Zigeng Wang
YOU?
Author Swipe
View article: Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads
Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads Open
View article: Experimental Study on Improving the Performance of Cement Mortar with Self-Synthesized Viscosity-Reducing Polycarboxylic Acid Superplasticizer
Experimental Study on Improving the Performance of Cement Mortar with Self-Synthesized Viscosity-Reducing Polycarboxylic Acid Superplasticizer Open
In this study, a viscosity-reducing polycarboxylic acid superplasticizer (VRPCE) was synthesized using methylallyl polyoxyethylene ether (HPEG), acrylic acid (AA), and maltodextrin maleic acid monoester (MDMA) as the main raw materials. Th…
View article: Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM
Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM Open
Resistive Random Access Memory (ReRAM) has emerged as a promising platform for deep neural networks (DNNs) due to its support for parallel in-situ matrix-vector multiplication. However, hardware failures, such as stuck-at-fault defects, ca…
View article: Experimental Study of Graphene Oxide on Hydration Process of Tricalcium Silicate
Experimental Study of Graphene Oxide on Hydration Process of Tricalcium Silicate Open
The effects of graphene oxide (GO) with different contents on hydration process of tricalcium silicate (C3S) were investigated in this article. The scanning electron microscopy, X-ray diffraction, thermogravimetric analysis, nitrogen desor…
View article: AutoReP: Automatic ReLU Replacement for Fast Private Network Inference
AutoReP: Automatic ReLU Replacement for Fast Private Network Inference Open
The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients' data privacy and security issues. Private inference (PI) techniques using cryptographic primitives offer a solution but often have high computation and…
View article: Towards Lossless Head Pruning through Automatic Peer Distillation for Language Models
Towards Lossless Head Pruning through Automatic Peer Distillation for Language Models Open
Pruning has been extensively studied in Transformer-based language models to improve efficiency. Typically, we zero (prune) unimportant model weights and train a derived compact model to improve final accuracy. For pruned weights, we treat…
View article: Predicting band gaps and band-edge positions of oxide perovskites using density functional theory and machine learning
Predicting band gaps and band-edge positions of oxide perovskites using density functional theory and machine learning Open
Density functional theory (DFT) within the local or semilocal density approximations, i.e., the local density approximation (LDA) or generalized gradient approximation (GGA), has become a workhorse in the electronic structure theory of sol…
View article: Multi-objective cluster based bidding algorithm for E-commerce search engine marketing system
Multi-objective cluster based bidding algorithm for E-commerce search engine marketing system Open
Search engine marketing (SEM) is an important channel for the success of e-commerce. With the increasing scale of catalog items, designing an efficient modern industrial-level bidding system usually requires overcoming the following hurdle…
View article: Deep Learning Based Page Creation for Improving E-Commerce Organic Search Traffic
Deep Learning Based Page Creation for Improving E-Commerce Organic Search Traffic Open
Organic search comprises a large portion of the total traffic for e-commerce companies. One approach to expand company's exposure on organic search channel lies on creating landing pages having broader coverage on customer intentions. In t…
View article: Simulation of Concrete Pumped in Horizontal Coil and Super High-Rise Building Based on CFD
Simulation of Concrete Pumped in Horizontal Coil and Super High-Rise Building Based on CFD Open
The Euler method of computational fluid dynamics (CFD), the Bingham constitutive relationship and the measured concrete performance indexes were combined as the basis, the horizontal coil test and super high-rise building pumping test of c…
View article: Machine Learning Techniques in Structure-Property Optimization of Polymeric Scaffolds for Tissue Engineering
Machine Learning Techniques in Structure-Property Optimization of Polymeric Scaffolds for Tissue Engineering Open
Biomaterials and biomedical implants have revolutionized the way medicine is practiced. Technologies, such as 3D printing and electrospinning, are currently employed to create novel biomaterials. Most of the synthesis techniques are ad-hoc…
View article: Against Membership Inference Attack: Pruning is All You Need
Against Membership Inference Attack: Pruning is All You Need Open
The large model size, high computational operations, and vulnerability against membership inference attack (MIA) have impeded deep learning or deep neural networks (DNNs) popularity, especially on mobile devices. To address the challenge, …
View article: Bidding via Clustering Ads Intentions: an Efficient Search Engine Marketing System for E-commerce.
