Jung-Eun Kimمشاهده پروفایل
استادیار
Jung-Eun Kim is an Assistant Professor in the Department of Computer Science at North Carolina State University, where she conducts research at the intersection of artificial intelligence, machine learning, and cyber-physical systems. Her work focuses on creating trustworthy, interpretable, and efficient AI systems, particularly for safety-critical applications. Education: Ph.D. in Computer Science, University of Illinois at Urbana-Champaign (2017) M.S. in Computer Science and Engineering, Seoul National University (2009) B.S. in Computer Science and Engineering, Seoul National University (2007) Dr. Kim's research primarily investigates how to make AI systems more trustworthy, interpretable, and efficient, with particular emphasis on understanding failure modes, safety risks, vulnerabilities, and biases in deep learning models. Her work bridges theoretical understanding with practical applications in safety-critical systems. She explores how efficiency considerations interact with these issues, seeking to fundamentally anatomize neural networks to understand what causes failure modes and how to mitigate them. Her approach has been described as 'like a heart surgeon, we open the heart of a neural network architecture, look into it, interpret it, and cure it.' Her recent publications demonstrate a strong focus on safety alignment in large language models, mitigation of spurious correlations, privacy preservation against membership inference attacks, and sustainable AI development. Her work spans theoretical foundations of trustworthy AI while addressing practical challenges in model deployment, particularly for resource-constrained environments. She has made significant contributions to understanding how model compression techniques like pruning and quantization can inadvertently amplify biases and vulnerabilities. Scientific Awards: ICLR Spotlight, 2025 IBM Faculty award, 2023 CRA Early & Mid Career Mentoring Workshop, 2023 Cloud GPU provided by Lambda, worth $17,280, for course, Spring 2023 NeurIPS Spotlight and nomination for Best Paper Award, 2022 CRA Career Mentoring Workshop, 2022 GPU Grant by NVIDIA Corporation, 2018 The MIT EECS Rising Stars, 2015 The Richard T. Cheng Endowed Fellowship, 2015-2016 Dr. Kim actively mentors PhD students, currently advising Xingli Fang, Varun Mulchandani, Jianwei Li, Rishi Singhal, and Minseon Kim. She has secured significant research funding, including an NSF SaTC (Secure and Trustworthy Cyberspace) grant as Co-PI for 'Partition-Oblivious Real-Time Hierarchical Scheduling' ($281,629.00, 2022-2024). Her research has also been supported by an NVIDIA GPU Grant and cloud resources from Lambda. She serves on program committees for top AI conferences including ICLR, ICML, NeurIPS, AAAI, and IJCAI, and has held roles such as Publicity Chair for IJCAI 2024. Her research group focuses on developing methods to make AI systems more trustworthy, interpretable, and efficient, with particular attention to safety-critical applications. The group investigates how to identify and mitigate failure modes in neural networks while maintaining efficiency, exploring the fundamental relationship between model architecture, safety risks, and computational constraints.
