Intro
I am a 4th year PhD student at the Algorithmic Intelligence Lab at KAIST AI, advised by Prof. Jinwoo Shin. My research focuses on developing reliable, efficient, and personalized intelligent systems, with an emphasis on post-training methods for improving the alignment, reasoning, and agentic capabilities of language models. More broadly, I am interested in generative models, reinforcement learning, safety, nature-inspired intelligence, and the general principles underlying intelligence. I always strive to more deeply understand the fundamental principles behind everything I work on.
Previously, I was a senior software engineer at Google, developing machine learning methods for localizing Google Search to low-resource languages. I also worked in Display Ads, building backend systems and improving auction algorithms for better user experience. I received an MS in Computer Science from Stanford University and a BS in Computer Science with a minor in Applied Mathematics from Cornell University.
Selected Publications
- Learning to Program Retrievals: Composing Search Primitives via Reinforcement Learning
- Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
- Self-Refining Language Model Anonymizers via Adversarial Distillation
- Personalized Language Models via Privacy-Preserving Evolutionary Model Merging
- Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents
- Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
- Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback
- Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models