• Multi-Length Skills with Priors for Reinforcement Learning 

  Jerez, Carlos; Zhang, Jun (ACM, 2025-02-20)

  Leveraging prior experience has been effective in accelerating reinforcement learning (RL). One approach for leveraging prior experience consists of learning skills, which are temporally extended sequences of actions, and ...

• Enhancing Image Restoration through Hybrid VQVAE and Transformer Architectures: A Novel Approach 

  Xue, Yake; Chen, Xia; He, Yinpan (2024-12-20)

  Image restoration is essential for enhancing the quality and utility of degraded images in various applications such as autonomous driving and robotics. Traditional convolutional neural network (CNN) approaches, while ...

• Refining Neural Network with Symbolic Regression 

  Wei, Wei; Lu, Qiang; Huang, Can; Luo, Jake (2025-07-14)

  Classical neural network (NN) compression methods, such as NN pruning and distillation, focus on reducing the NN size. However, these methods often sacrifice accuracy in the process. To address this issue, we propose a ...

• Celebrating 25 Years of Document Engineering 

  Munson, Ethan (2025-08-27)

• Saliency-Guided Lightweight Backdoor Defense for Edge Intelligence 

  Zhang, Zijian; Wu, Liang; Zeng, Zhen; Gu, Zhongshu (2025-12-03)

  The expansion of edge intelligence across diverse devices and sites significantly broadens the attack surface, making backdoor attacks a critical security threat. Existing backdoor trigger mitigation methods rely heavily ...

• Poster: A Lightweight Pruning for Mitigating Neural Network Backdoor on Edge 

  Taveira, Gabriel; Zhang, Zijian; Zeng, Zhen; Gu, Zhongshu (2025-12-03)

  Image-based neural networks are widely used across diverse applications, yet their inherent susceptibility to backdoor attacks has raised growing concerns. In particular, data-free backdoor attacks, which exploit benign ...

• How Heavy is the Edge? Resource Utilization of Edge Generative AI on Distributed AI Infrastructure 

  Wu, Liang; Zeng, Zhen; Gu, Zhongshu; Wu, Pengxia (2025-12-03)

  Distributed AI infrastructures are extensively employed in cloud industry settings to accommodate the growing demands of AI services. However, extending such infrastructures to the edge remains under exploration. This study ...

• Risk Prediction and Interpretation for Fall Events Using Explainable AI and Large Language Models 

  Luo, Jake; Khani, Masoud; Adams, Jazzmyne; Lu, Qiang; O'Connor, Kristian; Friedland, David (2025-05-16)

  Falls represent a significant public health concern, particularly among older adults, with approximately 35.6 million cases annually in the United States alone. Traditional machine learning-based fall risk prediction methods ...

• Multi-Level Explainable AI for ECG-Based Atrial Fibrillation Detection: Exploring LIME, SHAP, and Grad-CAM for Clinical Interpretation 

  Luo, Jake; Noffke, Patrick; Taleban, Amirsajjad; Sparapani, Rodney (2025-05-16)

  Atrial fibrillation (AFib) detection through ECG interpretation remains a critical yet complex task in clinical settings. While deep learning models have shown promise in automated ECG analysis, their "black box" nature ...

• Unveiling Neural Network Data Free Backdoor Threats in Industrial Control Systems 

  Zhang, Zijian; Elsharef, Isra; Zeng, Zhen (ACM, 2023-11-20)

  The neural network data-free backdoor attack is an emerging and potent threat, which requires minimal resources and does not rely on original training data to implant backdoors. This threat poses a significant risk to ...

• Navigating Daily Life: Insights from Powered Wheelchair Users on Assistive Technologies and Caregiver Support 

  Shahria, Md Tanzil; Banik, Nayan; Sunny, Md Samiul Haque; Rahman, Mohammad H (ACM, 2024-05-02)

  The increasing number of powered wheelchair users, driven by an aging global population and advancements in medical care, highlights a critical need to understand their unique experiences and challenges, particularly ...

• InArt: In-Network Aggregation with Route Selection for Accelerating Distributed Training 

  Liu, Jiawei; Zhai, Yutong; Zhao, Gongming; Xu, Hongli; Fang, Jin; Zeng, Zhen; Zhu, Ying (ACM, 2024-05-05)

  Deep learning has brought about a revolutionary transformation in network applications, particularly in domains like e-commerce and online advertising. Distributed training (DT), as a critical means to expedite model ...

• Semantics of RxJS 

  Zhao, Tian; Li, Yonglun (2022-11-11)

  RxJS is a popular JavaScript library for reactive programming in Web applications. It provides numerous operators to create, combine, transform, and filter discrete events and to handle errors. These operators may be ...

• On Equivalence of Anomaly Detection Algorithms 

  Jerez, Carlos Ivan; Zhang, Jun; Silva, Marcia R. (2022-08-08)

  In most domains anomaly detection is typically cast as an unsupervised learning problem because of the infeasability of labelling large datasets. In this setup, the evaluation and comparison of different anomaly detection ...

• Stable Matchings with Restricted Preferences: Structure and Complexity 

  Cheng, Christine T.; Rosenbaum, Will (2022-09-30)

  In the stable marriage (SM) problem, there are two sets of agents–traditionally referred to as men and women–and each agent has a preference list that ranks (a subset of) agents of the opposite sex. The goal is to find a ...

• Clinical Term Normalization Using Learned Edit Patterns and Subconcept Matching: System Development and Evaluation 

  Kate, Rohit J. (2021-01-14)

  Background: Clinical terms mentioned in clinical text are often not in their standardized forms as listed in clinical terminologies because of linguistic and stylistic variations. However, many automated downstream ...

• Criteria and Practices of Various States for the Design of Jointless and Integral Abutment Bridges 

  Tabatabai, Habib; Magbool, Hassan; Bahumdain, Ahmed; Fu, Cui (2017-06-01)

  The design of integral abutment bridges is not explicitly addressed in the U.S. bridge design specifications. Despite the lack of a specific national design standard for such bridges, their usage has grown steadily since ...

• Reliability of Bridge Superstructures in Wisconsin 

  Nabizadehdarabi, Azam (2015-08-01)

  Bridge reliability analyses form the basis of modern bridge design provisions. Such analyses are also used to evaluate bridge condition and assess future maintenance needs. The majority of these reliability assessments are ...

• Survival Analyses for Bridge Decks in Northern United States 

  Tabatabai, Habib; Lee, Chin-Wei; Tabatabai, Mohammad A (2016-06-29)

  The use of deicing salts in northern regions of the United States is a major contributor to the long-term deterioration of bridge decks. In this study, the 2008 U.S. National Bridge Inventory (NBI) records were used to ...

• From superhydrophilicity to superhydrophobicity: high-resolution neutron imaging and modeling of water imbibition through porous surfaces treated with engineered nano-coatings 

  Zemajtis, Filip; Hasan, Abul Borkot Md Rafiqul; Yetik, Ohan; Trtik, Pavel; Pillai, Krishna M.; Sobolev, Konstantin (2023-07-10)

  This paper reports on a superhydrophilic to superhydrophobic transformation of TiO2 nanoparticles doped zinc phosphate coating systems when a hydrophobic agent is applied. The objective of the reported research was to ...

View more