Xiaomeng Ye

Dr. Xiaomeng Ye’s research focuses on Explainable Artificial Intelligence (XAI): building AI systems that make accurate predictions while also helping people understand why those predictions were made. His current work develops NN-kNN, a retrieval-based neural learning framework that “runs like a neural network” while explaining decisions through similar past cases.

This research program has led to major recent successes, including two consecutive IJCAI main-track publications: Run Like a Neural Network, Explain Like k-Nearest Neighbor at IJCAI 2025 and NN-kNN for Regression: Accurate Prediction from Interpretable Retrieval at IJCAI 2026. IJCAI is one of the premier international conferences in artificial intelligence, making these publications significant recognition of the impact and promise of his research program. His work has also appeared in ICCBR, FLAIRS and XAI-focused workshops, and received the Best Paper Award at ICCBR 2021. Dr. Ye has served on the program committees of multiple AI conferences, including ICCBR and FLAIRS, and as ICCBR 2025 Workshop Co-chair.

A central part of Dr. Ye’s work is mentoring undergraduate students as emerging AI researchers. As of 2026 (his 4th year), he has coauthored published work with eight Berry students, reflecting his commitment to creating high-impact research opportunities at a liberal arts college. He believes that modern AI has opened a more even playing field: students from many backgrounds can make meaningful contributions if they are willing to invest the time, discipline, creativity, grit and open-mindedness required to learn deeply and build seriously.

Dr. Ye welcomes collaborations with students, academic researchers and industry partners interested in explainable AI, interpretable neural models, retrieval-based learning and trustworthy AI applications in domains where transparency and accountability matter.