Changho Shin

(신창호, @ch-shin)

Face

Ph.D. Student in CS at University of Wisconsin-Madison

email cshin23@wisc.edu
Twitter
Github
insert_drive_file CV

I am a fifth-year PhD student in Computer Science at University of Wisconsin-Madison, where I am fortunate to be advised by Frederic Sala. Before that, I was a master’s student at Seoul National University, where I was lucky to learn deep learning, exploratory data analysis, and information theory from Wonjong Rhee. Prior to that, I received B.A in Psychology and B.S. in Computer Science and Engineering from Seoul National University.

My research focuses on data-centric AI, with an emphasis on programmatic weak supervision and weak-to-strong generalization in foundation models. Additionally, I am developing techniques that enable zero-shot adaptation of foundation models without fine-tuning, addressing challenges related to data distribution shifts.

I expect to graduate with my Ph.D. in Summer 2025 and am actively seeking industry researcher positions.

Publications

[P4] Weak-to-Strong Generalization Through the Data-Centric Lens, Under Review
Changho Shin, John Cooper, Frederic Sala

[P3] TARDIS: Mitigate Temporal Misalignment via Representation Steering, Under Review
Changho Shin, Xinya Yan, Frederic Sala

[P2] Evaluating Language Model Context Windows: A” Working Memory” Test and Inference-time Correction, Under Review
Amanda Dsouza, Christopher Glaze, Changho Shin, Frederic Sala

[P1] Is Free Self-Alignment Possible?, Under Review
Dyah Adila, Changho Shin, Yijing Zhang, 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

[W3] Pool-Search-Demonstrate: Improving Data-wrangling LLMs via better in-context examples, NeurIPS 2023 TRL Workshop
Changho Shin*, Joon Suk Huh*, Elina Choi

[W2] Multimodal Data Curation via Object Detection and Filter Ensembles, ICCV 2023 DataComp Workshop
Changho Shin*, Tzu-heng Huang*, Sui Jiet Tay, Dyah Adila, Frederic Sala

[C3] Mitigating Source Bias for Fairer Weak Supervision, NeurIPS 2023
Changho Shin, Sonia Cromp, 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

[C2] Universalizing Weak Supervision, ICLR 2022
Changho Shin, Winfred Li, Harit Vishwakarma, Nicholas Roberts, Frederic Sala

[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

[C1] Subtask Gated Networks for Non-Intrusive Load Monitoring, AAAI 2019
Changho Shin, Sunghwan Joo, Jaeryun Yim, Hyoseop Lee, Taesup Moon, and Wonjong Rhee

AWARDS

Work Experience

apartment Snorkel AI, Redwood City, CA (Remote) 2024.06 - 2024.08

apartment Twitter, San Francisco, CA 2022.06 - 2022.08

apartment Encored Technologies, Seoul, Korea 2018.01 - 2020.07

apartment KIDA (Korea Institute for Defense Analyses), Seoul, Korea 2017.01 - 2017.12

Teaching Experience

school University of Wisconsin-Madison 2020.09 -