Yaqi Xie

Postdoctoral Fellow of Carnegie Mellon University (CMU).

I am currently a postdoctoral researcher at Carnegie Mellon University (CMU) in the Robotics Institute advised by Prof. Katia Sycara. Before that, I received my Ph.D. in Computer Science from National University Singapore (NUS), where I was fortunated to be advised by Prof. Harold Soh.

My work centers on Human-AI Synergy through neural-symbolic fusion, bridging the complementary strengths of symbolic reasoning and deep learning to create adaptive, interpretable intelligence systems. I aim to integrate structured domain knowledge with neural architectures to enhance robustness, efficiency, and trustworthiness in dynamic environments. My research applications span perception, decision-making, and generative models.

In the long run, I strive to build adaptive AI agents that not only learn from data but also incorporate human knowledge and feedback, work seamlessly with humans, and align with human needs to enhance everyday life.

Feel free to contact me if you are interested in my research and want to discuss relevant research topic or potential collaborations!

news

Oct 2025 I’m excited to be on the faculty job market this year and would love to connect!
Feb 2023 I joined Carnegie Mellow University (CMU) as a postdoctoral fellow.

selected publications

For a complete list of publications, please visit my Google Scholar page.

  1. NeurIPSSpotlight (3%)
    Thought Communication in Multiagent LLMs
    Yujia Zheng, Zhuokai Zhao, Zijian Li, Yaqi Xie, Mingze Gao, Lizhu Zhang, and Kun Zhang
    In Advances in Neural Information Processing Systems (NeurIPS) 2025
  2. NeurIPS
    Adaptively Coordinating with Novel Partners via Learned Latent Strategies
    Benjamin Li, Shuyang Shi, Lucia Romero, Huao Li, Yaqi Xie, Woojun Kim, Stefanos Nikolaidis, Charles Michael Lewis, Katia P. Sycara, and Simon Stepputtis
    In Advances in Neural Information Processing Systems (NeurIPS) 2025
  3. RSS WorkshopBest Paper
    Modeling Latent Partner Strategies for Adaptive Zero-Shot Human-Agent Collaboration
    Benjamin Li, Shuyang Shi, Lucia Romero, Huao Li, Yaqi Xie, Woojun Kim, Stefanos Nikolaidis, Michael Lewis, Katia Sycara, and Simon Stepputtis
    In Robotics: Science and Systems (RSS) GenAI-HRI Workshop 2025
  4. ICCV
    ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models
    Zifu Wan, Ce Zhang, Silong Yong, Martin Q Ma, Simon Stepputtis, Louis-Philippe Morency, Deva Ramanan, Katia Sycara, and Yaqi Xie
    In International Conference on Computer Vision (ICCV) 2025
  5. ACL
    InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning
    Zifu Wan, Yaqi Xie, Ce Zhang, Zhiqiu Lin, Zihan Wang, Simon Stepputtis, Deva Ramanan, and Katia Sycara
    In Annual Meeting of the Association for Computational Linguistics (ACL) 2025
  6. ICLR
    Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
    Ce Zhang, Zifu Wan, Zhehan Kan, Martin Q. Ma, Simon Stepputtis, Deva Ramanan, Russ Salakhutdinov, Louis-Philippe Morency, Katia Sycara, and Yaqi Xie
    In International Conference on Learning Representations (ICLR) 2025
  7. ICLR
    OMG: Opacity Matters in Material Modeling with Gaussian Splatting
    Silong Yong, Venkata Nagarjun Pudureddiyur Manivannan, Bernhard Kerbl, Zifu Wan, Simon Stepputtis, Katia P. Sycara, and Yaqi Xie
    In International Conference on Learning Representations (ICLR) 2025
  8. AISTATS
    Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
    Xutong Zhao, and Yaqi Xie
