Young-Jin Park

Young-Jin Park

Building reliable AI • MIT PhD '26 • Ex-Meta, NAVER →

Google Scholar GitHub LinkedIn

About

AI engineer and researcher focused on building reliable AI systems that maintain strong performance and efficiency at scale. Experienced in building and deploying billion-scale production ML systems while developing state-of-the-art models for robotics and large language models. Current work focuses on world models, end-to-end autonomy, and scalable vision-language reasoning systems.

Research Focus
World Modeling, End-to-End Autonomy (Current)
Foundation Model Reliability, Calibration, Reasoning Models, Vision-Language Models (2022 – 2026)
Sequential Decision Making, Recommendation Systems, Reinforcement Learning (2017 – 2022)

Recent Posts

FAQs: Uncertainty, Confidence, and Hallucination
May 2026 Directions
Stochastic Blackbox
Mar 2026 Thoughts
From Reasoning to World Models for Reliable AI
Feb 2026 Directions
View all posts →

Selected Publications

Full publication list available at Google Scholar

LLM Reliabiltiy
Overconfidence & Calibration in Medical VQA: Empirical Findings & Hallucination-Aware Mitigation
J.Y. Byun, Y.J. Park, J.P. Corbeil, and A. Ben Abacha
Under review at Conference on Language Modeling (COLM), 2026
Paper Project Page
Know What You Don't Know: Uncertainty Calibration of Process Reward Models
Y.J. Park, K. Greenewald, K. Alim, H. Wang, and N. Azizan
Neural Information Processing Systems (NeurIPS), 2025 [Featured on MIT News]
Paper Project Page Slides
Robotics
Distilling a Hierarchical Policy for Planning & Control via Representation and Reinforcement Learning
J.S. Ha*, Y.J. Park*, H.J. Chae, S.S. Park, and H.L. Choi
IEEE International Conference on Robotics and Automation (ICRA), 2021
Paper Video
Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems
J.S. Ha, Y.J. Park, H.J. Chae, S.S. Park, and H.L. Choi
Neural Information Processing Systems (NeurIPS), 2018
Paper Video
Time-Series Forecasting
Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models
Y.J. Park, F. Germain, J. Liu, Y. Wang, T. Akino, G. Wichern, N. Azizan, C. Laughman, and A. Chakrabarty
Energy and Buildings, 2025
Paper
A Large-Scale Ensemble Learning Framework for Demand Forecasting
Y.J. Park, D. Kim, F. Odermatt, J. Lee, and K.M. Kim
IEEE International Conference on Data Mining (ICDM), 2022 [Oral Presentation; Top 9.77%]
Paper Slides