Wei Zhang

High-dimensional entanglement between distant atomic-ensemble memories

2016 · Light Science & Applications

Entangled quantum states in high-dimensional space show many advantages compared with entangled states in two-dimensional space. The former enable quantum communication with higher channel capacity, enable more efficient quantum-information processing and are more feasible for …

Efficient fully homomorphic encryption with circularly secure key switching process

2016 · International Journal of High Performance Computing and Networking

Fully homomorphic encryption (FHE) has important applications in cloud computing. However, almost all fully homomorphic encryption schemes share two common flaws that they all use large-scale secret keys and some operations are inefficient. In this …

A single-state semi-quantum key distribution protocol and its security proof

2016 · arXiv (Cornell University)

Semi-quantum key distribution (SQKD) can share secret keys by using less quantum resource than its fully quantum counterparts, and this likely makes SQKD become more practical and realizable. In this paper, we present a new …

Interdecadal correlation of solar activity with Tibetan Plateau snow depth and winter atmospheric circulation in East Asia

2018 · Sciences in Cold and Arid Regions

Studies on the impact of solar activity on climate system are very important in understanding global climate change. Previous studies in this field were mostly focus on temperature, wind and geopotential height. In this paper, …

APT Attack Analysis in SCADA Systems

2018 · MATEC Web of Conferences

SCADA (Supervisory Control and Data Acquisition) systems play a significant role in ICS (Industrial Control System). Safety, security and stable operation is crucial to the SCADA system. However, SCADA system currently faces many security threats, …

Development and Implementation of Innovative Practical Projects Based on Electronic Contests

2018 · Proceedings of the 2018 8th International Conference on Social science and Education Research (SSER 2018)

Based on the opportunity of college students' electronic competition, with the experience of guiding students attend the national contest of electronic practice, this paper constructed a comprehensive innovation practice project system, perfected the training course …

Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

2019

Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang, Huajun Chen. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 …

SEE: Syntax-Aware Entity Embedding for Neural Relation Extraction

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Distant supervised relation extraction is an efficient approach to scale relation extraction to very large corpora, and has been widely used to find novel relational facts from plain text. Recent studies on neural relation extraction …

Improving Domain-Adapted Sentiment Classification by Deep Adversarial Mutual Learning

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Domain-adapted sentiment classification refers to training on a labeled source domain to well infer document-level sentiment on an unlabeled target domain. Most existing relevant models involve a feature extractor and a sentiment classifier, where the …

Improving Neural Relation Extraction with Positive and Unlabeled Learning

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning. This approach first applies reinforcement learning to decide whether a sentence is positive to a …

An entanglement-based quantum network based on symmetric dispersive optics quantum key distribution

2019 · arXiv (Cornell University)

Quantum key distribution (QKD) is a crucial technology for information security in the future. Developing simple and efficient ways to establish QKD among multiple users are important to extend the applications of QKD in communication …

Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Embeddings and the Implications to Representation Learning

2020 · arXiv (Cornell University)

Human judgments of word similarity have been a popular method of evaluating the quality of word embedding. But it fails to measure the geometry properties such as asymmetry. For example, it is more natural to …

Research on Chinese Legal Document Reading Comprehension Based on Pre-Training Model

2021

We research how to read and understand Chinese legal documents. At first, we analyze the difficulties of reading comprehension of Chinese legal documents. Data imbalance exists seriously among span extraction query, yes/no query and unanswerable …

Session-Recommendation Based on Gated Neural Network to Extract Item Structure Feature Graph

2022

The issue of inaccurate user portrait recommendations for short-term conversations is solved. The classical recommendation is based on an assumption: the user's historical behavior can represent the user's stable long-term preferences, and the result is …

[Research progress on medical image dataset expansion methods].

2023 · PubMed

Computer-aided diagnosis (CAD) systems play a very important role in modern medical diagnosis and treatment systems, but their performance is limited by training samples. However, the training samples are affected by factors such as imaging …

SR-DCQCN: Combining SACK and ECN for RDMA Congestion Control

2022

In recent years, the use of RDMA in data center networks has increased significantly, with the largest deployments of the RoCEv2 protocol using the go-back-n scheme for loss recovery. However, it can waste time and …

Explainable Recommendation with Personalized Review Retrieval and Aspect Learning

2023

Hao Cheng, Shuo Wang, Wensheng Lu, Wei Zhang, Mingyang Zhou, Kezhong Lu, Hao Liao. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Knowledge-aware Collaborative Filtering with Pre-trained Language Model for Personalized Review-based Rating Prediction

2023 · arXiv (Cornell University)

Personalized review-based rating prediction aims at leveraging existing reviews to model user interests and item characteristics for rating prediction. Most of the existing studies mainly encounter two issues. First, the rich knowledge contained in the …

MEDOE: A Multi-Expert Decoder and Output Ensemble Framework for Long-tailed Semantic Segmentation

2023 · arXiv (Cornell University)

Long-tailed distribution of semantic categories, which has been often ignored in conventional methods, causes unsatisfactory performance in semantic segmentation on tail categories. In this paper, we focus on the problem of long-tailed semantic segmentation. Although …

The development and validation of pathological sections based U-Net deep learning segmentation model for the detection of esophageal mucosa and squamous cell neoplasm

2023 · Journal of Gastrointestinal Oncology

Background: Deep learning methods have demonstrated great potential for processing high-resolution images. The U-Net model, in particular, has shown proficiency in the segmentation of biomedical images. However, limited research has examined the application of deep …

Special Issue: “AI Acceleration on FPGAs”

