Dongyoung Kim
Graduate student at KAIST
KAIST AI
kingdy2002 [AT] kaist.ac.kr
About
I am a 1nd year M.S & Ph.D. student at Algorithmic Intelligence Laboratory (ALIN-LAB), advised by Prof. Jinwoo Shin at Korea Advanced Institute of Science and Technology (KAIST). I received my B.S. in Computer Science School at KAIST in 2024.
My ultimate research goal is to achieve Artificial General Intelligence (AGI) by developing AI models capable of recursive self-improvement. My primary research focuses on reinforcement learning-based approaches, particularly in self-improving systems and test-time reasoning strategies to enhance model performance. I aim to advance these methodologies in key domains such as large language models (LLMs) and robotics.
Publications
Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
Dongyoung Kim, Kimin Lee ,Jinwoo Shin, Jaehyung Kim
International Conference on Learning Representations (ICLR) 2025, Oral Presentation (207/11672=1.77%)
Learning to Correct for QA Reasoning with Black-box LLMs
Jaehyung Kim, Dongyoung Kim, Yiming Yang
Conference on Empirical Methods in Natural Language Processing (EMNLP) 2024 (Long, Main)
Visual Representation Learning with Stochastic Frame Prediction
Huiwon Jang,Dongyoung Kim, Junsu Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
International Conference on Machine Learning (ICML), 2024
Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration
Dongyoung Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
Conference on Neural Information Processing Systems (NeurIPS), 2023
Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
Dongyoung Kim, Kimin Lee ,Jinwoo Shin, Jaehyung Kim
International Conference on Learning Representations (ICLR) 2025, Oral Presentation (207/11672=1.77%)
Learning to Correct for QA Reasoning with Black-box LLMs
Jaehyung Kim, Dongyoung Kim, Yiming Yang
Conference on Empirical Methods in Natural Language Processing (EMNLP) 2024 (Long, Main)
Visual Representation Learning with Stochastic Frame Prediction
Huiwon Jang,Dongyoung Kim, Junsu Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
International Conference on Machine Learning (ICML), 2024
Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration
Dongyoung Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
Conference on Neural Information Processing Systems (NeurIPS), 2023
Education
Korea Advanced Institute of Science and Technology (KAIST)Jun. 2024 - Present
M.S & Ph.D. Student in Artificial Intelligence
Korea Advanced Institute of Science and Technology (KAIST)Mar. 2020 - Jun. 2024
B.S. in Computer Science