Lei Wang

Filtering spam in Weibo using ensemble imbalanced classification and knowledge expansion

2015

Weibo has become an important information sharing platform in our daily life in China. Many applications utilize Weibo data to analyze hot topic and opinion evolution patterns to gain insights into user behavior. However, various …

Three Models to Analyze the Uncertainty of Boiler Emission Flue Gas Heat Loss

2015

Uncertainty assessment is a quantitative method about accuracy grade. This essay mainly focused on the principle of uncertainty analysis, including establish the uncertainty analysis model, assess the uncertainty components of type A and type B, …

Particle swarm optimization-based solution updating strategy for biogeography-based optimization

2016

Biogeography-based optimization (BBO) is a powerful evolutionary algorithm inspired from the science of biogeography. It mainly uses the biogeography-based migration operator to share the information among individuals. In canonical BBO, according to the principle of …

Corpus-based Automatic Generation of Multiple Choice Questions for College English Tests

2017

At present multiple choice questions as a testing item are adopted widely in College English tests, and play a significant role in assessing students' English proficiency. However, in practice the design of multiple choice questions …

BOPS, Not FLOPS! A New Metric, Measuring Tool, and Roofline Performance Model For Datacenter Computing.

2018

The past decades witness FLOPS (Floating-point Operations per Second), as an important computation-centric performance metric, guides computer architecture evolution, bridges hardware and software co-design, and provides quantitative performance number for system optimization. However, for emerging …

Instance-Level Embedding Adaptation for Few-Shot Learning

2019 · IEEE Access

Few-shot learning aims to recognize novel categories from just a few labeled instances. Existing metric learning-based approaches perform classifications by nearest neighbor search in the embedding space. The embedding function is a deep neural network …

XKX Does Not Preserve Unpredictability

2019 · Proceedings of the 3rd International Conference on Computer Science and Application Engineering

In this paper, the security of the XKX tweakable blockcipher construction is revisited. Proposed at FSE 2018, the security of the XKX was proved to be a tweakable pseudorandom permutation, which assumed the underlying blockcipher …

When Blockchain Meets SGX: An Overview, Challenges, and Open Issues

2020 · IEEE Access

As a decentralized, public, and digital ledger technology in Peer-to-Peer network, blockchain has received much attention from various fields, including finance, healthcare, supply chain, etc. However, some challenges (e.g., scalability, privacy, and security issues) severely …

Enhanced Velocity-Driven Particle Swarm Optimization for Evolving Artificial Neural Network

2021

research-article Share on Enhanced Velocity-Driven Particle Swarm Optimization for Evolving Artificial Neural Network Authors: Wei Li Xi'an University of Technology, China Xi'an University of Technology, ChinaView Profile , Haonan Luo Xi'an University of Technology, China …

MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization

2022 · arXiv (Cornell University)

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore …

Design of plasmonic enhanced all-optical phase-change memory for secondary storage applications

2022 · Nanotechnology

Phase-change optical device has recently gained tremendous interest due to its ultra-fast transmitting speed, multiplexing and large bandwidth. However, majority of phase-change optical devices are only devoted to on-chip components such as optical tensor core …

A quantum secure direct communication scheme based on intermediate-basis

2023 · Frontiers of Physics

Quantum secure direct communication (QSDC) is a method of communication that transmits secret information directly through a quantum channel. This paper proposes a two-step QSDC scheme based on intermediate-basis, in which the intermediate-basis Einstein–Podolsky–Rosen (EPR) …

Regularized Adaptive Huber Matrix Regression and Distributed Learning

2023 · Statistica Sinica

Matrix regression provides a powerful technique for analyzing matrixtype data, as exemplified by many contemporary applications. Despite the rapid advance, distributed learning for robust matrix regression to deal with heavy-tailed noises in the big data …

LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay

2023 · arXiv (Cornell University)

This paper explores the open research problem of understanding the social behaviors of LLM-based agents. Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. While previous studies have touched …

CoT-Driven Framework for Short Text Classification: Enhancing and Transferring Capabilities from Large to Smaller Model

2024 · arXiv (Cornell University)

Short Text Classification (STC) is crucial for processing and understanding the brief but substantial content prevalent on contemporary digital platforms. The STC encounters difficulties in grasping the semantic and syntactic intricacies, an issue that is …

Investigating the Impact of Prompt Engineering on the Performance of Large Language Models for Standardizing Obstetric Diagnosis Text: Comparative Study (Preprint)

2023

<sec> <title>BACKGROUND</title> The accumulation of vast electronic medical records (EMRs) through medical informatization creates significant research value, particularly in obstetrics. Diagnostic standardization across different health care institutions and regions is vital for medical data analysis. …

Adaptive User-Centric Entanglement Routing in Quantum Data Networks

2024 · arXiv (Cornell University)

Distributed quantum computing (DQC) holds immense promise in harnessing the potential of quantum computing by interconnecting multiple small quantum computers (QCs) through a quantum data network (QDN). Establishing long-distance quantum entanglement between two QCs for …

YuLan: An Open-source Large Language Model

2024 · arXiv (Cornell University)

Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many open-source LLMs have been released with technical reports, the lack of training …

SpMis: An Investigation of Synthetic Spoken Misinformation Detection

2024 · arXiv (Cornell University)

In recent years, speech generation technology has advanced rapidly, fueled by generative models and large-scale training techniques. While these developments have enabled the production of high-quality synthetic speech, they have also raised concerns about the …

Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight

2024 · arXiv (Cornell University)

Video anomaly detection (VAD) has witnessed significant advancements through the integration of large language models (LLMs) and vision-language models (VLMs), addressing critical challenges such as interpretability, temporal reasoning, and generalization in dynamic, open-world scenarios. This …

A multi-channel meter smart communication method based on low-voltage power line broadband carrier

2025 · Journal of Physics Conference Series

Abstract The conventional meter intelligent communication method establishes a communication network with an existing network, which is affected by background noise, impulse noise, and so on, and the communication quality is degraded. Therefore, a multi-channel …

Visual Representation Learning through Causal Intervention for Controllable Image Editing

2025

A key challenge for controllable image editing is that visual attributes with semantic meanings are not always independent, resulting in spurious correlations in model training. However, most existing methods ignore such issues, leading to biased …

Research on human computer interaction of information interactive robot based on temporal knowledge graph

2026 · IET conference proceedings.

The rapid development of artificial intelligence has promoted the widespread application of intelligent interactive robots in various industries. The human-machine interaction technology of information interactive robots based on temporal knowledge graph has become the key …

An attention-based BiLSTM-CRF approach to document-level chemical named entity recognition

2017 · Bioinformatics

Motivation: In biomedical research, chemical is an important class of entities, and chemical named entity recognition (NER) is an important task in the field of biomedical information extraction. However, most popular chemical NER methods are …

Template-Based Math Word Problem Solvers with Recursive Neural Networks

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

The design of automatic solvers to arithmetic math word problems has attracted considerable attention in recent years and a large number of datasets and methods have been published. Among them, Math23K is the largest data …

Graph-to-Tree Learning for Solving Math Word Problems

2020

While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities …

LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models

2023

The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development of numerous cost-effective and accessible alternatives that are created by finetuning open-access LLMs with task-specific data (e.g., ChatDoctor) or …