Full paper lists

Preprints

Chanwoo Park, Asuman Ozdaglar, “Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex”, arXiv preprint arXiv:2607.23333. pdf
Chanwoo Park, Mingyang Liu, Dingwen Kong, Kaiqing Zhang, Asuman Ozdaglar, “RLHF with Diverse Feedback via Personalization and Preference Aggregation”, Submitted. pdf
Seungju Han, Konwoo Kim, Chanwoo Park, Benjamin Newman, Suhas Kotha, Jaehun Jung, James Zou, Yejin Choi, “Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG”, arXiv preprint arXiv:2603.23562. pdf
Yubin Kim, Chanwoo Park, Taehan Kim, Eugene Park, Samuel Schmidgall, Salman Rahman, Chunjong Park, Cynthia Breazeal, Xin Liu, Hamid Palangi, Hae Won Park, Daniel McDuff, “TeamBench: Evaluating Agent Coordination under Enforced Role Separation”, arXiv preprint arXiv:2605.07073. pdf
Hwangyu Jeong, Chanwoo Park, “Masked Diffusion Training Induces Resampling-like Carry Representations in Addition”, ICML 2026 Workshop on Mechanistic Interpretability, (C. Park - corresponding author). pdf
Hyunin Lee, Chanwoo Park, Somayeh Sojoudi, Negar Mehr, “A Prospect Theoretic Rationality: Loss Aversion Can Accelerate Reinforcement Learning”, Submitted
Jaeyeon Kim, Chanwoo Park, Asuman Ozdaglar, Jelena Diakonikolas, Ernest K. Ryu, “Mirror Duality in Convex Optimization”, Submitted. pdf
Zae Myung Kim, Chanwoo Park, Vipul Raheja, Dongyeop Kang, “Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models”, Submitted. pdf
Yubin Kim, Hyewon Jeong, Chanwoo Park, MingYu Lu, Eugene W Park, Haipeng Zhang, Xin Liu, Hyeonhoon Lee, Daniel McDuff, Cynthia Breazeal, Samir Tulebaev, Hae Won Park, “Tiered Agentic Oversight: A Hierarchical Multi-Agent System for AI Safety in Healthcare”, Submitted
Yubin Kim, Zhiyuan Hu, Hyewon Jeong, Eugene Park, Shuyue Stella Li, Chanwoo Park, Shiyun Xiong, MingYu Lu, Hyeonhoon Lee, Xin Liu, Daniel McDuff, Cynthia Breazeal, Samir Tulebaev, Hae Won Park, “BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity Spectrum”, Submitted. pdf
Gunmin Lee, Jae Seok Heo, Dohyeong Kim, Jeongwoo Oh, Minyoung Hwang, Chanwoo Park, Kyungjae Lee, Songhwai Oh, “SafeIL: Safety Constrained Imitation Learning for Autonomous Systems”, Submitted.
MITAIR Initiative, “Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts”, arXiv preprint arXiv:2606.04490. pdf

Published Papers

Chanwoo Park, Ziyang Chen, Asuman Ozdaglar, Kaiqing Zhang, “Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach”, ICML 2026. pdf
Chanwoo Park, Seungju Han, Xingzhi Guo, Asuman Ozdaglar, Kaiqing Zhang, Joo-Kyung Kim, “MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning”, ACL 2025, main paper, pdf
Chanwoo Park*, Xiangyu Liu*, Asuman Ozdaglar, Kaiqing Zhang, “Do LLM Agents Have Regret? A Case Study in Online Learning and Games”, pdf, ICLR 2025, Oral presentation at How Far Are We From AGI, ICLR 2024, Invited Talk at INFORMS 2024
Gagik Magakyan, Amirhossein Reisizadeh, Chanwoo Park, Pablo A. Parrilo, Asuman Ozdaglar, “Collaborative and Efficient Fine-tuning: Leveraging Task Similarity”, ICML 2026. pdf
Yubin Kim, Ken Gu, Chanwoo Park, Chunjong Park, Samuel Schmidgall, A. Ali Heydari, Yao Yan, Zhihan Zhang, et al., “Capable Language Models Can Outgrow the Benefits of Collaboration”, Nature Machine Intelligence, 2026. Earlier preprint title: “Towards a Science of Scaling Agent Systems”. pdf
Hyunin Lee, Chanwoo Park, David Abel, Ming Jin, Javad Lavaei, Somayeh Sojoudi, “A Black Swan Hypothesis: the Role of Human Perception in Unchanging Environments”, ICLR 2025. pdf, Oral Presentation at Financial AI, ICLR 2025
Yubin Kim, Chawoo Park, Hyewon Jeong, Yik Siu Chan, Xuhai Xu, Daniel McDuff, Marzyeh Ghassemi, Cynthia Breazeal, Hae Won Park, “Adaptive Collaboration Strategy for LLMs in Medical Decision Making”, NeurIPS 2024, Oral, pdf
Chanwoo Park, Ernest K. Ryu, “Optimal First-Order Algorithms as a Function of Inequalities”, Journal of Machine Learning (JMLR) 2024 pdf
Minyoung Hwang, Luca Weihs, Chanwoo Park, Kimin Lee, Aniruddha Kembhavi, Kiana Ehsani, “Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences”, CVPR 2024, pdf
Chanwoo Park*, Kaiqing Zhang*, Asuman Ozdaglar, “Multi-Player Zero-Sum Markov Games with Networked Separable Interactions”, NeurIPS 2023, Invited Talk at INFORMS 2023 pdf
Jaeyeon Kim*, Asuman Ozdaglar*, Chanwoo Park*, Ernest K. Ryu*, “Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value”, NeurIPS 2023, (Oral presentation at Duality Principles for Modern ML, ICML 2023), pdf
Chanwoo Park*, Sangdoo Yun*, Sanghyuk Chun, “A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective”, NeurIPS 2022pdf
Chanwoo Park, Jisun Park, Ernest K. Ryu, “Factor-$\sqrt{2}$ Acceleration of Accelerated Gradient Methods”, Applied Mathematics and Optimization, 2022 pdf
Chanwoo Park, Boram Kim, Taesung Park, “DeepHisCoM: Deep Learning based Pathway Analysis”, Briefings in Bioinformatics, 2022 pdf
Jongmin Lee, Chanwoo Park, Ernest K. Ryu, “A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast”, NeurIPS 2021 pdf
Chanwoo Park, Nan Jiang, Taesung Park, “Pure additive contribution of genetic variants to a risk prediction model using propensity score matching: application to type 2 diabetes”, Genomics & Informatics, Vol. 17, No. 4, Dec. 2019. pdf