Papers

Asterisks (*) denote equal contribution as a co-first author.

Preprints

• “Betting on Bets: Anytime-Valid Tests for Stochastic Dominance”
  Y. J. Choe*, S. Arnold*, M. Scarsini, I. Tsetlin
  arXiv preprint, 2026
  

  • Presenting at HBS EEO Workshop, IMS NRC Asia, and SAVI 2026
  • Links: arXiv

• “The Information Geometry of Softmax: Probing and Steering”
  K. Park, T. Nief, Y. J. Choe, V. Veitch
  Submitted, 2026
  

  • Links: arXiv, code

• “On the Significance of Softmax Geometry: Interpretability and Token Decoding”
  Y. Jiang, L. Gui, S. M. Richardson, M. Muchane, Y. J. Choe, V. Veitch
  Submitted, 2026

Publications

• “Combining Evidence Across Filtrations”
  Y. J. Choe, A. Ramdas
  Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2026
  

  • Invited talk at SAVI 2025 & ICSDS 2024; contributed talk at JSM 2024
  • Links: arXiv, slides (SAVI 2025), slides (ICSDS 2024), code, blog

• “The Geometry of Categorical and Hierarchical Concepts in LLMs”
  K. Park, Y. J. Choe, Y. Jiang, V. Veitch
  International Conference on Learning Representations (ICLR), 2025
  

  • Oral Presentation (Top 1.8% of all submitted papers)
  • Best Paper Award, ICML 2024 Workshop on Mechanistic Interpretability
  • Links: arXiv, slides, poster, code, video (ICLR 2025)

• “The Linear Representation Hypothesis and the Geometry of LLMs”
  K. Park, Y. J. Choe, V. Veitch
  International Conference on Machine Learning (ICML), 2024
  

  • Presented at NeurIPS 2023 Workshop on Causal Representation Learning
  • Links: arXiv, slides, poster, code

• “Counterfactually Comparing Abstaining Classifiers”
  Y. J. Choe, A. Gangrade, A. Ramdas
  Advances in Neural Information Processing Systems (NeurIPS), 2023
  

  • Presented at INFORMS 2024 (invited session on Causal Inference; slides) & ICML 2023 Workshop on Counterfactuals in Minds and Machines
  • Links: proceedings, arXiv, slides (full-length), poster, code, video (15-min talk)

• “Comparing Sequential Forecasters”
  Y. J. Choe, A. Ramdas
  Operations Research, 2023
  

  • Poster Award (Runner-up w/ $10K Research Grant), Citadel Securities Inaugural PhD Summit
  • Presented at the 1st Workshop on Safe, Anytime-Valid Inference and Game-theoretic Statistics (SAVI 2022)
    
  • Links: journal, arXiv, slides, poster, code

• “KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding”
  J. Ham*, Y. J. Choe*, K. Park*, I. Choi, H. Soh
  Findings of the ACL: EMNLP (EMNLP-Findings), 2020

  • Links: proceedings, arXiv, data

• “word2word: A Collection of Bilingual Lexicons for 3,564 Language Pairs”
  Y. J. Choe*, K. Park*, D. Kim*
  Language Resources and Evaluation Conference (LREC), 2020

  • Links: proceedings, arXiv, code

• “Jejueo Datasets for Machine Translation and Speech Synthesis”
  K. Park, Y. J. Choe, J. Ham
  Language Resources and Evaluation Conference (LREC), 2020

  • Links: proceedings, arXiv, code
    

• “Predicting Drug–Target Interaction Using a Novel Graph Neural Network with 3D Structure-Embedded Graph Representation”
  J. Lim, S. Ryu, K. Park, Y. J. Choe, J. Ham, W. Y. Kim
  Journal of Chemical Information and Modeling, 2019

  • Links: journal, arXiv

• “A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learning”
  Y. J. Choe*, J. Ham*, K. Park*, Y. Yoon*
  Workshop on Building Educational Applications (BEA), 2019
  (Peer-reviewed & published in official proceedings. Publisher: ACL.)

  • Runner-up (Top-2 Submission), BEA Workshop Shared Task
  • Links: proceedings, arXiv, code

• “Discovery of Natural Language Concepts in Individual Units of CNNs”
  S. Na, Y. J. Choe, D. Lee, G. Kim
  International Conference on Learning Representations (ICLR), 2019

  • Links: proceedings, arXiv, code

• “Local White Matter Architecture Defines Functional Brain Dynamics”
  Y. J. Choe, S. Balakrishnan, A. Singh, J. M. Vettel, T. Verstynen
  IEEE Int’l Conference on Systems, Man, and Cybernetics (IEEE SMC), 2018
  

  • Franklin V. Taylor Memorial Award (for Best Paper & Oral Presentation), IEEE SMC Society
  • Links: proceedings, arXiv, slides

Ph.D. Thesis

• “Comparing Forecasters and Abstaining Classifiers”
  Y. J. Choe
  Ph.D. Thesis, Carnegie Mellon University, 2023
  • Links: kilthub, slides

Miscellaneous Articles

• “Discussion of ‘Statistical exploration of the Manifold Hypothesis’ by Whiteley, Gray and Rubin-Delanchy”
  K. Park, Y. J. Choe, Y. Jiang
  Journal of the Royal Statistical Society Series B: Statistical Methodology (Discussion Paper Contribution), 2026

  • Links: article

• “An Empirical Study of Invariant Risk Minimization”
  Y. J. Choe, J. Ham, K. Park
  ICML Workshop on Uncertainty and Robustness in Deep Learning, 2020

  • Links: arXiv, code, slides

• “Probabilistic Interpretations of Recurrent Neural Networks”
  Y. J. Choe*, J. Shin*, N. Spencer*
  Technical Report, 2017

• “A Statistical Analysis of Neural Networks”
  Y. J. Choe
  Technical Report, 2016

• “Learning Diverse Overcomplete Dictionaries via Determinantal Priors”
  M. Al-Shedivat, Y. J. Choe, N. Spencer, E. P. Xing
  ICML Workshop on Geometry in Machine Learning, 2016