Dongyoung Kim
Graduate student at KAIST
KAIST AI
kingdy2002 [AT] kaist.ac.kr
About
I am a 2nd 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 goal is to build generally intelligent robots that can understand the real world and adapt to diverse situations. To achieve this, my research focuses on Vision-Language-Action (VLA) models, specifically on enhancing their world understanding and strengthening embodied reasoning. To this end, I have conducted research on aligning VLMs and LLMs through reinforcement learning, improving the spatiotemporal understanding of vision models, and optimizing policies with RL.
Publications
Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
Dongyoung Kim, Sumin Park,Huiwon Jang, Jinwoo Shin, Jaehyung Kim*, Younggyo Seo*
Conference on Neural Information Processing Systems (NeurIPS), 2025
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%)
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
Debiasing Online Preference Learning via Preference Feature Preservation
Dongyoung Kim, Jinsung Yoon,Jinwoo Shin, Jaehyung Kim
Annual Meeting of the Association for Computational Linguistics (ACL) 2025 (Findings)
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
Training-free LLM Verification via Recycling Few-shot Examples
Dongseok Lee, Jimyung Hong, Dongyoung Kim, Jaehyung Kim
International Conference on Machine Learning (ICML) 2025 Workshop ES-FoMo-III
RoboAlign: Reinforcement Learning for Action-Aligned Multimodal Large Language Models
Dongyoung Kim, Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim, Huiwon Jang, Jaehyung Kim, Younggyo Seo, Jinwoo Shin
Preprint
SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning
Byoungwooo Jeon*, Dongyoung Kim*,Huiwon Jang,Jinwoo Shin
Preprint
Contrastive Representation Regularization for Vision-Language-Action Models
Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin
Preprint
INFUSER: Injecting Synthetic Failures for Self-Correcting Embodied Agents
Byungjun Yoon, Dongyoung Kim, Jaehyun Nam, Wook Jung, Jinwoo Shin
Preprint
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
John Won, Kyungmin Lee, Huiwon Jang, Dongyoung Kim, Jinwoo Shin
Preprint
Verifier-free Test-Time Sampling for Vision Language Action Models
Suhyeok Jang, Dongyoung Kim, Changyeon Kim, Youngsuk Kim, Jinwoo Shin
Preprint
Collaborative LLM Inference via Planning for Efficient Reasoning
Byeongchan Lee, Jonghoon Lee, Dongyoung Kim, Jaehyung Kim, Jinwoo Shin
Preprint
Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
Dongyoung Kim, Sumin Park,Huiwon Jang, Jinwoo Shin, Jaehyung Kim*, Younggyo Seo*
Conference on Neural Information Processing Systems (NeurIPS), 2025
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%)
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
Debiasing Online Preference Learning via Preference Feature Preservation
Dongyoung Kim, Jinsung Yoon,Jinwoo Shin, Jaehyung Kim
Annual Meeting of the Association for Computational Linguistics (ACL) 2025 (Findings)
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
Training-free LLM Verification via Recycling Few-shot Examples
Dongseok Lee, Jimyung Hong, Dongyoung Kim, Jaehyung Kim
International Conference on Machine Learning (ICML) 2025 Workshop ES-FoMo-III
RoboAlign: Reinforcement Learning for Action-Aligned Multimodal Large Language Models
Dongyoung Kim, Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim, Huiwon Jang, Jaehyung Kim, Younggyo Seo, Jinwoo Shin
Preprint
SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning
Byoungwooo Jeon*, Dongyoung Kim*,Huiwon Jang,Jinwoo Shin
Preprint
Contrastive Representation Regularization for Vision-Language-Action Models
Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin
Preprint
INFUSER: Injecting Synthetic Failures for Self-Correcting Embodied Agents
Byungjun Yoon, Dongyoung Kim, Jaehyun Nam, Wook Jung, Jinwoo Shin
Preprint
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
John Won, Kyungmin Lee, Huiwon Jang, Dongyoung Kim, Jinwoo Shin
Preprint
Verifier-free Test-Time Sampling for Vision Language Action Models
Suhyeok Jang, Dongyoung Kim, Changyeon Kim, Youngsuk Kim, Jinwoo Shin
Preprint
Collaborative LLM Inference via Planning for Efficient Reasoning
Byeongchan Lee, Jonghoon Lee, Dongyoung Kim, Jaehyung Kim, Jinwoo Shin
Preprint
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
Honors & Awards
Recipient, Google Conference Scholarships (APAC)May. 2025
Travel Award, Conference on Neural Information Processing Systems (NeurIPS) 2023Dec. 2023