Sen He

DynamicLip: Shape-Independent Continuous Authentication via Lip Articulator Dynamics

Thu, 01 Jan 2026 00:00:00 +0000

Harnessing large language models for virtual reality exploration testing: a case study

Thu, 01 Jan 2026 00:00:00 +0000

Microservice logs analysis employing AI: A systematic literature review

Thu, 01 Jan 2026 00:00:00 +0000

Performance analysis of AI-generated code: A case study of Copilot, Copilot Chat, CodeLlaMa, and DeepSeek-Coder models

Thu, 01 Jan 2026 00:00:00 +0000

UWB-PostureGuard: A Privacy-Preserving RF Sensing System for Continuous Ergonomic Sitting Posture Monitoring

Thu, 01 Jan 2026 00:00:00 +0000

Welcome to My New Research Website

Fri, 11 Apr 2025 00:00:00 +0000

Welcome to my updated research website! I’m Sen He, an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Arizona.

This site serves as a central hub for my research activities, publications, teaching, and information for prospective students. I’ll be posting updates here about new publications, project milestones, and opportunities in my lab.

Current highlights:

Our paper on using LLMs for VR exploration testing has been published in Automated Software Engineering.
PerfOrch, our multi-agent LLM orchestration framework, has been submitted to TOSEM.
I’m teaching SFWE 409/509 Cloud Computing Principles this spring.

GraphQL-Aware Healing in Service-Oriented Architectures via Multi-Signal Learning

Wed, 01 Jan 2025 00:00:00 +0000

Self-Supervised Graph Transformer with Contrastive Learning for Brain Connectivity Analysis Towards Improving Autism Detection

Wed, 01 Jan 2025 00:00:00 +0000

Unveiling code clone patterns in open source VR software: an empirical study

Wed, 01 Jan 2025 00:00:00 +0000

AI-Driven Software Testing

Sat, 01 Jun 2024 00:00:00 +0000

Overview

Modern software systems — from virtual reality applications to microservice architectures — present unique testing challenges that traditional approaches struggle to address. This project explores how large language models and AI techniques can be applied to automate and improve software testing across these domains.

Research Directions

LLM-Based VR Testing: We investigate using LLMs for exploration testing of VR applications, where the state space is large and traditional test generation methods are insufficient. Our work demonstrates how LLMs can generate meaningful interaction sequences that achieve high code coverage.

Code Clone Detection in VR Software: Empirical studies on code cloning patterns specific to VR software development, identifying unique maintenance and security implications.

Software Security in VR: Investigating software security weaknesses across VR projects, examining when and why vulnerabilities emerge during the development lifecycle.

Microservice Log Analysis with AI: Systematic analysis of how AI techniques can be applied to microservice log data for anomaly detection, root cause analysis, and system health monitoring.

Applied Computer Vision and Medical Image Analysis

Mon, 01 Jan 2024 00:00:00 +0000

Overview

This research thrust applies deep learning and computer vision techniques to impactful application domains, with a current emphasis on medical image analysis and privacy-preserving sensing.

Active Projects

Brain Connectivity Analysis for Autism Detection: Developing self-supervised graph transformers with contrastive learning to analyze brain connectivity patterns from fMRI data, with the goal of improving autism spectrum disorder detection (published at ISBI 2025).

Medical Image Segmentation: Collaborating on advanced segmentation architectures for biomedical imaging applications, including work targeting ECCV venues.

Privacy-Preserving Posture Monitoring (UWB-PostureGuard): A UWB-based RF sensing system for continuous ergonomic sitting posture monitoring that avoids the privacy concerns of camera-based approaches (published at HICSS 2026, NSF I-Corps participation).

Sediment Concentration Estimation: Applying machine learning models to estimate suspended sediment concentration from laboratory data, bridging computer vision/ML with environmental monitoring.

Experience

Mon, 01 Jan 2024 00:00:00 +0000

Multi-Agent LLM Orchestration for Software Engineering

Mon, 01 Jan 2024 00:00:00 +0000

Overview

Large language models have demonstrated remarkable capabilities in code generation, but individual models often produce code with functional errors or performance inefficiencies. This project investigates multi-agent orchestration frameworks that coordinate multiple LLMs through structured collaboration pipelines — combining specialized agents for categorization, code generation, debugging, and refinement.

Key Contributions

Our flagship system, PerfOrch, introduces a memory-augmented multi-agent architecture where:

A Categorizing Agent classifies programming tasks using a fixed category vocabulary to enable retrieval of relevant historical solutions.
Generator and Debugger Agents collaborate through iterative cycles to produce functionally correct code.
A Refinement Agent optimizes code performance using aggregated insights from the orchestration’s memory module.
The architecture leverages asymmetric aggregation strategies (product vs. sum) across different pipeline stages.

We evaluate across 5 frontier LLMs and demonstrate significant improvements over single-model baselines on both correctness and runtime performance metrics.

Status

Manuscript submitted to ACM Transactions on Software Engineering and Methodology (TOSEM).

Performance Testing for Cloud and Serverless Computing

Sun, 01 Jan 2023 00:00:00 +0000

Overview

Cloud computing introduces fundamental challenges for performance testing due to resource contention, hidden scheduling policies, and passive auto-scaling. These challenges are amplified in serverless computing environments where the resource abstraction level is higher and auto-scaling behaviors are not well-characterized.

Research Thrusts

Serverless Auto-Scaling Characterization: We define and characterize auto-scaling stages for serverless platforms, decomposing performance uncertainty into resource contention during execution and cold start-up latencies during environment initiation.

Monte Carlo Simulation-Based Testing: We develop simulation-based methodologies that can predict performance distributions of serverless applications, accounting for the stochastic nature of cloud performance fluctuations.

AI-Based Cloud Emulation: Building systems that emulate cloud environments on local machines to help users obtain accurate performance results at reduced testing costs, particularly when multiple applications need to be evaluated.

Performance Assurance in DevOps: Using development and operational data to detect performance regressions early in the software delivery cycle, with attention to end-user impact.