창호 · CHAHNG-hoh volume_up
Postdoc at Princeton University
email cs1095@princeton.eduI am a postdoctoral researcher in the Department of Computer Science at Princeton University, where I work with Brenden Lake. I completed my Ph.D. in Computer Science at the University of Wisconsin–Madison under the supervision of Frederic Sala. Prior to that, I studied psychology and computer science at Seoul National University and earned a Master’s degree under the supervision of Wonjong Rhee.
My research explores how humans can effectively guide increasingly capable AI systems, and how these systems can, in turn, better understand and support people. I investigate the principles and methods of scalable supervision and oversight, including weak supervision, weak-to-strong generalization, reliable LLM evaluation, and self-improvement. I also study human learning and cognition to help build AI systems that better understand and empower people.
[P3] Modeling Student Arithmetic Reasoning by Distilling Cognitive Priors into Language Models, Under Review
Max Gupta*, Changho Shin*, Brenden Lake, Tammy Kwan
[P2] VoirDire: Counterfactual Calibration for Reliable LLM-as-a-Judge Aggregation, arXiv preprint, 2026
Changho Shin, Frederic Sala
[P1] Compositional Self-Improvement: Promises and Pitfalls, arXiv preprint, 2026
Changho Shin, Daiwei Chen, Brenden Lake, Frederic Sala, Ramya Korlakai Vinayak
[C10] SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks, NeurIPS 2026
Gabriel Orlanski, Devjeet Roy, Alexander Yun, Changho Shin, Alex Gu, Albert Ge, Dyah Adila, Nicholas Roberts, Frederic Sala, Aws Albarghouthi
[C9] Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics, COLM 2026
Changho Shin, David Alvarez-Melis
[C8] CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation, ICML 2026
Jitian Zhao*, Changho Shin*, Tzu-Heng Huang, Srinath Namburi, Frederic Sala
[C7] Weak-to-Strong Generalization Through the Data-Centric Lens, ICLR 2025
Changho Shin, John Cooper, Frederic Sala
[C6] Personalize Your LLM: Fake it then Align it, NAACL 2025 Findings
Yijing Zhang, Dyah Adila, Changho Shin, Frederic Sala
[C5] OTTER: Improving Zero-Shot Classification via Optimal Transport, NeurIPS 2024
Changho Shin, Jitian Zhao, Sonia Cromp, Harit Vishwakarma, Frederic Sala
[C4] Zero-Shot Robustification of Zero-Shot Models, ICLR 2024
Also presented in NeurIPS 2023 R0-FoMo Workshop (Best Paper Award Honorable Mention)
Dyah Adila*, Changho Shin*, Linrong Cai, Frederic Sala
[C3] Mitigating Source Bias for Fairer Weak Supervision, NeurIPS 2023
Changho Shin, Sonia Cromp, Dyah Adila, Frederic Sala
[C2] Universalizing Weak Supervision, ICLR 2022
Changho Shin, Winfred Li, Harit Vishwakarma, Nicholas Roberts, Frederic Sala
[C1] Subtask Gated Networks for Non-Intrusive Load Monitoring, AAAI 2019
Changho Shin, Sunghwan Joo, Jaeryun Yim, Hyoseop Lee, Taesup Moon, and Wonjong Rhee
[J2] The ENERTALK dataset, 15 Hz electricity consumption data from 22 houses in
Korea, Scientific Data
Changho Shin, Eunjung Lee, Jeongyun Han, Jaeryun Yim, Hyoseop Lee, and Wonjong Rhee
[J1] Data Requirements for Applying Machine Learning to Energy Disaggregation, Energies
Changho Shin, Seungeun Rho, Hyoseop Lee, and Wonjong Rhee
[W7] Coarse-to-Fine Category Structure in Child’s-View Model Representations, NeurIPS 2026 DevAI Workshop
Changho Shin, Jeonghwan Cheon, Brenden Lake
[W6] Compositional Self-Improvement, ICML 2026 CompLearn Workshop
Changho Shin, Daiwei Chen, John Cooper, Brenden Lake, Frederic Sala, Ramya Korlakai Vinayak
[W5] LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting, NeurIPS 2025 BERT2S Workshop
Sungjun Cho, Changho Shin, Suenggwan Jo, Xinya Yan, Shourjo Aditya Chaudhuri, Frederic Sala
[W4] Is Free Self-Alignment Possible?, NeurIPS 2024 MINT Workshop
Dyah Adila, Changho Shin, Yijing Zhang, Frederic Sala
[W3] Pool-Search-Demonstrate: Improving Data-wrangling LLMs via better in-context examples, NeurIPS 2023 TRL Workshop (Oral)
Changho Shin*, Joon Suk Huh*, Elina Choi
[W2] Multimodal Data Curation via Object Detection and Filter Ensembles, ICCV 2023 DataComp Workshop (Filtering Track Rank #1 (Small))
Changho Shin*, Tzu-Heng Huang*, Sui Jiet Tay, Dyah Adila, Frederic Sala
[W1] Can we get smarter than majority vote? Efficient use of individual rater’s labels for content moderation, NeurIPS 2022 ENLSP Workshop
Changho Shin, Alice Schoenauer Sebag