Xiaofeng Wang

Offensive Strategy in the 2D Soccer Simulation League Using Multi-Group Ant Colony Optimization

2016 · International Journal of Advanced Robotic Systems

The 2D soccer simulation league is one of the best test beds for the research of artificial intelligence (AI). It has achieved great successes in the domain of multi-agent cooperation and machine learning. However, the …

POSTER

2017

Origin authentication is one of the most concentrated and advocated BGP security approach against IP prefix hijacking. However, the potential risk of centralized authority abuse and the fragile infrastructure may lead a sluggish deployment of …

iTLS/iDTLS

2019

Transport Layer Security (TLS) and Datagram TLS (DTLS) are the de-facto protocols of Internet of Things (IoT) for end-to-end secure communication. However, typical deployment scenarios of highly constrained devices in low-power and lossy networks make …

Social loafing prevention in agile software development teams using team expectations agreements

2021 · IET Software

Abstract Social loafing is a common issue encountered by many software development teams. In practice, agile software development teams often use team expectations agreements (TEAs), which contain rules to prevent social loafing behaviour. However, few …

Context-aware Heterogeneous Graph Attention Network for User Behavior Prediction in Local Consumer Service Platform

2021 · arXiv (Cornell University)

As a new type of e-commerce platform developed in recent years, local consumer service platform provides users with software to consume service to the nearby store or to the home, such as Groupon and Koubei. …

Towards Imbalanced Large Scale Multi-label Classification with Partially Annotated Labels

2023

Multi-label classification is a widely encountered problem in daily life, where an instance can be associated with multiple classes. In theory, this is a supervised learning method that requires a large amount of labeling. However, …

Identification technique of cryptomining behavior based on traffic features

2023 · Frontiers in Physics

Recently, the growth of blockchain technology and the economic benefits of cryptocurrencies have led to a proliferation of malicious cryptomining activities on the internet, resulting in significant losses for companies and institutions. Therefore, accurately detecting …

Hybrid Work meets Agile Software Development: A Systematic Mapping Study

2024 · arXiv (Cornell University)

Hybrid work, a fusion of different work environments that allow employees to work in and outside their offices, represents a new frontier for agile researchers to explore. However, due to the nascent nature of the …

PersonaMark: Personalized LLM watermarking for model protection and user attribution

2024 · arXiv (Cornell University)

The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confidential information. With the extensive adoption of private LLMs, safeguarding model copyright and ensuring …

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models

2024

Parameter-Efficient Fine-Tuning (PEFT) methods have gained significant popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks, primarily due to their potential to significantly reduce memory and computational overheads.However, a common limitation in most …