2023 · ACM Transactions on Embedded Computing Systems

introduction Share on Special Issue: “AI Acceleration on FPGAs” Authors: Yun (Eric) Liang Peking University, Peking, People's Republic of China Peking University, Peking, People's Republic of China 0000-0002-9076-7998View Profile , Wei Zhang The Hong Kong …

Design of Automatic Identification System for Substation Monitoring Interface Based on Machine Vision

2023

Substation is one of the key nodes in building a new energy system. The level of intelligence in substations directly affects the safety and efficiency of smart grids. In order to test and evaluate the …

Quantum Enhanced Hazardous Substances Surveillance System

2024 · Quantum Engineering

Unauthorized access to hazardous substances poses a serious threat to public health. Typically, these substances, such as chemicals, are housed within warehouses or laboratory facilities, making strict control over any unauthorized entry. The control can …

Research and Development of Computational Thinking Assessment for College Students Integrating Cognitive and Non-Cognitive Abilities

2024

Currently, the tools for assessing the computational thinking(CT) abilities of college students lack comprehensive coverage, focusing only on the cognitive aspects of CT and neglecting exploration of non-cognitive abilities. In this study, through a literature …

Prediction method and simulation study of port photovoltaic power generation output power

2024

Photovoltaic power generation has the characteristics of large randomness, poor stability, and great influence by meteorological conditions. A large number of grid-connected photovoltaic power system will bring random impact to the power grid, which may …

Aspect-Enhanced Explainable Recommendation with Multi-modal Contrastive Learning

2024 · ACM Transactions on Intelligent Systems and Technology

Explainable recommender systems ( ERS ) aim to enhance users’ trust in the systems by offering personalized recommendations with transparent explanations. This transparency provides users with a clear understanding of the rationale behind the recommendations, …

Development of Smart Operation and Maintenance Platform for Distributed Large-scale Battery Energy Storage Stations Based on Cloud Edge Collaboration

2024

With the continuous growth of the installed capacity of battery storage power stations and the expansion of single station scale, the operation and maintenance level has become the key to reducing costs, increasing efficiency, and …

GAuV: A Graph-Based Automated Verification Framework for Perfect Semi-Honest Security of Multiparty Computation Protocols

2024

Proving the security of a Multiparty Computation (MPC) protocol is a difficult task. Under the current simulation-based definition of MPC, a security proof consists of a simulator, which is usually specific to the concrete protocol …

Fault Localization of Distribution Network Based on Reverse-Local Learning Based Particle Swarm Optimization Algorithm

2024

With the large-scale access of distributed generation, the power flow characteristics of distribution network have been greatly changed. The conventional fault localization methods for distribution networks are no longer applicable. To deal with the problems …

LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios

2024 · arXiv (Cornell University)

As Large Language Models (LLMs) evolve in natural language processing (NLP), their ability to stably follow instructions in long-context inputs has become critical for real-world applications. However, existing benchmarks seldom focus on instruction-following in long-context …

Exploring the Application of Large Language Models in Instrumentation and Control Engineering Education: A Questionnaire Survey and Examination Performance Analysis

2025 · European Journal of Education

ABSTRACT This study investigates the use of Large Language Models (LLMs) by undergraduates majoring in Instrumentation and Control Engineering (ICE) at University of Shanghai for Science and Technology. We conducted a questionnaire survey to assess …

Data-Enhanced Prediction with Decomposition and Amplitude-Aware Permutation Entropy in Distributed Computing Systems

2024

In recent years, distributed computing has wit-nessed widespread applications across numerous organizations. Predicting workload and computing resource data can facilitate proactive service operation management, leading to substantial improvements in quality of service and cost efficiency. …

Communication-Efficient Multi-Server Federated Learning via Over-the-Air Computation

2025 · IEEE Transactions on Mobile Computing

Thanks to the Internet of Things (IoT), there has been explosive growth in edge devices, which generate a tremendous amount of data that holds invaluable potential. However, conventional data mining and machine learning (ML) paradigms …

Incomplete Multi-View Drug Recommendation via Multi-Level Representation Learning and Curriculum Learning

2025

The drug recommendation task aims to provide effective and safe prescription decision support for clinical treatment based on patients' past Electronic Health Records (EHR). However, the prevalent phenomenon of missing views in multi-source heterogeneous EHR …

Surface Ion Trap for Fast Microwave Gates

2025 · Chips

Microwave-driven quantum logic gates in trapped-ion systems offer a scalable and laser-free alternative to optical control, with the potential for robust integration into surface-electrode trap architectures. In this work, we present a systematic design guideline …

GCPT: Gradient-aware Clustering Method for Efficient Post-Training Quantization in Large Neural Networks

2026

Large-scale neural network models have achieved outstanding performance across diverse tasks, but often come with expensive computational costs. In this paper, we propose a gradient-aware clustering method for post-training quantization (GCPT) in order to effectively …

Scientific AI systems require domain-aware robustness validation

2026 · Cell Reports Physical Science

AI has become an essential tool in many areas of scientific discovery. However, its robustness, particularly in high-stakes scientific applications, remains insufficiently understood. While adversarial vulnerabilities have been widely studied in image recognition, their implications …

R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering

2017 · arXiv (Cornell University)

In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et …

Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding

2018

Distant supervision is an effective method to generate large scale labeled data for relation extraction, which assumes that if a pair of entities appears in some relation of a Knowledge Graph (KG), all sentences containing …

Deep Matrix Factorization With Implicit Feedback Embedding for Recommendation System

2019 · IEEE Transactions on Industrial Informatics

Automatic recommendation has become an increasingly relevant problem to industries, which allows users to discover new items that match their tastes and enables the system to target items to the right users. In this paper, …