Xin Li

MARS: A multi-aspect Recommender system for Point-of-Interest

2015

With the pervasive use of GPS-enabled smart phones, location-based services, e.g., Location Based Social Networking (LBSN) have emerged . Point-of-Interests (POIs) Recommendation, as a typical component in LBSN, provides additional values to both customers and …

Latency and efficiency driven dynamic content replacement in elastic optical datacenter networks

2017

We study the problem of dynamic content replacement in terms of network state variation in elastic optical datacenter networks. A dynamic content replacement scheme is proposed to minimize spectrum consumption, blocking probability and network latency.

Research on the Construction of Digital Portal Website in University Library

2017 · Advances in computer science research

Purpose/significance] Through the construction of high-level digital portal suitable for readers' needs, it can effectively improve the level of information service and the service quality.

GANE: A Generative Adversarial Network Embedding

2018 · arXiv (Cornell University)

Network embedding has become a hot research topic recently which can provide low-dimensional feature representations for many machine learning applications. Current work focuses on either (1) whether the embedding is designed as an unsupervised learning …

An Empirical Study on the Mobile Informatization Teaching Model Applied to College Students Mental Health Education Course

2018

This paper studied the Mobile informatization teaching model applied in the college students' mental health education course in order to see its effect on improving the level of college students' mental health. In this study, …

Overdue Prediction of Bank Loans Based on LSTM-SVM

2018

In the aspect of bank loans, the accuracy of traditional user loan risk prediction models, such as KNN, Bayesian, DNN, are not benefit from the data growth. This article is based on the work of …

Delay-Aware Resource Allocation for Data Analysis in Cloud-Edge System

2018

There is a strong need for data analysis in information systems to support various services. Traditional cloud data centers provide powerful ability to conduct data analysis jobs. However, the data transmission consumes a large amount …

An Investigation of Ensemble Approaches to Cross-Version Defect Prediction

2019 · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering

Software defect prediction can help software testers to focus on software modules with more defects. Many ensemble methods have been proposed for software defect prediction to divide software modules into defect-prone and defect-free, and these …

A Geographical Behavior-Based Point-of-Interest Recommendation

2019

With the development of mobile devices, point-of-interest (POI) recommendation has received increasing attention. However, achieving accurate personalized POI recommendation is challenging due to the sparsity of the available data per user. In addition, previous efforts …

Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

2020

Latent factor collaborative filtering (CF) has been a widely used technique for recommender system by learning the semantic representations of users and items. Recently, explainable recommendation has attracted much attention from research community. However, trade-off …

Exploiting Semantic Relations for Fine-grained Entity Typing

2020 · Rare & Special e-Zone (The Hong Kong University of Science and Technology)

Fine-grained entity typing results can serve as important information for entities while constructing knowledge bases. It is a challenging task due to the use of large tag sets and the requirement of understanding the context. …

TEAC: Intergrating Trust Region and Max Entropy Actor Critic for Continuous Control

2021

Trust region methods and maximum entropy methods are two state-of-the-art branches used in reinforcement learning (RL) for the benefits of stability and exploration in continuous environments, respectively. This paper proposes to integrate both branches in …

Identifying Illicit Drug Dealers on Instagram with Large-scale Multimodal Data Fusion

2021 · arXiv (Cornell University)

Illicit drug trafficking via social media sites such as Instagram has become a severe problem, thus drawing a great deal of attention from law enforcement and public health agencies. How to identify illicit drug dealers …

A Preprocessing and Feature Extraction Method of Ground-based Cloud Images for Photovoltaic Power Prediction

2021

The photovoltaic system is affected by many factors, so its ultra-short-term prediction faces enormous challenges. Total Sky Imager (TSI) is used for sky monitoring, which is of great significance for photovoltaic power prediction, but its …

Statistical learning in chip (SLIC)

2015

Despite best efforts, integrated systems are “born” (manufactured) with a unique `personality' that stems from our inability to precisely fabricate their underlying circuits, and create software a priori for controlling the resulting uncertainty. It is …

Chinese Lexical Sememe Prediction Using CilinE Knowledge

2022 · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences

Sememes are the smallest semantic units of human languages, the composition of which can represent the meaning of words. Sememes have been successfully applied to many downstream applications in natural language processing (NLP) field. Annotation …

