Dr. Xi Peng (Peter), 彭曦

AI/ML Scientist & Educator at University of Delaware

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

Welcome! I am an Assistant Professor at University of Delaware. My research focuses on machine learning, computer vision, and safe learning system.

I'm interested in how to make AI systems more reliable and trustworthy, particularly for high-stake use in science, medicine, and autonomous driving.

I lead the Deep-REAL (Deep Robust & Explainable AI Lab) at UD. My groups publish in top-tier AI/ML venues including NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, AAAI, IJCAI, KDD, and TPAMI. According to csrankings.org, I am the top-ranked individual in the CIS Department and the second-best scholar in Computer Science at UD. 

My research are supported by NSF, DoD, CDC, MSK Cancer Center, Google Research, Snap Research, and UD. My work received prestigious awards for young investigators: NSF CAREER Award, DoD DEPSCoR Award, Google Faculty Research Award, and UD Research Foundation Award.

I earned my Ph.D. in Computer Science from Rutgers University in 2018. My advisor is the Chair and Distinguished Professor Dimitris N. Metaxas. Before that, I received my M.S. degree from the Institute of Automation, Chinese Academy of Sciences in 2011, and my B.S. degree from Beihang University in 2008. I was a full-time software engineer at Baidu (Beijing) in 2011, and summer interns at IBM Watson (NY) in 2015 and NEC Labs America (CA) in 2016.  

Research Interests

Safe Learning System: My research focuses on developing reliable, explainable, and scalable models, algorithms, and theory foundations. 

--- ICML'24, CIKM'24, ICLR'23, TMAPI'23, CVPR'22, CVPR'21, CVPR'20, NeurIPS'20, NeurIPS'19, CVPR'19, TPAMI'19

--- ECCV'24, CVPR'23, NeurIPSW'21 Best Paper, ICLR'21 Spotlight, ICCV'19 Oral, NeurIPS'19, KDD'19 Oral

--- ICML'24, ICCV'23, CVPR'22, AAAI'21, CVPR'22, CVPR'21, CVPR'20, CVPR'19

Safety-critical Applications: The goal is to pioneer safe learning systems for critical domains where safety and reliability cannot be compromised.

Top-tier AI/ML publication since joined UD in 2019 (A Full List)

[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]

[ECCV'24] DEAL: Disentangle and Localize Concept-level Explanations for VLM. [PDF] [Code]

[CIMK'24] Adaptive Cascading Network for Continual Test-Time Adaptation. [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 Oral] Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embedding. [PDF]

Students

PhD students:

Co-advise students:

Visiting student:

Undergraduate students:

Teaching