Peiqi Yu

peiqiy@andrew.cmu.edu

peiqiyu.jpg

I am a third-year Ph.D. candidate in the Intelligent Control Lab at the Department of ECE of Carnegie Mellon University, advised by Prof. Changliu Liu.

I work toward self-improving embodied agents for long-horizon robotic manipulation, with a focus on agentic robotics, neuro-symbolic reasoning, and continual learning.

I received my M.S. in Electrical and Computer Engineering from Carnegie Mellon University in May 2026 and my B.Eng. in Automation from Tsinghua University in June 2023. At Tsinghua, I worked with Prof. Jiwen Lu on computer vision.

news

Jun 25, 2025 Excited to present at the RSS Workshop on Neuro-Symbolic Packing (NeSyPack)! :sparkles:
May 22, 2025 Won First Prize ($60k) in the ICRA Competition on Bimanual Packing 🏆
Aug 12, 2024 Thrilled to join the CMU ECE PhD program! :smile:

selected publications

2026

  1. enap-pipeline.gif
    Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories
    2026
    Yiyuan Pan*, Xusheng Luo*, Hanjiang Hu, Peiqi Yu, and Changliu Liu
    Robotics: Science and Systems,
    arXiv Video Website
  2. hrc-2x.gif
    Robustifying Long-term Human-Robot Collaboration through a Multimodal and Hierarchical Framework
    2026
    Peiqi Yu*, Abulikemu Abuduweili*, Ruixuan Liu, and Changliu Liu
    IFAC Cyber-Physical & Human Systems,
    arXiv
  3. aidf-failure-detection.gif
    Autonomous Integration and Improvement of Robotic Assembly using Skill Graph Representations
    2026
    Peiqi Yu*, Philip Huang*, Chaitanya Chawla*, Guanya Shi, Jiaoyang Li, and Changliu Liu
    ICRA 2026 Workshop on Multi-Agent Robotic Systems: Real-World Collaboration and Interaction,
    arXiv Website
  4. maniskillformer.gif
    ManiSkillFormer: Demonstration-Free Compositional Manipulation via Geometric Contracts and Agentic Skill Graph
    2026
    Peiqi Yu, Mosam Dabhi, Shangtao Li, Bowei Li, Laszlo Jeni, and Changliu Liu
    Submitted to ICRA 2027,
    arXiv PDF Website
  5. koopman-teacher-student.gif
    Dynamic Neural Koopman Distillation for Real-Time Robot Control Using Diffusion Models
    2026
    Lei Zheng, Peiqi Yu, Zengqi Peng, Changliu Liu, and Armin Lederer
    arXiv preprint arXiv:2605.24924,
    arXiv Website

2025

  1. wbcd.gif
    NeSyPack: A Neuro-Symbolic Framework for Bimanual Logistics Packing
    2025
    Bowei Li*, Peiqi Yu*, Zhenran Tang, Han Zhou, Yifan Sun, Ruixuan Liu, and Changliu Liu
    RSS 2025 Workshop on Benchmarking Robot Manipulation,
    arXiv Website

2022

  1. pixel_flow_captioned.gif
    Recovering Realistic Details for Magnification-Arbitrary Image Super-Resolution
    2022
    Cheng Ma, Peiqi Yu, Jiwen Lu, and Jie Zhou
    IEEE Transactions on Image Processing,
    PDF