Lu Zhang

Single photon detector with high polarization sensitivity

2015 · Scientific Reports

Polarization is one of the key parameters of light. Most optical detectors are intensity detectors that are insensitive to the polarization of light. A superconducting nanowire single photon detector (SNSPD) is naturally sensitive to polarization …

Enhancing Defect Prediction with Static Defect Analysis

2015

In the software development process, how to develop better software at lower cost has been a major issue of concern. One way that helps is to find more defects as early as possible, on which …

Achieving non-discrimination in data release

2016 · arXiv (Cornell University)

Discrimination discovery and prevention/removal are increasingly important tasks in data mining. Discrimination discovery aims to unveil discriminatory practices on the protected attribute (e.g., gender) by analyzing the dataset of historical decision records, and discrimination prevention …

Describe Library Resources with Knowledge Graph

2017 · CAS OpenIR (Chinese Academy of Sciences)

Libraries have large amount of credible knowledge. But unfortunately, advanced Internet search tools and knowledge graphs cannot fully cover the valuable library collections. Using knowledge graph to describe collections can optimize knowledge services in several …

OCoR

2020

Code retrieval helps developers reuse code snippets in the open-source projects. Given a natural language description, code retrieval aims to search for the most relevant code relevant among a set of code snippets. Existing state-of-the-art …

Migrate On-Premises Real-Time Data Analytics Jobs Into the Cloud

2021

Twitter's data platform team is serving a large number of real-time analytics jobs, powering a wide range of data science use cases, from aggregations over time to spam detection. These analytics jobs constitute a crucial …

A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classification

2021 · 2021 IEEE Global Communications Conference (GLOBECOM)

Advantages of deep learning over traditional methods have been demonstrated for radio signal classification in the recent years. However, various researchers have discovered that even a small but intentional feature perturbation known as adversarial examples …

Spacecraft Telemetry Anomaly Detection Based on Parametric Causality and Double-Criteria Drift Streaming Peaks over Threshold

2022 · Applied Sciences

Most of the spacecraft telemetry anomaly detection methods based on statistical models suffer from the problems of high false negatives, long time consumption, and poor interpretability. Besides, complex interactions, which may determine the propagation of …

A Syntax-Guided Edit Decoder for Neural Program Repair

2021 · arXiv (Cornell University)

Automated Program Repair (APR) helps improve the efficiency of software development and maintenance. Recent APR techniques use deep learning, particularly the encoder-decoder architecture, to generate patches. Though existing DL-based APR approaches have proposed different encoder …

A Countermeasure Against Adversarial Attacks on Power Allocation in a Massive MIMO Network

2022

Deep learning has been emerging as a powerful design tool for the current and future generations of wireless networks. Among many other successful applications, deep learning has been shown to reduce computational complexity in power …

Algorithmic Recourse in Abnormal Multivariate Time Series

2023 · arXiv (Cornell University)

Algorithmic recourse provides actionable recommendations to alter unfavorable predictions of machine learning models, enhancing transparency through counterfactual explanations. While significant progress has been made in algorithmic recourse for static data, such as tabular and image …

IDMS Quantum Password-Authenticated Key Exchange Protocols

2024 · International Journal of Information and Computer Security

In this paper, we design an ID-based M-server quantum password-authenticated key exchange scheme, where the client computes a strong key from its password and splits the key into m portions, and then encrypts them and …

A Denial of Service Attack Defense Method for Roadside Units

2024

Roadside Units (RSUs) constitute a vital component of Vehicular Ad Hoc Network (VANET) due to their primary role in gathering vehicle information. However, as indicated in the literature, they are vulnerable to Denial of Service …

RAPID: Reliable and efficient Automatic generation of submission rePorting checklists with Large language moDels

2025 · bioRxiv (Cold Spring Harbor Laboratory)

Abstract Importance Medical reporting guidelines are significant in improving the transparency, quality, and integrity of medical research, particularly in randomized clinical trials; adherence to these guidelines supports research interpretability and has direct implications for downstream …

Vision Transformer With Adversarial Indicator Token Against Adversarial Attacks in Radio Signal Classifications

2025 · IEEE Internet of Things Journal

The remarkable success of transformers across various fields such as natural language processing and computer vision has paved the way for their applications in automatic modulation classification, a critical component in the communication systems of …

TurnaboutLLM: A Deductive Reasoning Benchmark from Detective Games

2025 · arXiv (Cornell University)

This paper introduces TurnaboutLLM, a novel framework and dataset for evaluating the deductive reasoning abilities of Large Language Models (LLMs) by leveraging the interactive gameplay of detective games Ace Attorney and Danganronpa. The framework tasks …

Natural Language Inference by Tree-Based Convolution and Heuristic Matching

2016

In this paper, we propose the TBCNNpair model to recognize entailment and contradiction between two sentences. In our model, a tree-based convolutional neural network (TBCNN) captures sentencelevel semantics; then heuristic matching layers like concatenation, element-wise …

Sequence to Backward and Forward Sequences: A Content-Introducing\n Approach to Generative Short-Text Conversation

2016 · arXiv (Cornell University)

Using neural networks to generate replies in human-computer dialogue systems\nis attracting increasing attention over the past few years. However, the\nperformance is not satisfactory: the neural network tends to generate safe,\nuniversally relevant replies which carry little …