Preprint

• Recurisve Harness Self-Improvement
  Hyunin Lee, Jinglue Xu, Jeffrey Seely, Donghyun Lee, Matei Zaharia and Yujin Tang
  Preprint
  [blog]

• Sakana Fugu Technical Report
  Yujin Tang, Edoardo Cetin, Jinglue Xu, Qi Sun, Stefan Nielsen, Vincent Richard, Haruto Goda, Iaroslav Tymchenko, Nhan Nguyen, Hyunin Lee, Mari Ashiga, Shashank Kotyan, So Kuroki, Tarin Clanuwat
  Preprint
  [blog]

• Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models
  Hyunin Lee, Yong Zhang, Hoang Vu Nguyen, Xiaoyi Liu, Namyong Park, Christopher Jung, Rong Jin, Yang Wang, Zhigang Wang, Somayeh Sojoudi, Xue Feng
  Preprint
  [blog]

Journal

• Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction
  Donghao Ying, Mengzi Amy Guo, Hyunin Lee, Yuhao Ding, Javad Lavaei, and Zuo-Jun Max Shen
  Under revision for JAIR, 2024. [codes]

• Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization
  Yuhao Ding, Junzi Zhang, Hyunin Lee, and Javad Lavaei
  IEEE Transactions on Automatic Control (TAC), 2023.

• Explainable Deep Learning Model for EMG-Based Finger Angle Estimation using Attention
  Hyunin Lee, Dongwook Kim, and Yong-Lae Park
  IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE), 2022.
  [slides] [videos] [codes]

Conference

• Position: AI Safety Must Embrace an Antifragile Perspective
  Ming Jin, Hyunin Lee
  International Conference on Machine Learning (ICML), 2025.

• A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
  Hyunin Lee, Chanwoo Park, David Abel, and Ming Jin
  International Conference on Learning Representation (ICLR), 2025.
  ICLR 25 Financial AI workshop (Oral, top 1%).
  [slides]

• Pausing Policy Learning in Non-stationary Reinforcement Learning.
  Hyunin Lee, Ming Jin, Javad Lavaei, and Somayeh Sojoudi
  International Conference on Machine Learning (ICML), 2024, (Oral, top 1%)
  [Talk]

• Tempo Adaption in Non-stationary Reinforcement Learning.
  Hyunin Lee, Yuhao Ding, Jongmin Lee, Ming Jin, Javad Lavaei, and Somayeh Sojoudi
  Neural Information Processing Systems (NeurIPS), 2023
  [slides] [codes]

• Initial State Interventions for Deconfounded Imitation Learning
  Samuel Pfrommer, Yatong Bai, Hyunin Lee, and Somayeh Sojoudi
  IEEE Conference on Decision and Control (CDC), 2023.