Wei Chen

The Geological Disaster Monitoring Method Based on GNSS

2016 · Advances in computer science research

In recent years, the frequent occurrence of geological disasters such as landslides, debris flow and so on causes huge losses to the lives and property of the people. To solve this problem, this paper proposes …

Fine-Grained Access Control for Cloud Data Sharing by Secure and Efficient Attribute-Revocable Ciphertext-Policy Attribute-Based Encryption

2016 · International Journal of Security and Its Applications

Nowadays, more and more users outsource their data to third party cloud storage servers for the purpose of sharing, so cloud data sharing becomes one of the popular services offered by cloud service providers. However, …

Addressing Memory Pressure in Data-intensive Parallel Programs via Container Based Virtualization

2017

Out-of-memory (OOM) errors and excessive garbage collection (GC) activities are common issues in dataintensive parallel programs, which cause not only poor performance but also execution failures. A recent study [1] proposed a new programming model …

Asynchronous Stochastic Proximal Optimization Algorithms with Variance Reduction

2017 · Proceedings of the AAAI Conference on Artificial Intelligence

Regularized empirical risk minimization (R-ERM) is an important branch of machine learning, since it constrains the capacity of the hypothesis space and guarantees the generalization ability of the learning algorithm. Two classic proximal optimization algorithms, …

FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning

2020 · arXiv (Cornell University)

In this paper, we identify a new phenomenon called activation-divergence which occurs in Federated Learning (FL) due to data heterogeneity (i.e., data being non-IID) across multiple users. Specifically, we argue that the activation vectors in …

EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble Model on Short-Text Conversation

2020 · arXiv (Cornell University)

Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and cons. Despite the natural …

Finite-key analysis for round-robin-differential-phase-shift quantum key distribution

2020 · Optics Express

Since the round-robin-differential-phase-shift (RRDPS) quantum key distribution (QKD) protocol was proposed, it has attracted much attention due to its unique characteristic i.e., it can bind the amount of information leakage without monitoring signal disturbance. Recently, …

Neighborhood Attentional Memory Networks for Recommendation Systems

2021 · Scientific Programming

Deep learning systems have been phenomenally successful in the fields of computer vision, speech recognition, and natural language processing. Recently, researchers have adopted deep learning techniques to tackle collaborative filtering with implicit feedback. However, the …

Interference at the single-photon level based on silica photonics robust against channel disturbance

2020 · Photonics Research

Quantum key distribution (QKD) provides a solution for communication of unconditional security. However, the quantum channel disturbance in the field severely increases the quantum bit-error rate, degrading the performance of a QKD system. Here we …

Tackling Cold Start of Serverless Applications by Efficient and Adaptive Container Runtime Reusing

2021

During the past few years, serverless computing has changed the paradigm of application development and deployment in the cloud and edge due to its unique advantages, including easy administration, automatic scaling, built-in fault tolerance, etc. …

Indiscriminate Poisoning Attacks Are Shortcuts.

2021 · arXiv (Cornell University)

Indiscriminate data poisoning attacks, which add imperceptible perturbations to training data to maximize the test error of trained models, have become a trendy topic because they are thought to be capable of preventing unauthorized use …

FT-DeepNets: Fault-Tolerant Convolutional Neural Networks with Kernel-based Duplication

2022 · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Deep neural network (deepnet) applications play a crucial role in safety-critical systems such as autonomous vehicles (AVs). An AV must drive safely towards its destination, avoiding obstacles, and respond quickly when the vehicle must stop. …

Tighter Monogamy Relations in Multi-Qubit Systems

2021 · arXiv (Cornell University)

In this paper, we present some monogamy relations of multiqubit quantum entanglement in terms of the βth power of concurrence, entanglement of formation and convex-roof extended negativity. These monogamy relations are proved to be tighter …

TKGF-NTP: Temporal Knowledge Graph Forecasting via Neural Temporal Point Process

2023

Knowledge graphs (KGs) with real-world facts are vital for various downstream applications. However, the incomplete nature of KGs has brought lots of problems to them, and probing missing facts via reasoning or forecasting has become …

Measurement-Device-Independent Quantum Key Distribution with Practical Spontaneous Parametric Down-Conversion Sources

2023 · Physical Review Applied

Measurement-device-independent (MDI) quantum key distribution (QKD) closes all the loopholes in the detection side, which greatly improves the practical security of QKD. Spontaneous parametric down-conversion (SPDC) sources play a significant role in MDI QKD by …

Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

Neural ranking models (NRMs) have shown great success in information retrieval (IR). But their predictions can easily be manipulated using adversarial examples, which are crafted by adding imperceptible perturbations to legitimate documents. This vulnerability raises …

VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However, sound comprehensive research on detecting program vulnerabilities, a more specific task related …

ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge

2024

To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic …

Heterogenous Multi-Source Data Fusion Through Input Mapping and Latent Variable Gaussian Process

2024 · arXiv (Cornell University)

Artificial intelligence and machine learning frameworks have served as computationally efficient mapping between inputs and outputs for engineering problems. These mappings have enabled optimization and analysis routines that have warranted superior designs, ingenious material systems …

A Deep Reinforcement Learning Scheduling Algorithm for Heterogeneous Tasks on Heterogeneous Multi-Core Processors

2024

Heterogeneous multi-core processor systems are common complex processing environments for scheduling DAG application tasks. Deep reinforcement learning has become a popular solution for scheduling in these systems due to its superior direct perception decision-making and …

Enhancing the Skin Disease Classification Accuracy base on Weighted Cross-Entropy Method with ISIC Dataset

2024

Early detection of skin diseases is essential for improving patient survival rates and preventing serious harm to people's lives and health. In recent years, there have been advancements in the field of skin disease identification …

CognTKE: A Cognitive Temporal Knowledge Extrapolation Framework

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

Reasoning future unknowable facts on temporal knowledge graphs (TKGs) is a challenging task, holding significant academic and practical values for various fields. Existing studies exploring explainable reasoning concentrate on modeling comprehensible temporal paths relevant to …

LLM-as-Critic: Contrastive and Adversarial Strategies for Authentic Text Verification

2025 · Preprints.org

The rapid proliferation of sophisticated large language models (LLMs) has revolutionized content generation but concurrently poses significant challenges for distinguishing human-authored from AI-generated text. Traditional detection methods often struggle with the increasing fluency of LLM …

Coevolutionary Neural Dynamics Considering Multiple Strategies for Nonconvex Optimization

2025 · Tsinghua Science & Technology

In the field of practical applications, the solution of nonconvex optimization problems plays a crucial role. However, many practical applications often encounter perturbations that may affect solutions to relevant nonconvex problems. Such perturbations are typically …

Mining Association Rules for Academic Performance Factors and Teaching Optimization

2025

With the Ministry of Education's advancement of "AI + Education" strategy and the backdrop of student-centered educational philosophy, this study focuses on mining the truth contained in the massive student data, exploring key factors influencing …

Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets

2018

Zhen Yang, Wei Chen, Feng Wang, Bo Xu. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

Large language models for generative information extraction: a survey

2024 · Frontiers of Computer Science

Abstract Information Extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation. As a result, numerous works have …