Devin White
Scholar

Devin White

Google Scholar ID: 9sorVs8AAAAJ
Machine Learning Researcher, Army Educational Outreach Program
RLHFHuman Guided Reinforcement LearningAI AlignmentLarge Language ModelsSmall Language Model
Citations & Impact
All-time
Citations
43
 
H-index
3
 
i10-index
2
 
Publications
8
 
Co-authors
7
list available
Resume (English only)
Academic Achievements
  • Paper accepted to AAAI 2024 (on RbRL)
  • Two papers accepted to AAAI 2025 Collaborative AI and Modelling of Humans Bridge Program
  • One paper accepted to AAAI 2025 Toward Knowledgeable Foundation Models Workshop
  • Work presented at ICML 2023 Many Facets of Preference Learning Workshop
  • Research presented at 2022 Army Research Labs Humans in Complex Systems Technical Advisory Board meeting (hosted by National Academy of Sciences)
  • Paper accepted to AIAA Guidance, Navigation, and Controls Conference 2024
Research Experience
  • Oct 2023–Present: Machine Learning Researcher at AEOP (Army Educational Outreach Program), working on RbRL optimization and LLM benchmarking in Atari
  • Sep 2022–Dec 2023: Graduate Research Assistant at UTSA, finalized RbRL research and worked on time-constrained intercept guidance
  • Jan 2022–Aug 2022: Technical Laboratory Assistant II at UTSA, designed IRB-approved user study and built custom Gymnasium environment for RL
  • Aug 2021–Dec 2021: Undergraduate Research Assistant at UTSA, led a team of four in implementing RbRL in Atari environments
  • Jun 2021–Aug 2021: NSF REU participant at UTSA, gained hands-on AI research experience through projects and lectures
Background
  • Machine Learning Researcher with an M.S. in Artificial Intelligence
  • Specializes in emergent capabilities of Large Language Models (LLMs) in interactive environments (e.g., Atari)
  • Expertise in Reinforcement Learning (RL), Reinforcement Learning from Human Feedback (RLHF), particularly Rating-based RL (RbRL)
  • Demonstrated end-to-end research capability with 5 publications in top AI venues
  • Proficient in Python, PyTorch, TensorFlow, Stable Baselines3, and other AI/ML tools