Dr. Xi Peng (Peter), 彭曦, AI/ML Scientist & Educator
Welcome! I am a computer science faculty at the University of Delaware (UD):
Assistant Professor, Department of Computer & Information Sciences (CIS)
Resident Faculty, Data Science Institute (DSI)
Affiliate Faculty, Delaware Environmental Institute (DENIN)
Email: xipeng at udel dot edu Tel: (302) 831-2876
Office: FinTech 416C, 591 Collaboration Way, Newark, DE 19713
Google Scholar Deep-REAL Lab (Deep Robust & Explainable AI Lab)
Short Bio
Dr. Peng is leading the Deep-REAL Lab (Deep Robust & Explainable AI Lab) at the University of Delaware. His research interests primarily focus on two areas: (1) Trustworthy Machine Learning, specifically in building algorithm foundations for robustness, explainability, and scalability; and (2) AI for Sciences, for safety-critical applications in Geo and Bio domains. His group publishes on top AI/ML venues such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, AAAI, IJCAI, KDD, and TPAMI. According to csrankings.org, Dr. Peng is ranked as the top individual in the CIS department, and the second highest across the entire university. His research work has garnered recognition, including the Best Paper Award at the NeurIPS'21 MLPH workshop and the Best Student Paper Finalist at ECCV'16. His research has received support from NSF, DOD, CDC, industry awards such as Memorial Sloan Kettering Cancer Center, Google Faculty Research Award, Snap Research Award, and internal awards such as General University Research Award and University of Delaware Research Foundation Award. He received Ph.D. in Computer Science advised by Chair and Distinguished Professor Dimitris N. Metaxas from Rutgers University in 2018.
Research Interests
Trustworthy Machine Learning (methodology): I am interested in researching and developing principled models, algorithms, and theory to solve fundamental machine learning problems regarding robustness, explainability , and scalability:
Robust Optimization: handle out-of-distribution (OoD) data due to distributional shifts or exhibiting poor behavior in complex and dynamic environments.
Trustworthy Explanation: provide reasons for their decisions in a way humans can understand and can potentially lead to scientific knowledge discovery.
Collaborative Learning: manage large amounts of distributed data and complex models while ensuring data privacy or regulation compliance.
AI for Sciences (applications): Building upon established methodologies, my research aims to develop trustworthy systems that are reliable, interpretable, and scalable to use in high-stakes scientific applications:
Geo Science: Underwater acoustic data analytics; Seafloor mapping and characterization; Illicit mining detection.
Bio Medical: MRI image analytics; AI-assist prostate cancer diagnosis; Multi-modal biomechanics.
[ICML'24] Ensemble Pruning for Out-of-distribution Generalization. [PDF] [Code]
[ICML'24] Beyond Federation: Topology-aware Federated Learning for Generalization to Unseen Clients. [PDF] [Code]
[ICCV'23] Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition. [PDF] [Code]
[CVPR'23] Are Data-driven Explanations Robust against Out-of-Distribution Data? [PDF] [Code]
[ICLR'23] Topology-aware Robust Optimization for Out-of-Distribution Generalization. [PDF] [Code]
[TNNLS'23, IF=14.3] Semi-identical Twins Variational AutoEncoder for Few-Shot Learning. [PDF]
[TPAMI'22, IF=24.3] Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach. [PDF] [Code]
[TMM'22, IF=8.2] Region-aware Arbitrary-shaped Text Detection with Progressive Fusion. [PDF] [Code]
[CVPR'22] Are multimodal transformers robust to missing modality? [PDF] [Code]
