Xi Peng

Assistant Professor
Xi Peng
Office: 416C FinTech Innovation Hub, 591 Collaboration Way
Phone: 302-831-2876

Xi Peng

Assistant Professor

EDUCATION

PhD | 2018 | Rutgers, The State University of New Jersey

Executive Summary

Dr. Xi Peng is an Assistant Professor at the University of Delaware. His research focuses on Machine Learning, Computer Vision, and Safe Learning Systems.

He is interested in how to make AI systems safer and more reliable, particularly for high-state use in science, medicine, and autonomous systems.

Research Interests:

  • Robust Machine Learning: Tackle the out-of-distribution challenge that involves dynamic, long-tail, or previously unseen data. Our work also optimizes the modern HPC platform to manage the scaling law.
  • Explainable Machine Learning: Safeguard AI predictions with valid rationales for safety and reliability. Our works provide reasons for AI decisions in a way domain experts can understand and can potentially lead to scientific knowledge discovery.
  • Safe AI Applications: Develop safe learning systems for critical domains where safety and reliability cannot be compromised. Our group has particular expertise in safe AI for science, medicine, and autonomous systems.

According to CSRankings, Dr. Peng is recognized as the top-1 individual in the CIS department and the second-best computer science scholar of the entire university. He has been honored with prestigious research awards for young investigators:

  • NSF CAREER Award (2024)
  • DOD DEPSCoR Award (2023)
  • Google Faculty Research Award (2022)
  • General University Research Award (2022)
  • University of Delaware Research Foundation Award (2022)

Dr. Peng leads the DeepREAL (Deep Robust & Explainable AI Lab), which regularly publishes in top-tier AI and machine learning venues including NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, AAAI, IJCAI, KDD, and TPAMI. He has won a series of paper awards:

  • Best Paper Award, NeurIPSW 2021
  • Oral Presentation, CVPR 2021, acceptance rate 4.3%
  • Spotlight Presentation, ICLR 2021, acceptance rate 3.8%
  • Oral Presentation, ICCV 2019, acceptance rate 4.7%
  • Oral Presentation, KDD 2019, acceptance rate 9.2%
  • Oral Presentation, BMVC 2018, acceptance rate 4.6%
  • Best Student Paper Finalist, ECCV 2016, acceptance rate 0.4%
  • Oral Presentation, ICPR 2016, acceptance rate 14.1%
  • Oral Presentation Award, ACCV 2010, acceptance rate 3.5%

Dr. Peng’s research are generously supported by various sources including federal agencies (NSF, DOD, CDC), industrial labs (MSK, Google, Snap), and internal university funds.

Research Areas

  • Artificial Intelligence and Machine Learning
  • Computer Vision, Robotics, and Autonomous Systems
  • Vehicle Computing
  • Autonomous Vehicles
  • Connected Health