💻
AI PhD Researcher · Software Engineering
Linqiang (Jackson) Guo
AI-driven mobile automation · LLM agents · Multimodal VLM post-training
I'm a Software Engineering PhD student at Concordia University and a Graduate Student Researcher at Mila, building LLM-based agents that reason about state, recover from failure, and understand user interfaces. Previously a software engineer at Walmart Global Tech.
10Publications
AAAI · ICSE · ECCV · COLMVenues
🏆 Best PaperECCV 2026 MDA WS
Mila · WalmartAffiliations
01 — About
Research at the intersection of AI & software systems
My work focuses on intelligent mobile software systems — designing agents that combine large language models, vision-language pipelines, and finite-state reasoning to automate and test complex mobile applications. I care about making these systems state-aware, robust, and recoverable when things go wrong. I'm also a Graduate Student Researcher at Mila, working on RL-based post-training (GRPO, DPO) for multimodal GUI agents.
Before my PhD, I built and maintained microservices for customer personalization and recommendation at Walmart Global Tech, integrating GenAI workflows into search and working with Milvus on Kubernetes. I hold an MS in ECE (AI track) from the University of Miami and a BS in Electrical Engineering from the University of Missouri.
- 📍 Montreal, Canada
- 🎓 PhD @ Concordia University
- 🤖 LLM agents & mobile automation
- ✉️ linqg327@gmail.com
Education
-
2024 — Present
PhD, Software Engineering
Concordia University · Montreal, CA
-
2020 — 2022
MS, Electrical & Computer Engineering (AI track)
University of Miami · Miami, US
-
2016 — 2019
BS, Electrical Engineering
University of Missouri Columbia · Columbia, US
02 — Skills
Tools & technologies
🧠
AI / ML Frameworks
⚙️
Backend & Platforms
03 — Publications
Selected publications
-
ECCV 2026 WS
Learning to Adapt: Few-Shot Generalization of Mobile Agents to Unseen Applications
🏆 Best Paper Award · ECCV 2026 Workshop on Multimodal Digital Agents (MDA) · Spotlight Talk + Poster
-
ECCV 2026 WS
StepReflect: Structured Reflection for Mobile GUI Agents
ECCV 2026 Workshop on Multimodal Digital Agents (MDA) · Poster + Lightning Talk · arXiv:2608.05587
-
ECCV 2026 WS
CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications
ECCV 2026 Workshop on Multimodal Digital Agents (MDA) · Poster + Lightning Talk · arXiv:2608.11588
-
ECCV 2026 WS
Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?
ECCV 2026 Workshop on Multimodal Digital Agents (MDA) · Poster · arXiv:2606.19388
-
AAAI 2026
Agent SAMA: State Aware Mobile Assistant
-
ICSE 2025
Guiwatcher: Automatically Detecting GUI Lags by Analyzing Mobile Application Screencasts
-
COLM 2025 Workshop
MAPLE: A Mobile Assistant with Persistent Finite State Machines for Recovery Reasoning
-
CMIG
Registration on DCE-MRI Images via Multi-Domain Image-to-Image Translation
Computerized Medical Imaging and Graphics (IF 7.422)
-
Under Review
Screencast-Based Analysis of User-Perceived GUI Responsiveness
-
Under Review
PopSweeper: Automatically Detecting and Resolving App-Blocking Pop-Ups to Assist Automated Mobile GUI Testing
04 — Experience
Where I've worked
-
Jul 2026 — Present
Graduate Student Researcher · Mila — Quebec Artificial Intelligence Institute
Montreal, Quebec, Canada
- Research on multimodal / GUI agents.
- RL-based post-training for agentic models (GRPO, DPO).
-
Jan 2024 — Present
Research Assistant · SPEAR Lab
Software Performance, Engineering, Analysis & Reliability Lab · Montreal, Canada
- Research intelligent mobile software systems with a focus on AI-driven automation and UI understanding.
- Develop methods to improve agent reasoning, state awareness, and robustness in complex mobile environments.
- Co-authored multiple papers at top venues including AAAI, ICSE, TOSEM, and COLM.
-
Jan 2025 — Jan 2026
Teaching Assistant · Concordia University
Montreal, Canada
- Assist teaching Software Engineering courses: software design, UML modeling, testing, and project management.
- Lead weekly tutorials and support students through office hours and online discussions.
- Guide students through core SE concepts and GitHub-based project workflows.
-
Aug 2022 — Dec 2023
Software Developer · Walmart Global Tech
Sunnyvale, California, USA · in contract
- Built and maintained microservices for customer personalization, data ingestion, and recommendation using Java, Spring, and cloud tools.
- Optimized performance of the Milvus vector database on Kubernetes.
- Integrated GenAI workflows into search components, improving query understanding and relevance ranking.
- Deployed scalable API endpoints and streamlined CI/CD with data science and platform teams.
-
Jan 2020 — Feb 2020
Software Engineer Intern · CPECC Gulf Region
Abu Dhabi, United Arab Emirates
- Developed RESTful web services (e.g. travel-request management) with Spring Boot, Spring MVC, Maven, and Hibernate.
- Tested features with JUnit and Mockito; used Git and GitHub for version control and code review.
05 — Honors & Awards
Honors & awards
-
2026
🏆 Best Paper Award · ECCV 2026 Workshop on Multimodal Digital Agents (MDA)
For Learning to Adapt: Few-Shot Generalization of Mobile Agents to Unseen Applications
-
2023
Concordia University International Tuition Award of Excellence
-
2023
Concordia University Split Graduate Fellowship
06 — Projects
Selected projects
Face Recognition System
May 2022Compared Deep Learning vs. Bag-of-Visual-Words for face recognition. Modified GoogLeNet with custom FC/output layers via transfer learning; built a multi-SVM classifier over a BoVW codebook. Achieved 83.5% (DL) vs. 58.5% (BoVW) accuracy.
Online Ticket Ordering System
Jun 2021Microservice architecture in Spring with HTTP communication and a React front-end for searching events and viewing recommendations. MySQL/MongoDB for CRUD; an ML-based recommender driven by user preferences.
Color Image Enhancement
Oct 2021Digital image processing pipeline for feature matching: sharpening (high-boost & Laplacian), per-channel Gaussian denoising, histogram equalization for tone correction, and homomorphic filtering for illumination adjustment.
Game Outcome Prediction
Apr 2021Predicted match winners from a ~9,900-game League of Legends dataset (47 attributes). Cleaned to ~7,000 samples / 30 attributes, then compared SVM, Decision Tree, and Logistic Regression performance.
Rocket Telemetry System
Mar 2018Real-time data collection & transmission for a Mizzou Space Program rocket (launched May 2018). Integrated temperature/humidity/pressure sensors, an IMU and GPS over I2C, an RF transceiver/receiver via Arduino, and an SD backup system.
07 — Contact
Let's connect
Interested in collaborating on AI agents, mobile automation, or software-engineering research? I'd love to hear from you.
Email me ✉️