Portfolio
Profile History
Education
Rochester Institute of Technology
PhD in Computing and Information Sciences
Rochester, NY, USA
GPA: 3.78
Crafted a grant proposal and secured $1k funding to purchase research equipment.
Achieved second place at college physics Olympiad at RIT 2023.
Achieved fully-funded PhD research and teaching assistantship.
Gettysburg College
BS in Computer Science
Gettysburg, PA, USA
GPA: 3.93
Achieved Dean's list award for 4 years.
Achieved computer science department's class honor award.
Achieved presidential scholarship that covered 80% tuition fee for four years.
Work Experiences
Visiting Researcher
VinUniversity
Hanoi, Vietnam
VinUniversity
Nov 24' -- Present
Conducting research on large language models and multimodal deep learning for scaling hate speech classification funded by the US NSF, EU's Horizon Europe 2024, and Petanux GmbH.
Preparing 1 manuscript for submission to a top-tier conference.
Graduate Teaching Assistant
Rochester Institute of Technology
Rochester, NY, USA
Rochester Institute of Technology
Aug 24' -- Present
Served as a teaching assistant for the graduate course 'Advanced Object-Oriented Programming Concepts'.
Led comprehensive weekly recitation sessions, facilitating in-depth discussions, reinforcing key course concepts, and providing additional instructional support to enhance students' understanding.
Managed communication channels, mentored students, addressed their questions, and handled organizational tasks.
Machine Learning & Robotics Researcher
Neural Adaptive Computing Lab
Rochester, NY, USA
Neural Adaptive Computing Lab
Aug 22' -- Present
Led a research team implementing reinforcement learning algorithms, resulting in 1 submitted paper to top-tier robotics conference.
Built a multimodal generative model for a reinforcement learning agent, resulting in 1 research manuscript in multimodal robotics.
Collaborated with 1 external robotics laboratory to improve deep reinforcement learning systems, resulting in 1 submitted paper on reinforcement learning.
Mentored 1 master's student through a successful thesis defense and currently guiding 3 additional master's students in completing their theses.
Computer Vision Researcher
Computer Graphics and Applied Perception Lab
Rochester, NY, USA
Computer Graphics and Applied Perception Lab
Aug 22' -- Present
Led development of a novel Sim2Real algorithms for eye-tracking data in collaboration with Meta Reality Labs, resulting in 1 accepted paper on image segmentation and Best Paper Award at ACM ETRA 2024.
Developed novel machine learning algorithms for dynamic vision sensor data streams, resulting in 1 research manuscript on event-based pupil detection.
Directly worked with Meta Reality Labs to improve eye tracking pipelines.
Visiting Researcher
University College Dublin
Dublin, Ireland
University College Dublin
Sep 24' -- Nov 24'
Conducted research on large language models and multimodal deep learning for robotics, supported by the US NSF's AWARE-AI NRT program and Ireland SFI's ML-Labs.
Prepared 1 manuscript for submission to a top-tier conference.
Multimodal AI Researcher Intern
Petanux GmbH
Bonn, Germany
Petanux GmbH
June 24' -- Sep 24'
Led a €3.7M grant proposal project about using computer vision, natural language processing, large language model, and AI systems to combat crime.
Implemented and solved core problems in 2 major company projects, with a total funding of €1.4M, using various constraint optimization methodologies.
Developed 1 large machine learning pipeline with different parallel processing and distributed training techniques.
Led a research team targeting top-tier conferences, resulting in 1 research manuscript.
Software Engineer Intern
Forestry Information System JSC
Hanoi, Vietnam
Forestry Information System JSC
Apr 21' -- Aug 21'
Implemented and deployed a wildfire detection application for iPhone using React Native and Swift.
Created and presented comprehensive documentation, requirements, and deliverables for mobile app projects.
Engineered deep learning wildfire detection models for deployment on embedded forest cameras.
Machine Learning Researcher
Gettysburg College
Gettysburg, PA, USA
Gettysburg College
May 20' -- Aug 22'
Led a research team in exploring the intersection of AI and Music, resulting in 1 first-authored publication in AAAI 2023.
Led a research team in developing a machine learning agent for playing Gin Rummy, resulting in 1 first-authored publication in AAAI 2021.
Publications
[ArXiv] R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models
Zhizhuo Yang
,Christopher L. Buckley
,Alexander Ororbia
There is relatively less work that builds AIF models in the context of partially observable Markov decision processes (POMDPs) environments. In POMDP scenarios, the agent must understand the hidden state of the world from raw sensory observations, e.g., pixels. Additionally, less work exists in examining the most difficult form of POMDP-centered control: continuous action space POMDPs under sparse reward signals. This work addresses these issues by introducing novel prior preference learning techniques and self-revision schedules to help the agent excel in sparse-reward, continuous action, goal-based robotic control POMDP environments. This repository contains detailed documentation needed to implement our proposed agent.
[ETRA-24] Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems
Reynold Bailey
,Gabriel J. Diaz
,Chengyi Ma
,Alexander Fix
,Alexander Ororbia
We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data, and to prune the training dataset in a manner that maximizes distribution overlap. We demonstrate that our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
[AAAI-23] Predicting Perceived Music Emotions with Respect to Instrument Combinations
Quan H. Nguyen
,Richard G. Freedman
We compare the accuracy difference between music emotion recognition models given music pieces as a whole versus music pieces separated by instruments. We provide empirical evidence that training Random Forest and Convolution Recurrent Neural Network with mixed instrumental music data conveys a better understanding of emotion than training the same models with music that are separated into each instrumental source
[AAAI-21] A Deterministic Neural Network Approach to Playing Gin Rummy
Dung Doan
,Todd W. Neller
This paper describes a deterministic approach to building a fixed-strategy gin rummy player. We develop and evaluate both heuristic and neural network models for informing draw, discard, and knock decisions in the game
Services and Leadership
Reviewer for Artificial Intelligence, Entropy, IEEE TNNLS, Pattern Recognition journals, and IEEE ICRA conference.
Publicity co-chair for HCCS'24 and HCCS'25 at IEEE PerCom 2024 and 2025.
NSF's AWARE-AI NRT member/researcher from 2022 to present.