Lei Chen

VRCA: a clustering algorithm for massive amount of texts

2015 · International Conference on Artificial Intelligence

There are lots of texts appearing in the web every day. This fact enables the amount of texts in the web to explode. Therefore, how to deal with large-scale text collection becomes more and more …

Evaluating Speech, Face, Emotion and Body Movement Time-series Features for Automated Multimodal Presentation Scoring

2015

We analyze how fusing features obtained from different multimodal data streams such as speech, face, body movement and emotion tracks can be applied to the scoring of multimodal presentations. We compute both time-aggregated and time-series …

A weighted heteroscedastic Gaussian process modeling via particle swarm optimization

2016

Gaussian process regression (GPR) algorithm has good adaptability to deal with high dimensional, small sample, and nonlinear problems. The standard GPR algorithm assumes constant noise power throughout the sampling process. However, different sample points are …

MRSIM: Mitigating Reducer Skew In MapReduce

2017

MapReduce has emerged as a popular programming model in the field of data-intensive computing. This is due to its simplistic design, which provides ease of use for programmers, and its framework implementations such as Hadoop, …

Nowcasting Methods For Optimising Building Performance

2020 · Building Simulation Conference proceedings

In meteorology term, nowcasting is weather forecasting for the next few minutes to six hours using all immediately available weather data. It is a relatively new subject, which often involves remote sensing, numerical weather prediction …

Automatic cyber security risk assessment based on fuzzy fractional ordinary differential equations

2020 · Alexandria Engineering Journal

Real-time network security risk detection is of great significance to the research of dynamic network security, and it is one of the current research hotspots of network security. Based on the idea of artificial immune, …

A Practical Low-Cost Security Solution for Log Management and File Integrity Monitoring

2020

Log management and file integrity are among the most critical security controls in protecting valuable business data assets against internal and external security attacks. Despite the importance of these controls, many businesses, especially smaller ones, …

Mcore: Multi-Agent Collaborative Learning for Knowledge-Graph-Enhanced Recommendation

2021

Recently, knowledge-graph-enhanced recommendation systems have attracted much attention, since knowledge graph (KG) can help improving the dataset quality and offering rich semantics for explainable recommendation. However, current KG-enhanced solutions focus on analyzing user behaviors on …

Micro-expression Detection based on Action Units and Multi-region Feature Fusion

2022

Recently, micro-expression detection has attracted much attention, since micro-expression has potential lie detection applications. In this paper, a micro-expression detection algorithm based on action units (AUs) and multi-region feature fusion is proposed. First, the regions …

Dark Web Forensics: An Investigation of Tracking Dark Web Activity with Digital Forensics

2022

The Dark Web has become home to malicious, illegal, and exploitative activities. Due to the nature of the Dark Web and the browsers used to reach it, uncovering these activities presents grave challenges to digital …

Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers

2024 · arXiv (Cornell University)

Large language models have been successful at tasks involving basic forms of in-context reasoning, such as generating coherent language, as well as storing vast amounts of knowledge. At the core of the Transformer architecture behind …

Logic Synthesis with Generative Deep Neural Networks

2024 · arXiv (Cornell University)

While deep learning has achieved significant success in various domains, its application to logic circuit design has been limited due to complex constraints and strict feasibility requirement. However, a recent generative deep neural model, "Circuit …

An Architectural Design of Network Scenario Cognitive Engine Based on Metacognitive Core

2024

The cognitive engine is the core component that promotes the development of cognitive communication. However, current cognitive engines designed for a single decision algorithm, which makes it difficult to meet the needs of a variety …

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

2024 · arXiv (Cornell University)

In this technical report, we introduce OpenR, an open-source framework designed to integrate key components for enhancing the reasoning capabilities of large language models (LLMs). OpenR unifies data acquisition, reinforcement learning training (both online and …

Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models

2025

Haoyang Li, Xuejia Chen, Zhanchao Xu, Darian Li, Nicole Hu, Fei Teng, Yiming Li, Luyu Qiu, Chen Jason Zhang, Li Qing, Lei Chen. Findings of the Association for Computational Linguistics: ACL 2025. 2025.

A NOVEL POINT CLOUD CLASSIFICATION METHOD BASED ON SUBSPACE EXTENSION AND ADAPTIVE MULTIDIMENSIONAL FEATURE MINING WITH APPLICATION TO HEALTH MONITORING OF OVERHEAD TRANSMISSION LINES. 138-149

2026 · Control and Intelligent Systems

In the health monitoring of overhead transmission line equipment,intelligent point cloud classification confronts two critical challenges:discontinuous extraction of transmission lines caused by large terrainelevation differences, and high costs associated with acquiringlabelled data.

Revisiting Graph Based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Graph Convolutional Networks~(GCNs) are state-of-the-art graph based representation learning models by iteratively stacking multiple layers of convolution aggregation operations and non-linear activation operations. Recently, in Collaborative Filtering~(CF) based Recommender Systems~(RS), by treating the user-item interaction …