Seungyong Moon
Graduate Student Researcher
Seoul, South Korea
Summary
👤
Senior🎓
Top SchoolSeungyong Moon is a PhD candidate and graduate student researcher at Seoul National University with eight years of research experience at the intersection of language reasoning, reinforcement learning, and adversarial robustness. His work spans neural reasoning and automated theorem proving to practical RL applications in gaming and medical control, informed by internships at Qualcomm, KRAFTON, DeepMetrics, NAVER, and HKUST. He focuses on generalization in RL and reasoning/planning with large language models, bringing both theoretical rigor and applied systems experience. Based in Seoul, he combines a math-and-economics undergraduate background with deep CS training, enabling a quantitative approach to complex AI problems. An uncommonly broad internship portfolio hints at an ability to translate core research into domain-specific solutions.
8 years of coding experience
Doctor of Philosophy - PhD, computer science and engineering, Doctor of Philosophy - PhD, computer science and engineering at Seoul National University
Github Skills (29)
language-modeling10
transformer-architecture10
reinforcement-learning9
nlp9
deep-learning8
machine-learning8
minecraft7
adversarial-attacks7
adversarial-machine-learning7
optimization7
transformer7
mujoco6
explore6
language-model6
spectrum6
Programming languages (1)
Github contributions (5)
drillermoon/Conditional-Similarity-Network-MNIST
May 2018 - Jun 2018
Contributions:50 commits, 44 pushes, 1 branch in 1 month
snu-mllab/parsimonious-blackbox-attack
May 2019 - Dec 2020
Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization (ICML 2019)
Contributions:8 commits, 5 pushes, 4 comments in 1 year 7 months
pytorchadversarial-attacksboxadversarial-machine-learningadversarial
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.