Search Results for author:
Found 38 papers, 15 papers with code
Generalized Robot Learning Framework
Imitation based robot learning has recently gained significant attention in the robotics field due to its theoretical potential for transferability and generalizability.
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.
NeedleBench: Can LLMs Do Retrieval and Reasoning in 1 Million Context Window?
In evaluating the long-context capabilities of large language models (LLMs), identifying content relevant to a user's query from original long documents is a crucial prerequisite for any LLM to answer questions based on long text.
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.
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.
BiSwift: Bandwidth Orchestrator for Multi-Stream Video Analytics on Edge
To achieve this goal, we propose BiSwift, a bi-level framework that scales the concurrent real-time video analytics by a novel adaptive hybrid codec integrated with multi-level pipelines, and a global bandwidth controller for multiple video streams.
FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning
Psychiatrists diagnose mental disorders via the linguistic use of patients.
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.
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.
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.
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.
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.
AIGC Empowering Telecom Sector White Paper_chinese
Through the study of GPT, a typical representative of AIGC, the authors have analyzed how GPT empowers the telecom sector in the form of scenarios, discussed the gap between the current GPT general model and telecom services, proposed for the first time a Telco Augmented Cognition capability system, provided answers to how to construct a telecom service GPT in the telecom sector, and carried out various practices.
6G Network Business Support System
6G is the next-generation intelligent and integrated digital information infrastructure, characterized by ubiquitous interconnection, native intelligence, multi-dimensional perception, global coverage, green and low-carbon, native network security, etc.
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.
LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup
On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts.
StrokeGAN+: Few-Shot Semi-Supervised Chinese Font Generation with Stroke Encoding
The effectiveness of the proposed model for the zero-shot traditional Chinese font generation is also evaluated in this paper.
Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN).
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization
In this work, we propose a fixed-length adaptive numerical data type called ANT to achieve low-bit quantization with tiny hardware overheads.
Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd Counting
Besides the lightweight models, we also show that the suggested review mechanism can be used as a plug-and-play module to further boost the performance of a kind of heavy crowd counting models without modifying the neural network architecture and introducing any additional model parameter.
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
This paper proposes an on-the-fly DFQ framework with sub-second quantization time, called SQuant, which can quantize networks on inference-only devices with low computation and memory requirements.
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.
Boosting Mobile CNN Inference through Semantic Memory
Human brains are known to be capable of speeding up visual recognition of repeatedly presented objects through faster memory encoding and accessing procedures on activated neurons.
DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing
However, various factors such as different users, devices, and environments impact the performance of such applications, thus making the domain shift (i. e., distributional shift between the training domain and the target domain) a critical issue in mobile sensing.
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.
Dual-side Sparse Tensor Core
We demonstrate the feasibility of our design with minimal changes to the existing production-scale inner-product-based Tensor Core.
LEAP: TrustZone Based Developer-Friendly TEE for Intelligent Mobile Apps
ARM TrustZone is widely deployed on commercial-off-the-shelf mobile devices for secure execution.
Cryptography and Security
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.
StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
However, these deep generative models may suffer from the mode collapse issue, which significantly degrades the diversity and quality of generated results.
PaGraph: Scaling GNN Training on Large Graphs via Computation-aware Caching and Partitioning
Emerging graph neural networks (GNNs) have extended the successes of deep learning techniques against datasets like images and texts to more complex graph-structured data.
Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data
Based on the data and the platform, we conduct extensive experiments to compare the performance of state-of-the-art FL algorithms under heterogeneity-aware and heterogeneity-unaware settings.
Fast Hardware-Aware Neural Architecture Search
Unlike previous approaches that apply search algorithms on a small, human-designed search space without considering hardware diversity, we propose HURRICANE that explores the automatic hardware-aware search over a much larger search space and a two-stage search algorithm, to efficiently generate tailored models for different types of hardware.
Approximate Query Service on Autonomous IoT Cameras
Elf is a runtime for an energy-constrained camera to continuously summarize video scenes as approximate object counts.
Databases
Video Analytics with Zero-streaming Cameras
For efficiency, we advocate for these cameras to be zero streaming: capturing videos to local storage and communicating with the cloud only when analytics is requested.
A First Look at Deep Learning Apps on Smartphones
We are in the dawn of deep learning explosion for smartphones.
DeepCache: Principled Cache for Mobile Deep Vision
We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision.
