Graph neural networks (GNNs) have shown significant accuracy improvement...
Along with the fast evolution of deep neural networks, the hardware syst...
Registration of distant outdoor LiDAR point clouds is crucial to extendi...
The Serverless Computing is becoming increasingly popular due to its eas...
Graph neural networks (GNNs) are powerful tools for exploring and learni...
For many driving safety applications, it is of great importance to accur...
Transformer-based large language models (LLMs) have achieved great succe...
Monocular 3D object detection (Mono3D) in mobile settings (e.g., on a
ve...
Mobile monocular 3D object detection (Mono3D) (e.g., on a vehicle, a dro...
In-memory key-value stores (IMKVSes) serve many online applications beca...
The explosive growth of various types of big data and advances in AI
tec...
An activation function is an element-wise mathematical function and play...
Quantization is a technique to reduce the computation and memory cost of...
Post-training quantization (PTQ) attracts increasing attention due to it...
The attention mechanisms of transformers effectively extract pertinent
i...
Transformer architecture has become the de-facto model for many machine
...
Quantization of deep neural networks (DNN) has been proven effective for...
Deep learning (DL) models have achieved great success in many applicatio...
The development of cloud infrastructures inspires the emergence of
cloud...
Transformer models have achieved promising results on natural language
p...
Many of today's deep neural network accelerators, e.g., Google's TPU and...
Federated learning (FL) is a distributed machine learning paradigm that
...
Serverless computing provides fine-grain resource sharing between Cloud
...
Graph neural networks (GNNs) start to gain momentum after showing signif...
Many hardware vendors have introduced specialized deep neural networks (...
Recent research on the multi-head attention mechanism, especially that i...
Graph neural networks (GNN) represent an emerging line of deep learning
...
Network pruning can reduce the high computation cost of deep neural netw...
Deep learning is vulnerable to adversarial attacks, where carefully-craf...
While prior researches focus on CPU-based microservices, they are not
ap...
The research interest in specialized hardware accelerators for deep neur...
Database platform-as-a-service (dbPaaS) is developing rapidly and a larg...
Recently, researchers have started decomposing deep neural network model...
Forecasting the future traffic flow distribution in an area is an import...
To alleviate sparsity and cold start problem of collaborative filtering ...
Collaborative filtering often suffers from sparsity and cold start probl...
To address the sparsity and cold start problem of collaborative filterin...
We propose a reinforcement learning approach for real-time exposure cont...
Online news recommender systems aim to address the information explosion...
In online social networks people often express attitudes towards others,...
Online voting is an emerging feature in social networks, in which users ...
The goal of graph representation learning is to embed each vertex in a g...
With the growing popularity of short-form video sharing platforms such a...
Modern DRAM architectures allow a number of low-power states on individu...
The boundaries of conic polygons consist of conic segments or second
deg...