Bidding via Clustering Ads Intentions: an Efficient Search Engine Marketing System for E-commerce. Open
With the increasing scale of search engine marketing, designing an efficient bidding system is becoming paramount for the success of e-commerce companies. The critical challenges faced by a modern industrial-level bidding system include: 1…
View article: An Efficient Group-based Search Engine Marketing System for E-Commerce
An Efficient Group-based Search Engine Marketing System for E-Commerce Open
With the increasing scale of search engine marketing, designing an efficient bidding system is becoming paramount for the success of e-commerce companies. The critical challenges faced by a modern industrial-level bidding system include: 1…
View article: Simulation of the Flowability of Fresh Concrete by Discrete Element Method
Simulation of the Flowability of Fresh Concrete by Discrete Element Method Open
The discrete element method (DEM) was used to establish the slump model and J-Ring model of concrete to describe the flow behavior in the slump test and J-Ring test. Then, the contact parameters of particle-particle and particle-geometry f…
View article: Experimental Investigation of MgAl‐NO<sub>2</sub> and MgAl‐CO<sub>3</sub> LDHs on Durability of Mortar and Concrete
Experimental Investigation of MgAl‐NO<sub>2</sub> and MgAl‐CO<sub>3</sub> LDHs on Durability of Mortar and Concrete Open
Two kinds of layered double hydroxides (LDHs), MgAl‐NO 2 (N‐LDH) and MgAl‐CO 3 (C‐LDH), were incorporated to study the durability of mortar and concrete. The LDH contents of mortar were 1%, 2%, and 4% by mass and the LDH contents of concre…
View article: Simulation of Motion Behavior of Concrete in Pump Pipe by DEM
Simulation of Motion Behavior of Concrete in Pump Pipe by DEM Open
In this paper, the mesocalibration test was used to measure the contact parameters (restitution coefficient, rolling friction coefficient, static friction coefficient, and surface energy) between coarse aggregate particles and mortar parti…
View article: Early Cracking Risk Prediction Model of Concrete under the Action of Multifield Coupling
Early Cracking Risk Prediction Model of Concrete under the Action of Multifield Coupling Open
Through the adiabatic temperature rise experiment, the adiabatic temperature rise of concrete with hydration time was recorded. Based on the maturity degree theory, the relationship between the hydration degree of the concrete and the equi…
View article: A novel algorithm to accurately classify metagenomic sequences
A novel algorithm to accurately classify metagenomic sequences Open
Widespread availability of next-generation sequencing (NGS) technologies has prompted a recent surge in interest in the microbiome. As a consequence, metagenomics is a fast growing field in bioinformatics and computational biology. An impo…
View article: Against Membership Inference Attack: Pruning is All You Need
Against Membership Inference Attack: Pruning is All You Need Open
The large model size, high computational operations, and vulnerability against membership inference attack (MIA) have impeded deep learning or deep neural networks (DNNs) popularity, especially on mobile devices. To address the challenge, …
View article: Novel and efficient randomized algorithms for feature selection
Novel and efficient randomized algorithms for feature selection Open
Feature selection is a crucial problem in efficient machine learning, and it also greatly contributes to the explainability of machine-driven decisions. Methods, like decision trees and Least Absolute Shrinkage and Selection Operator (LASS…
View article: Experimental-Computational Investigation of Elastic Modulus of Ultra-High-Rise Pumping Concrete
Experimental-Computational Investigation of Elastic Modulus of Ultra-High-Rise Pumping Concrete Open
Based on the ultra-high-rise pumping concrete engineering test with pumping height of 407 m and maximum pumping pressure of 19.3 MPa, the variation of elastic modulus of the pumping concrete was analyzed by experiments and computational me…
View article: Experimental-Computational Approach to Investigate Nanoindentation of Magnesium Potassium Phosphate Hexahydrate (MKP) With X-CT Technique and Finite Element Analysis
Experimental-Computational Approach to Investigate Nanoindentation of Magnesium Potassium Phosphate Hexahydrate (MKP) With X-CT Technique and Finite Element Analysis Open
The magnesium phosphate cement (MPC) is a carbon-free cementitious material, widely used in solidification of nuclear waste, heavy metals, and repair and reinforcement. The magnesium potassium phosphate hexahydrate (MgKPO4·6H2O, MKP) is th…
View article: Semi-Automated evidence synthesis in health psychology: current methods and future prospects
Semi-Automated evidence synthesis in health psychology: current methods and future prospects Open
The evidence base in health psychology is vast and growing rapidly. These factors make it difficult (and sometimes practically impossible) to consider all available evidence when making decisions about the state of knowledge on a given phe…
View article: Nanoscale insight on the durability of magnesium phosphate cement: a molecular dynamics study
Nanoscale insight on the durability of magnesium phosphate cement: a molecular dynamics study Open
The sustainable green building material magnesium phosphate cement (MPC) is widely used in the fields of solidifying heavy metals and nuclear waste and repair and reinforcement.
View article: Efficient Sequential and Parallel Algorithms for Estimating Higher Order Spectra
Efficient Sequential and Parallel Algorithms for Estimating Higher Order Spectra Open
Higher order spectra (HOS) are a powerful tool in nonlinear time series analysis and they have been extensively used as feature representations in data mining, communications and cosmology domains. However, HOS estimation suffers from high…
View article: Methodology of Evaluating Elastic Modulus of Cement Mortar Corroded in Brine
Methodology of Evaluating Elastic Modulus of Cement Mortar Corroded in Brine Open
This article creatively established a four-stage methodology to evaluate the macroscopic elastic modulus of the cement mortar corroded in brine solution. At first, the nanoindentation technique was utilized to measure the microscopic elast…
View article: Study on the improvement of water resistance of magnesium phosphate cement by steel slag
Study on the improvement of water resistance of magnesium phosphate cement by steel slag Open
Steel slag powder was used as a mixed material of magnesium phosphate cement (MPC) to improve its mechanical water resistance. The mechanism of steel slag on MPC was studied through the composition and microstructure test of MPC hydration …
View article: Study on Axial Compression Test of Corroded Reinforced Concrete Columns Reinforced by MPC Bonding CFRP
Study on Axial Compression Test of Corroded Reinforced Concrete Columns Reinforced by MPC Bonding CFRP Open
In this paper, reinforced concrete was first reinforced by magnesium phosphate cement (MPC) bonding carbon fiber sheets (CFRP). The axial compression test was conducted to evaluate the property of the MPC-CFRP reinforcement corroded reinfo…
View article: Effect of Air Entraining Agent on Uniaxial Tensile Properties of PVA-ECC
Effect of Air Entraining Agent on Uniaxial Tensile Properties of PVA-ECC Open
In this paper, polyvinyl alcohol (PVA) fiber reinforced ECC (Engineered Cementitious Composites) mortar was selected as the research object. The effect of air entraining agent on the tensile properties of PVA-ECC was studied by uniaxial te…