28 citations · 74 across the 11 of their papers we have counts for
11 papers
Empowering In-Browser Deep Learning Inference on Edge Devices with Just-in-Time Kernel Optimizations
Fucheng Jia, Shiqi Jiang, Ting Cao +9
Web is increasingly becoming the primary platform to deliver AI services onto edge devices, making in-browser deep learning (DL) inference more prominent. Nevertheless, the heterog…
Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints
Wenxing Xu, Yuanchun Li, Jiacheng Liu +5
Unlike cloud-based deep learning models that are often large and uniform, edge-deployed models usually demand customization for domain-specific tasks and resource-limited environme…
PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification
Yizhen Yuan, Rui Kong, Shenghao Xie +2
Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled condit…
AutoDroid: LLM-powered Task Automation in Android
Hao Wen, Yuanchun Li, Guohong Liu +7
Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones. However, existing approaches suffer from poor scalab…
SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget
Rui Kong, Yuanchun Li, Qingtian Feng +5
Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts. However, serving MoE models on me…
AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments
Hao Wen, Yuanchun Li, Zunshuai Zhang +5
Deep learning models are increasingly deployed to edge devices for real-time applications. To ensure stable service quality across diverse edge environments, it is highly desirable…
LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup
Xiaohu Tang, Yang Wang, Ting Cao +5
On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts. To alleviate that, we propose LUT-NN, the first system to empower in…
Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
Cong Guo, Yuxian Qiu, Jingwen Leng +6
An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN). Many novel and sophisticated activation functions have been…
FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients
Jaemin Shin, Yuanchun Li, Yunxin Liu +1
Federated Learning (FL) trains a machine learning model on distributed clients without exposing individual data. Unlike centralized training that is usually based on carefully-orga…
DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing
Taesik Gong, Yewon Kim, Adiba Orzikulova +4
Many applications utilize sensors in mobile devices and machine learning to provide novel services. However, various factors such as different users, devices, and environments impa…
Representational Continuity for Unsupervised Continual Learning
Divyam Madaan, Jaehong Yoon, Yuanchun Li +2
Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual l…