal latent processes can be identified from their observed nonlinear mixtures.
  • We develop a theoretically-grounded training framework that enforces the assumed conditions through proper constraints.

💼 Experience

  • 2023.04 - Now, Postdoctoral Researcher, Department of Machine Learning, MBZUAI and CMU.
  • 2021.03 - 2021.09, Internship, NEC Laboratories, China.

📖 Educations

  • 2017.09 - 2023.03, Ph.D. in Control Science and Engineering, Southeast University, China.
  • 2013.09 - 2017.06, Bachelor of Control Science and Engineering, Shandong University, China.
  • 2013.09 - 2017.06, Bachelor of Financial Mathematics and Financial Engineering, Shandong University, China.

📝 Services

  • Conference Reviewer: ICML, NeurIPS, ICLR, UAI, CLeaR.
  • Journal Reviewer: ACM Computing Surveys.
  • Session Chair: ICDM’24.

💬 Teaching and Talks

  • Invited Talk: Causal Representation Learning: Theoretical Innovations and Practical Applications, DataFunSummit, 2024.
  • Teaching Assistant: Probabilistic and Statistical Inference, MBZUAI, 2024.

🎖 Honors and Awards

  • 2022.08, Top reviewer of UAI’22.