Search Results for author:
Found 23 papers, 12 papers with code
AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation
Inspired by the remarkable coding abilities of recent small language models (SLMs), we propose to convert the UI task automation problem to a code generation problem, which can be effectively solved by an on-device SLM and efficiently executed with an on-device code interpreter.
Threshold Neuron: A Brain-inspired Artificial Neuron for Efficient On-device Inference
Enhancing the computational efficiency of on-device Deep Neural Networks (DNNs) remains a significant challengein mobile and edge computing.
ChainStream: An LLM-based Framework for Unified Synthetic Sensing
Many applications demand context sensing to offer personalized and timely services.
A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage
With the advent of lightweight LLM models and specially designed GPUs, on-device LLM inference has achieved the necessary accuracy and performance metrics.
LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design
Recent literature has found that an effective method to customize or further improve large language models (LLMs) is to add dynamic adapters, such as low-rank adapters (LoRA) with Mixture-of-Experts (MoE) structures.
LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation
LlamaTouch comprises three key techniques: (1) On-device task execution that enables mobile agents to interact with realistic mobile environments for task execution.
Anatomizing Deep Learning Inference in Web Browsers
The gap on mobile CPU and mobile GPU is 15. 8 times and 7. 8 times, respectively.
A Survey of Resource-efficient LLM and Multimodal Foundation Models
Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine learning lifecycle, from training to deployment.
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.
Empowering In-Browser Deep Learning Inference on Edge Devices with Just-in-Time Kernel Optimizations
Web is increasingly becoming the primary platform to deliver AI services onto edge devices, making in-browser deep learning (DL) inference more prominent.
SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget
Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts.
AutoDroid: LLM-powered Task Automation in Android
Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones.
Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints
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 environments.
PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification
However, most backdoor attacks have to modify the neural network models through training with poisoned data and/or direct model editing, which leads to a common but false belief that backdoor attack can be easily avoided by properly protecting the model.
DroidBot-GPT: GPT-powered UI Automation for Android
Given a natural language description of a desired task, DroidBot-GPT can automatically generate and execute actions that navigate the app to complete the task.
AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments
Model elastification generates a high-quality search space of model architectures with the guidance of a developer-specified oracle model.
FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients
Federated Learning (FL) trains a machine learning model on distributed clients without exposing individual data.
PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing
Vision Transformer (ViT) is known to be highly nonlinear like other classical neural networks and could be easily fooled by both natural and adversarial patch perturbations.
DistFL: Distribution-aware Federated Learning for Mobile Scenarios
Previous studies focus on the "symptoms" directly, as they try to improve the accuracy or detect possible attacks by adding extra steps to conventional FL models.
Representational Continuity for Unsupervised Continual Learning
Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge.
ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
The knowledge of a deep learning model may be transferred to a student model, leading to intellectual property infringement or vulnerability propagation.
DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection
The core of the attack is a neural conditional branch constructed with a trigger detector and several operators and injected into the victim model as a malicious payload.
Beyond the Virus: A First Look at Coronavirus-themed Mobile Malware
To facilitate future research, we have publicly released all the well-labelled COVID-19 themed apps (and malware) to the research community.
Cryptography and Security
