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
Feb 8, 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.- ICLRSelf-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language ModelsIn International Conference on Learning Representations (ICLR) 2025
- Dual Prototype Evolving for Test-Time Generalization of Vision-Language ModelsIn Advances in Neural Information Processing Systems (NeurIPS) 2024
- RA-LLet Me Help You! Neuro-Symbolic Short-Context Action AnticipationIEEE Robotics and Automation Letters (RA-L) 2024
- WACVSigma: Siamese Mamba Network for Multi-Modal Semantic SegmentationIn IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025
- CVPRHiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph GenerationIn IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
- PreprintToward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis2024
- Embedding Symbolic Knowledge into Deep NetworksIn Advances in Neural Information Processing Systems (NeurIPS) 2019
- ICRAEmbedding Symbolic Temporal Knowledge into Deep Sequential ModelsIn IEEE International Conference on Robotics and Automation (ICRA) 2021
- IJRRMulti-task trust transfer for human–robot interactionThe International Journal of Robotics Research (IJRR) 2019
- HRIRobot Capability and Intention in Trust-Based Decisions Across TasksIn ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2019
- PreprintTranslating Natural Language to Planning Goals with Large-Language Models2023