Quantum color image scaling based on bilinear interpolation

2022 · Chinese Physics B

As a part of quantum image processing, quantum image scaling is a significant technology for the development of quantum computation. At present, most of the quantum image scaling schemes are based on grayscale images, with …

A Differential Privacy Budget Allocation Algorithm Based on Out-of-Bag Estimation in Random Forest

2022 · Mathematics

The issue of how to improve the usability of data publishing under differential privacy has become one of the top questions in the field of machine learning privacy protection, and the key to solving this …

Enhancing Cross-lingual Prompting with Dual Prompt Augmentation

2023

Prompting shows promising results in few-shot scenarios. However, its strength for multilingual/cross-lingual problems has not been fully exploited. hao and Schütze (2021) made initial explorations in this direction by presenting that cross-lingual prompting outperforms cross-lingual …

Towards Multi-modal Transformers in Federated Learning

2024 · arXiv (Cornell University)

Multi-modal transformers mark significant progress in different domains, but siloed high-quality data hinders their further improvement. To remedy this, federated learning (FL) has emerged as a promising privacy-preserving paradigm for training models without direct access …

XFMP: A Benchmark for Explainable Fine-Grained Abnormal Behavior Recognition on Medical Personal Protective Equipment

2024 · IEEE Transactions on Circuits and Systems for Video Technology

The proper use of medical personal protective equipment (MPPE) is critical for frontline healthcare workers (HCWs) to handle highly contagious diseases. Due to the complexity of PPE donning and doffing protocols, public health organizations typically …

Safety Monitoring Twin System for Three Major Building Super-Large Excavation Pits Based on Internet of Things Technology

2024 · Industrial Construction

With the rapid development of economy and urbanization, the scale and number of super-large excavation pit projects have surged. However, the construction of super-large underground space structure is faced with challenges such as complex underground …

Privacy-Preserving E-Voting Scheme with Dynamically Involved Voters

2024

As a more economical and efficient voting method than traditional voting, electronic voting (e-voting) has been widely concerned and supported. However, e-voting schemes face great challenges in privacy and security protection. In order to solve …

The influencing mechanism of leader and employee exchange satisfaction on employees' proactive behavior

2024 · Social Behavior and Personality An International Journal

On the basis of social exchange theory, we proposed the concept of exchange satisfaction, which refers to employees' and leaders' subjective perception of and degree of satisfaction with the quality of leader–member exchange. We found …

AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation

2024 · arXiv (Cornell University)

The impressive performance of proprietary LLMs like GPT4 in code generation has led to a trend to replicate these capabilities in open-source models through knowledge distillation (e.g. Code Evol-Instruct). However, these efforts often neglect the …

Scale-Aware Crowd Counting Network With Annotation Error Modeling

2025 · IEEE Transactions on Image Processing

Traditional crowd-counting networks suffer from information loss when feature maps are reduced by pooling layers, leading to inaccuracies in counting crowds at a distance. Existing methods often assume correct annotations during training, disregarding the impact …

COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization

2025 · IEEE Access

Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing these models to their low-bit counterparts without compromising the original accuracy remains …

AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model

2025 · arXiv (Cornell University)

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in …

DiaBlo: Diagonal Blocks Are Sufficient For Finetuning

2025 · arXiv (Cornell University)

Fine-tuning is a critical step for adapting large language models (LLMs) to domain-specific downstream tasks. To mitigate the substantial computational and memory costs of full-model fine-tuning, Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed to update …

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 …

Inferring a Personalized Next Point-of-Interest Recommendation Model with Latent Behavior Patterns

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

In this paper, we address the problem of personalized next Point-of-interest (POI) recommendation which has become an important and very challenging task in location-based social networks (LBSNs), but not well studied yet. With the conjecture …

Category-aware Next Point-of-Interest Recommendation via Listwise Bayesian Personalized Ranking

2017

Next Point-of-interest (POI) recommendation has become an important task for location-based social networks (LBSNs). However, previous efforts suffer from the high computational complexity and the transition pattern between POIs has not been well studied. In …