Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
A lightweight reward-trained module that adds composable reasoning skills to frozen language models.
arXivI am a Ph.D. student at KAIST, advised by Prof. Jong Chul Ye. I study how to make language models reason, retrieve evidence, and respond to rewards more effectively.
My research focuses on language model reasoning, retrieval-augmented generation, reinforcement learning, and reward-guided model behavior, with applications in general reasoning and clinical AI.
A lightweight reward-trained module that adds composable reasoning skills to frozen language models.
arXivA training-free retrieval planner that searches for evidence useful to a decision, rather than broadly relevant context.
arXivLongitudinal clinical reasoning with verifiable intermediate rewards for real-world dementia prognosis.
arXivA particle-swarm-inspired framework for evolving reusable reasoning skills across a population of agents.
arXivGrounded score distillation for precise image edits with multiple attributes and spatial constraints.
arXivRAG pipeline for clinical decision support
LLM-based dementia data processing and support platform
Graduate coursework and research in solid-state physics
Universal Reasoner · 2nd Prize in Signal Processing
Ground-A-Score · Top 2% paper
Advisor: Prof. Jong Chul Ye
Diffusion models and LLM-guided image editing
Full scholarship · Early graduation · 3.95/4.3