Reinforcement learning is the focus of my current work. Below are selected RL papers, followed by my broader research.
Reinforcement learning
Stackelberg Coupling of Online Representation Learning and Reinforcement Learning
ICLR, 2026
A Stackelberg formulation lets representations adapt faster than value estimates, stabilizing their interaction in deep Q-learning.
In-Context Reinforcement Learning via Communicative World Models
IJCAI, 2026
A pretrained world model communicates reusable context, helping a separate control agent learn faster and adapt to new tasks.
Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models
arXiv preprint, 2026 (Submitted manuscript)
Pretrained world models predict the consequences of alternative actions, improving fully decentralized on-policy multi-agent learning.
Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense
IEEE GLOBECOM, 2026 (Accepted; proceedings forthcoming)
LLM advice shapes rewards during training, improving sample efficiency for autonomous cyber defense without LLM calls at deployment.
Additional publications
Multi-Stage Enhanced Zero Trust Intrusion Detection System for Unknown Attack Detection in Internet of Things and Traditional Networks
ACM Transactions on Privacy and Security, 2025
A multi-stage zero trust intrusion detection architecture combining supervised and unsupervised learning to identify unknown attack classes and variants.
Decoding Fatphobia: Examining Anti-Fat and Pro-Thin Bias in AI-Generated Images
Findings of NAACL, 2025
Evaluates weight bias and stereotypical associations in 4,000 DALL-E 3 images generated from paired positive and negative prompts.
Benchmarking Interpretability in Healthcare Using Pattern Discovery and Disentanglement
Bioengineering, 2025
Benchmarks an interpretable pattern discovery system on clinical notes and compares its explanations with post hoc interpretability techniques.
SPRIG: Stackelberg Perception-Reinforcement Learning with Internal Game Dynamics
AAAI Planning & Reinforcement Learning Workshop, 2025
Models perception and policy learning as a cooperative Stackelberg game. Experiments on Atari BeamRider examine how coordinating the two modules improves returns relative to PPO.
Learning in Multiple Spaces: Few-Shot Network Attack Detection with Metric-Fused Prototypical Networks
AAAI AI for Cyber Security Workshop, 2025
Combines multiple distance metrics in a prototypical learning framework for few-shot network attack detection.
Admissions in the Age of AI: Detecting AI-Generated Application Materials in Higher Education
Scientific Reports, 2024
Studies domain-specific detection of AI-generated and AI-revised graduate application documents, with a public codebase.
GPT vs. Llama2: Which Comes Closer to Human Writing?
EDM 2024, 2024
Compares GPT and Llama 2 text with human writing through vocabulary, structure, and domain-specific classification experiments.
Redefining Cyber Resilience with Dual-Space Prototypical Networks for DDoS Attack Detection
ICCCN, 2024
Uses geometric and angular similarity in a dual-space prototypical network to detect known and novel DDoS attack patterns with limited training data.
Integrating Multiple Visual Attention Mechanisms in Deep Neural Networks
COMPSAC, 2023
Combines parallel visual attention mechanisms with an efficient encoder, evaluated on dog breed classification and demonstrated in an interactive application.
Rediscovering Fraud Detection in Bitcoin Transactions Using Machine Learning Models
WF-IoT, 2023
Compares conventional machine learning, multilayer perceptrons, and graph convolutional networks for fraudulent Bitcoin transaction detection.
Rediscovering The Particle in a Box: Machine learning regression analysis for hypothesis generation in physical chemistry lab
Journal of Chemical Education, 2023
A laboratory activity using regression over 13 molecular features to connect cyanine dye absorption with the particle-in-a-box model.
Preprints and submitted manuscripts
Listed separately from published and accepted papers, with the status shown for each.
A Machine Learning Approach to Examine Personality, Adjustment, and Engineering Identity Among College Engineering Students
Manuscript, 2023 (Submitted manuscript)
Investigates how personality traits and college adjustment relate to academic achievement and engineering identity using machine learning.