Zining Zhu (zzhu41)

Zining Zhu

Assistant Professor

School of Computing

Gateway Center S429
(201) 216-3573
Website

Education

  • Ph.D. (2024) University of Toronto (Computer Science)
  • B.S. (2019) University of Toronto (Engineering Science, Robotics)

Research

I direct the Explainable and Controllable AI Lab, where we research the foundations and applications of approaches that make AI explainable and controllable. The areas of research include:
- Model interpretability
- Efficient AIs
- Reasoning, explanation and AI for research
- Application of AI agents

General Information

Zining is an Assistant Professor at the Department of Computer Science at the Charles V. Schaefer Jr. School of Engineering and Science at the Stevens Institute of Technology. He directs the Explainable and Controllable AI lab. He is affiliated with the Stevens Institute for Artificial Intelligence (SIAI) and the Center for Research Toward Advancing Financial Technologies (CRAFT). Prior to joining Stevens, Zining received Ph.D. degree at the University of Toronto and Vector Institute, advised by Dr. Frank Rudzicz. His research is in Natural Language Processing and Explainable AI including understanding the mechanisms and abilities of AIs, and incorporating the findings into controlling the AIs. Zining looks forward to building safe, trustworthy and efficient agentic AIs that can assist humans discover knowledge and better perform high-stake tasks. Zining has received paper award at NAACL. He has served as Senior Area Chair for EMNLP, Area Chair for NeurIPS, ICML, and an Action Editor for ACL Rolling Review.

Experience

Applied Scientist Intern, Amazon Search Query Understanding, 2022

Institutional Service

  • SIAI Steering Committee Member
  • Computer Science Course Curriculum Member
  • Research Computing Committee Member
  • Faculty Search Committee Member

Professional Service

  • ICLR Area Chair
  • AAAI Senior Program Committee
  • EMNLP Senior Area Chair
  • NeurIPS Area Chair
  • NSF Review Panelist
  • ICML Area Chair
  • ACL Rolling Review Action Editor
  • COLM Reviewer

Professional Societies

  • AAAI – Association for the Advancement of Artificial Intelligence Member
  • ACL – Association for Computational Linguistics Member

Selected Publications

Conference Proceeding

  1. Wang, Y.; Xu, Y.; Shen, N.; Su, J.; Huang, J.; Zhu, Z. (2026). The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models. Annual Meeting of Association for Computational Linguistics (ACL). San Diego, CA: Association for Computational Linguistics.
    https://aclanthology.org/2026.acl-long.665/.
  2. Javaji, S.; Cao, Y.; Li, H.; Yu, Y.; Muralidhar, N.; Zhu, Z. (2025). Can AI Validate Science? Benchmarking LLMs on Claim→Evidence Reasoning in AI Papers. Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. Mumbai: The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.
    https://aclanthology.org/2025.ijcnlp-long.127/.
  3. Wang, H.; Zhu, Z.; Shi, F. H. (2025). Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for COmputational Linguistics.
    https://aclanthology.org/2025.emnlp-main.1057/.
  4. Niu, J.; Yu, L.; Zhu, Z.; Chen, X.; Penn, G. (2025). Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics.
    https://aclanthology.org/2025.emnlp-main.446/.
  5. Javaji, S.; Zhu, Z. (2025). What Would You Ask When You First Saw a2+ b2= c2? Evaluating LLM on Curiosity-Driven Question Generation. Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL-IJCNLP). Mumbai: The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.
    https://aclanthology.org/2025.ijcnlp-long.126/.
  6. Li, H.; Cao, Y.; Yu, Y.; Suchow, J.; Zhu, Z. (2025). Truth Neurons. KnowFM Workshop at ACL 2025. KnowFM Workshop at ACL 2025.
  7. Roewer-Després, F.; Feng, J.; Zhu, Z.; Rudzicz, F. (2025). ACCORD: Closing the Commonsense Measurability Gap. NAACL. Association for Computational LInguistics.
    https://aclanthology.org/2025.naacl-long.193/.
  8. Zhu, Z.; Chen, H.; Ye, X.; Lyu, Q.; Tan, C.; Marasovic, A.; Wiegreffe, S. (2024). Tutorial: Explanation in the Era of Large Language Models. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (vol. Volume 5: Tutorial Abstracts, pp. 19-25). Mexico City: Association for Computational Linguistics.
    https://aclanthology.org/2024.naacl-tutorials.3/.
  9. Niu, J.; Liu, A.; Zhu, Z.; Penn, G. (2024). What does the Knowledge Neuron Thesis Have to do with Knowledge?. ICLR.
    https://arxiv.org/abs/2405.02421.
  10. Sahak, E.; Zhu, Z.; Rudzicz, F. (2023). A State-Vector Framework For Dataset Effects (vol. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 15231-15245). Singapore: EMNLP.
    https://aclanthology.org/2023.emnlp-main.942/.
  11. Zhu, Z.; Shahtalebi, S.; Rudzicz, F. (2022). Predicting fine-tuning performance with probing. EMNLP. Association for Computational Linguistics.
    https://aclanthology.org/2022.emnlp-main.793.

Courses

CS 584 Natural Language Processing, CS 810 Explainable Natural Language Processing, CS 541 Artificial Intelligence