    In International Conference on Artificial Intelligence and Statistics (AISTATS) 2025
  9. NeurIPS
    LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation
    Bowen Li, Zhaoyu Li, Qiwei Du, Jinqi Luo, Wenshan Wang, Yaqi Xie, Simon Stepputtis, Chen Wang, Katia Sycara, Pradeep Ravikumar, Alexander Gray, Xujie Si, and Sebastian Scherer
    In Advances in Neural Information Processing Systems (NeurIPS) 2024
  10. NeurIPS
    Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
    Ce Zhang, Simon Stepputtis, Katia Sycara, and Yaqi Xie
    In Advances in Neural Information Processing Systems (NeurIPS) 2024
  11. NeurIPS
    GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
    Silong Yong, Yaqi Xie, Simon Stepputtis, and Katia Sycara
    In Advances in Neural Information Processing Systems (NeurIPS) 2024
  12. RA-L, ICRAWorkshop Best Paper
    Let Me Help You! Neuro-Symbolic Short-Context Action Anticipation
    Sarthak Bhagat, Samuel Li, Joseph Campbell, Yaqi Xie, Katia Sycara, and Simon Stepputtis
    IEEE Robotics and Automation Letters (RA-L) 2024
  13. WACV
    Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation
    Zifu Wan, Pingping Zhang, Yuhao Wang, Silong Yong, Simon Stepputtis, Katia Sycara, and Yaqi Xie
    In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025
  14. IROS
    ShapeGrasp: Zero-Shot Task-Oriented Grasping with Large Language Models through Geometric Decomposition
    Samuel Li, Sarthak Bhagat, Joseph Campbell, Yaqi Xie, Woojun Kim, Katia P. Sycara, and Simon Stepputtis
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024
  15. CVPR
    HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation
    Ce Zhang, Simon Stepputtis, Joseph Campbell, Katia Sycara, and Yaqi Xie
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
  16. Preprint
    Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
    Yafei Hu, Quanting Xie, Vidhi Jain, Jonathan Francis, Jay Patrikar, Nikhil Keetha, Seungchan Kim, Yaqi Xie, Tianyi Zhang, Hao-Shu Fang, Shibo Zhao, Shayegan Omidshafiei, Dong-Ki Kim, Ali-akbar Agha-mohammadi, Katia Sycara, Matthew Johnson-Roberson, Dhruv Batra, Xiaolong Wang, Sebastian Scherer, Chen Wang, Zsolt Kira, Fei Xia, and Yonatan Bisk
    2024
  17. EMNLP
    Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models
    Simon Stepputtis, Joseph Campbell, Yaqi Xie, Zhengyang Qi, Wenxin Zhang, Ruiyi Wang, Sanketh Rangreji, Charles Lewis, and Katia Sycara
    In Empirical Methods in Natural Language Processing (EMNLP) Findings 2023
  18. NeurIPS
    Embedding Symbolic Knowledge into Deep Networks
    Yaqi Xie, Ziwei Xu, Mohan S Kankanhalli, Kuldeep S Meel, and Harold Soh
    In Advances in Neural Information Processing Systems (NeurIPS) 2019
  19. ICRA
    Embedding Symbolic Temporal Knowledge into Deep Sequential Models
    Yaqi Xie, Fan Zhou, and Harold Soh
    In IEEE International Conference on Robotics and Automation (ICRA) 2021
  20. IJRR
    Multi-task trust transfer for human–robot interaction
    Harold Soh, Yaqi Xie, Min Chen, and David Hsu
    The International Journal of Robotics Research (IJRR) 2019
  21. HRI
    Robot Capability and Intention in Trust-Based Decisions Across Tasks
    Yaqi Xie, Indu P Bodala, Desmond C. Ong, David Hsu, and Harold Soh
    In ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2019
  22. Preprint
    Translating Natural Language to Planning Goals with Large-Language Models
    Yaqi Xie, Chen Yu, Tongyao Zhu, Jinbin Bai, Ze Gong, and Harold Soh
    2023