Chong Yu
YOU?
Author Swipe
View article: Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning
Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning Open
Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, primarily based on integ…
View article: Persistent Neurological Deficits in Mouse PASC Reveal Antiviral Drug Limitations
Persistent Neurological Deficits in Mouse PASC Reveal Antiviral Drug Limitations Open
Post-Acute Sequelae of COVID-19 (PASC) encompasses persistent neurological symptoms, including olfactory and autonomic dysfunction. Here, we report chronic neurological dysfunction in mice infected with a virulent mouse-adapted SARS-CoV-2 …
View article: Communication-Efficient Hybrid Federated Learning for E-health with Horizontal and Vertical Data Partitioning
Communication-Efficient Hybrid Federated Learning for E-health with Horizontal and Vertical Data Partitioning Open
E-health allows smart devices and medical institutions to collaboratively collect patients' data, which is trained by Artificial Intelligence (AI) technologies to help doctors make diagnosis. By allowing multiple devices to train models co…
View article: Boosting Residual Networks with Group Knowledge
Boosting Residual Networks with Group Knowledge Open
Recent research understands the residual networks from a new perspective of the implicit ensemble model. From this view, previous methods such as stochastic depth and stimulative training have further improved the performance of the residu…
View article: Efficient Architecture Search via Bi-level Data Pruning
Efficient Architecture Search via Bi-level Data Pruning Open
Improving the efficiency of Neural Architecture Search (NAS) is a challenging but significant task that has received much attention. Previous works mainly adopted the Differentiable Architecture Search (DARTS) and improved its search strat…
View article: Boosting Residual Networks with Group Knowledge
Boosting Residual Networks with Group Knowledge Open
Recent research understands the residual networks from a new perspective of the implicit ensemble model. From this view, previous methods such as stochastic depth and stimulative training have further improved the performance of the residu…
View article: Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend
Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend Open
Adversarial attack is commonly regarded as a huge threat to neural networks because of misleading behavior. This paper presents an opposite perspective: adversarial attacks can be harnessed to improve neural models if amended correctly. Un…
View article: SpVOS: Efficient Video Object Segmentation With Triple Sparse Convolution
SpVOS: Efficient Video Object Segmentation With Triple Sparse Convolution Open
Semi-supervised video object segmentation (Semi-VOS), which requires only annotating the first frame of a video to segment future frames, has received increased attention recently. Among existing Semi-VOS pipelines, the memory-matching-bas…
View article: Accelerating Sparse Deep Neural Networks
Accelerating Sparse Deep Neural Networks Open
As neural network model sizes have dramatically increased, so has the interest in various techniques to reduce their parameter counts and accelerate their execution. An active area of research in this field is sparsity - encouraging zero v…
View article: Self-Supervised GAN Compression
Self-Supervised GAN Compression Open
Deep learning's success has led to larger and larger models to handle more and more complex tasks; trained models can contain millions of parameters. These large models are compute- and memory-intensive, which makes it a challenge to deplo…
View article: Attention Based Data Hiding with Generative Adversarial Networks
Attention Based Data Hiding with Generative Adversarial Networks Open
Recently, the generative adversarial network is the hotspot in research and industrial areas. Its application on data generation is the most common usage. In this paper, we propose the novel end-to-end framework to extend its application t…
View article: Semi-supervised Three-dimensional Reconstruction Framework with GAN
Semi-supervised Three-dimensional Reconstruction Framework with GAN Open
Because of the intrinsic complexity in computation, three-dimensional (3D) reconstruction is an essential and challenging topic in computer vision research and applications. The existing methods for 3D reconstruction often produce holes, d…
View article: Brain Network Modeling Based on Mutual Information and Graph Theory for Predicting the Connection Mechanism in the Progression of Alzheimer’s Disease
Brain Network Modeling Based on Mutual Information and Graph Theory for Predicting the Connection Mechanism in the Progression of Alzheimer’s Disease Open
Alzheimer’s disease (AD) is a progressive disease that causes problems of cognitive and memory functions decline. Patients with AD usually lose their ability to manage their daily life. Exploring the progression of the brain from normal co…
View article: Modeling and Performance of the IEEE 802.11p Broadcasting for Intra-Platoon Communication
Modeling and Performance of the IEEE 802.11p Broadcasting for Intra-Platoon Communication Open
Road capacity, traffic safety, and energy efficiency can be extremely improved by forming platoons with a small intra-vehicle spacing. Automated controllers obtain vehicle speed, acceleration, and position through vehicular ad hoc networks…
View article: Energy-Efficient and Fault-Tolerant Evolution Models Based on Link Prediction for Large-Scale Wireless Sensor Networks
Energy-Efficient and Fault-Tolerant Evolution Models Based on Link Prediction for Large-Scale Wireless Sensor Networks Open
Wireless sensor networks (WSNs) deployed in harsh environments, i.e., battlefield and natural disasters areas, often suffer from the problems of the deliberate attack, hardware failure, and energy depletion. It is crucial to propose the fa…