👨🏻‍💻 I’m a final year Ph.D. at the Arizona State University in Computer Science under the supervision of Prof. Huan Liu. Previously, I received my master’s and bachelor’s degrees from Carnegie Mellon University (CMU) and Huazhong University of Science and Technology (HUST), respectively.

🔬 My research spans human-centered AI, explainable and interpretable machine learning, foundation models, and trustworthy AI systems. I study the foundations of explainability, including intrinsic limits such as the simplicity paradox and faithfulness, as well as user-centric explanations for alignment, safety, and security. I further develop actionable explainability, designing methods where explanations actively guide model reasoning, agent decision-making, and human–AI interaction. A core part of my work focuses on interdisciplinary impact, creating explainable and reliable AI algorithms that advance applications in healthcare, computational bioinformatics, social science, and robotics.

📽️ I am on the job market for the 2025-2026 cycle. If you believe I might be a good fit for your institution or organization, I’d love to connect! — please feel free to reach out at ztan36[AT]asu.edu.

News and Updates

• 2025.11: [Award] 🎉 Our paper on “CAND: Cross-Domain Ambiguity Inference for Early Detecting Nuanced Illness Deterioration” is honored with the Best Paper Award at Time Series for Health Workshop of NeurIPS 2025! Congradulations to the all the co-authors!
• 2025.11: [Paper] 🎉 One paper is accepted to ICWSM 2026! See you in Los Angeles (maybe)!
• 2025.11: [Paper] 🎉 Two papers are accepted to AAAI 2026, including one Oral! See you in Singapore (maybe)!
• 2025.11: [Paper] 🎉 Two papers are accepted to IEEE BigData 2025! See you in Macau (maybe)!
• 2025.11: [Tutorial] Presented a tutorial on “Explainablity of LLMs” at ICDM 2025 in Washington, D.C.! Nice to Meet you all! 👉 Click to view the slides (Google Drive) with a request
• 2025.10: [Tutorial] 🎉 One Tutorial on “Explainablity of LLMs” is accepted to WSDM 2026! See you in Boise (definitely)!
• 2025.09: [Invited Talk] Gave invited Talk at ASU Osher Lifelong Learning Institute (OLLI) on “How Smart Is Today’s AI: An Introduction to Chatbots and Digital Assistants”; delivered a public lecture to 140+ senior and lifelong learners across the U.S., introducing practical uses of LLMs for daily life and digital literacy. Many thanks to the hosts!
• 2025.09: [Paper] 🎉 Two papers are accepted to CIKM 2025! See you in Seoul (maybe)!
• 2025.09: [Guest Lecture] Gave invited lectures titled “LLMs and Safety: Securing AI Systems and Harnessing AI for Human Safety” at UNC Chapel Hill, NC State, and UNC Charlotte! Many thanks to the hosts!
• 2025.09: [Invited Talk] Gave an invited Talk at Intuit AI on “Securing and Governing Large Language Model Ecosystems: From Model Outputs to Multi-Agent Systems”; presented safety, accountability, and governance frameworks for LLMs in enterprise settings as part of Intuit’s internal AI research series.
• 2025.08: [Paper] 🎉 Seven papers are accepted at EMNLP Main 2025, including two Orals! See you in Suzhou (maybe)!
• 2025.08: [Tutorial] 🎉 One Tutorial on “Explainablity of LLMs” is accepted to ICDM 2025! See you in Washington, D.C. (definitely)!
• 2025.08: [Paper] 🎉 Three papers are accepted at NeurIPS 2025! See you in San Diego (definitely)!
• 2025.07: [Workshop] 🎉 We are hosting The 1st Lock-LLM Workshop: Prevent Unauthorized Knowledge Use from LLMs at NeurIPS 2025! See you in San Diego!
• 2025.07: [News, Patent] 🎉 My ACL paper on “Memory Management for LLM Agents” during internship at Google is reported by Google Cloud! Received an invitation on filing a Patent from Google!
• 2025.05: [Paper] 🎉 Three papers are accepted at ACL Main 2025 [including one finished at Google Cloud Research], with two accepted as Orals! See you in Vienna (maybe)!
• 2025.05: [Paper] 🎉 One paper is accepted at KDD 2025 Applied Data Science Track! See you in Toronto (maybe)!
• 2025.05: [Award] 🎉 My PAKDD Best Award Paper on “Interpreting Pretrained Language Models via Concept Bottlenecks” is invited to be submitted to IJCAI Best Paper Track! See you in Montreal (maybe)!
• 2025.05: [Paper] 🎉 Two papers are accepted at ICML 2025! See you in Vancouver (maybe)!
• 2025.03: [Award] 🎉 One paper is accepted at AMIA Informatics Summit 2025 with Marco Ramoni Distinguished Paper Award.
• 2025.01: [Paper] 🎉 One paper is accepted at ICLR 2025 as Spotlight! See you in Singapore (maybe)!
• 2024.12: [Paper] 🎉 Two papers are accepted at AAAI 2025 as Orals! See you in Philadelphia (definitely)!