[CVPR'22] Symmetry and uncertainty-aware object slam for 6dof object pose estimation. [PDF] [Code]
[NeurIPS'21W Best Paper Award] Deep learning for spatiotemporal modeling of Urbanization. [PDF] [Video-10m]
[ICLR'21 Spotlight] A good image generator is what you need for high-resolution video synthesis. [PDF] [Video-10m] [Code]
[CVPR'21] Uncertainty-guided Model Generalization to Unseen Domains. [PDF] [Video-5m] [Code]
[CVPR'21 Oral] Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization. [PDF] [Video-5m] [Code]
[AAAI'21] Multimodal learning with severely missing modality. [PDF] [Video-60s] [Video-15m] [Code]
[NSDI'21] Adapting Wireless Mesh Network Configuration from Simulation to Reality via Deep Learning-based Domain Adaptation. [PDF]
[IJCV'20, IF=11.5] Towards image-to-video translation: A structure-aware approach via multi-stage generative adversarial networks. [PDF]
[NeurIPS'20] Maximum-entropy adversarial data augmentation for improved generalization and robustness. [PDF] [Code]
[CVPR'20] Learning to learn single domain generalization. [PDF] [Video-60s] [Code]
[CVPR'20] Knowledge as priors: Cross-modal knowledge generalization for datasets without superior knowledge. [PDF] [Video-60s]
[TPAMI'19, IF=24.3] Towards Efficient U-Nets: A Coupled and Quantized Approach. [PDF]
[NeurIPS'19] Semantic-guided multi-attention localization for zero-shot learning. [PDF]
[NeurIPS'19] Rethinking kernel methods for node representation learning on graphs. [PDF] [Code]
[ICCV'19 Oral] AdaTransform: Adaptive Data Transformation. [PDF]
[CVPR'19] Semantic graph convolutional networks for 3d human pose regression. [PDF]
[KDD'19] Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embedding. [PDF]
Students
PhD students:
Fengchun Qiao, PhD, (2020 Spring-):
Previous: Chinese Academy of Sciences
Pub: CVPR'20, CVPR'21, TPAMI'21, NeurIPS'22W, ICLR'23, CVPR'23, ICML'24
Mengmeng Ma, PhD, (2020 Fall-):
Previous: University of Southern California
Pub: AAAI'21, CVPR'22, CVPR'23, ICML'24
Tang Li, PhD, (2020 Fall-):
Previous: George Washington University
Pub: NeurIPS'21W Best Paper, CVPR'23, ICML'24
Nathaniel Merrill, PhD, (Co-advise 2021 Fall-):
Previous: University of Delaware
Pub: ICRA'21, CVPR'22
Qitong Wang, PhD, (2021 Fall-):
Previous: Boston University
Pub: CVPR'20W, ICIP'21, CVIU'22, TMM'22, ICCV'23
Kien X. Nguyen, PhD, (2021 Fall-):
Previous: Texas Christian University
Pub: IPCCC'20, ICME'21, CVIU'23
Jeffrey Peng, PhD, (2024 Spring-)
Previous: Columbia University
Ali Abbasi, PhD, (defer)
Visiting student:
Ricardo Santos, PhD, Universidade NOVA de Lisboa (Portugal), 2023-2024
Undergraduate students:
VIP Research (2024 Spring): Jakeb Miburn, Coleman Walsh, Furdeen Hasan, Jonathan Ma, Michael Lutz
Amani A. Kiruga (Junior): Paul D. Amer Meritorious Award; MIT 2023 Summer Research
Wenxuan Li (Senior): Dean's list; now JHU
Ruoxi Jin (Senior): Dean's list
Jonathan Ma (Junior)
Teaching
Undergraduate-Level: CISC484: Intro to Machine Learning
2019 Fall; 2021 Spring; 2021 Fall; 2022 Fall; 2022 Spring
Graduate-Level: CISC684: Intro to Machine Learning
2022 Fall; 2023 Fall; 2024 Spring; 2024 Fall
Advanced Graduate-Level: CISC889: Advanced Topics in Machine Learning and Deep Neural Networks
2020 Spring; 2020 Fall; 2022 Spring
Awards & Sponsors
National Science Foundation (NSF)
Department of Defense (DOD)
Centers for Disease Control and Prevention (CDC)
Memorial Sloan Kettering Cancer Center (MSKCC)
Google Faculty Research Award
Snap Research Award
General University Research (GUR) Award
University of Delaware Research Foundation (UDRF) Award
Intellectual Neighborhood Accelerator Program (InAccelerator) Award
Artificial Intelligence Center of Excellence (AICoE) Seed Grant
Data Science Institute (DSI) Seed Grant