I am a fourth-year PhD candidate in the College of Computer Science and Artificial Intelligence at Fudan University, advised by Prof. Xuanjing Huang and Prof. Xipeng Qiu. I am also affiliated with the Institute of Modern Languages and Linguistics.

My research interests center on the computational principles underlying human conceptual abstraction, specifically how concepts are acquired, represented, and deployed. I view concepts as key to understanding intelligence, offering an anchor for investigating learning, reasoning, and generalization across minds and machines.

I use AI and machine learning methods both to instantiate human-like conceptual abilities in computational models and to explain the mechanisms underlying those abilities. Currently, my work focuses on the capacity for conceptual representation in AI systems in comparison with humans: how concepts are learned and structured, and whether and how they are deployed during reasoning. My long-term goal is to build and understand models that learn and generalize in human-like ways under real-world constraints on time, data, and computation.

Previously, I received my B.A. in Chinese Language from Fudan University in 2022, where I began my research at the intersection of computational linguistics and AI.

Publications

• Ningyu Xu, Qi Zhang, Xipeng Qiu, and Xuanjing Huang. 2026. Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models. arXiv preprint arXiv:2602.07794. [paper] [pdf]

• Ningyu Xu, Qi Zhang, Chao Du, Qiang Luo, Xipeng Qiu, Xuanjing Huang, and Menghan Zhang. 2025. Revealing emergent human-like conceptual representations from language prediction. Proceedings of the National Academy of Sciences. [paper] [code and data]

• Ningyu Xu, Qi Zhang, Menghan Zhang, Peng Qian, and Xuanjing Huang. 2024. On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe. arXiv preprint arXiv:2402.14404. [paper] [pdf] [code]

• Ningyu Xu, Qi Zhang, Jingting Ye, Menghan Zhang, and Xuanjing Huang. 2023. Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization. In Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics. [paper] [pdf] [code]

• Ningyu Xu, Tao Gui, Ruotian Ma, Qi Zhang, Jingting Ye, Menghan Zhang, and Xuanjing Huang. 2022. Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. [paper] [pdf] [code]