Zining Zhu

Zining Zhu is an Assistant Professor at the Department of Computer Science at Stevens Institute of Technology, affiliated with the Stevens Institute for Artificial Intelligence (SIAI) and the Center for Research Toward Advancing Financial Technologies (CRAFT). He leads the Explainable and Controllable AI Lab, focusing on foundational and applied research in model interpretability, natural language explanations, and safe AI deployment. His work bridges theoretical advancements and practical applications in NLP and AI systems.

Education: PhD in Computer Science (2024, University of Toronto), advised by Frank Rudzicz; BS in Engineering Science (2019, University of Toronto). Prior to Stevens, he was a research intern at Amazon, Tencent, and Winterlight Labs.

Research Interests:

• Explainable AI and Model Interpretability
• Natural Language Processing and Large Language Models
• Societal Implications and Safe AI Deployments
• Knowledge Editing and Model Intervention

Publications: Recent work emphasizes explainability in LLMs, dataset effects, and financial AI applications. Key papers include NAACL’s Outstanding Paper Award-winning ACCORD and tutorials on LLM explanations.

Awards: Top Reviewer at NeurIPS (2023), Ontario Graduate Scholarship (2022-2023), and Vector Institute grants (2020-2023).

Teaching: Instructors CS 584 (Natural Language Processing) and CS 810 (Explainable NLP). Extensive TA experience at University of Toronto.

Labs: Leads the Explainable and Controllable AI Lab, fostering research into trustworthy AI systems.