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.

News

• (Sep. 2024) Our paper on effortless label distribution adaptation is accepted at NeurIPS 2024!
• (Jun. 2024) New preprint on free self-alignment!
• (Jun. 2024) Started my summer internship at Snorkel AI!
• (Feb. 2024) Our team (with Dyah Adila) is shortlisted as one of the finalists in Qualcomm Innovation Fellowship 2024!
• (Jan. 2024) Our paper on robustifying foundation models is accepted at ICLR 2024!
• (Dec. 2023) Our paper on robustifying foundation models was a best paper award honorable mention at the NeurIPS R0-FoMo workshop!
• (Oct. 2023) A course team project on data wrangling with LLM using retrieval-based in-context examples is accepted at NeurIPS 2023 TRL workshop!
• (Oct. 2023) New preprint on utilizing knowledge from language model for zero-shot classification! It’s accepted at NeurIPS 2023 R0-FoMo workshop!
• (Sep. 2023) Our paper on fair weak supervision is accepted at NeurIPS 2023!
• (Sep. 2023) Our team won DataComp competition filtering track (small)!
• (Oct. 2022) My internship project on efficient use of crowd sourced labels is accepted at NeurIPS 2022 ENLSP-II workshop!
• (Jun. 2022) Started my summer internship at Twitter!
• (Jan. 2022) Our paper on applying weak supervision to any metric spaces is accepted at ICLR 2022!

Preprints

[P3] Weak-to-Strong Generalization Through the Data-Centric Lens, Under Review
Changho Shin, John Cooper, Frederic Sala

[P2] Is Free Self-Alignment Possible?, Under Review
Dyah Adila, Changho Shin, Yijing Zhang, Frederic Sala

[P1] Personalize Your LLM: Fake it then Align it, Under Review
Yijing Zhang, Dyah Adila, Changho Shin, Frederic Sala

Conference Publications

[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

Journal Publications

[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

Workshop Publications

[W4] Foundation Models Can Robustify Themselves, For Free, 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 (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

AWARDS

• Qualcomm Innovation Fellowship Finalist, 2024
• Best Paper Award Honorable Mention (NeurIPS R0-FoMo Workshop), 2023
• NeurIPS 2023 Scholar Award, 2023
• Rank #1 in DataComp competition filtering track (small) (ICCV TNGCV Workshop), 2023
• CS Departmental Scholarship (University of Wisconsin-Madison), 2020
• Merit-based Scholarship (SNU), 2015

Work Experience

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

• Research Intern

apartment Twitter, San Francisco, CA ^{2022.06 - 2022.08}

• Machine Learning Engineer Intern, Health Team

apartment Encored Technologies, Seoul, Korea ^{2018.01 - 2020.07}

• Data Scientist, Applied Research Team
• Projects: Deep Learning in NILM, Appliance Promotion based on Disaggregated Appliance Usage, Anomaly Detection in Photovoltaic System, Solar Power Generation Prediction

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

• Researcher, Defense Information Planning Division
• Topics: Informatization Policy, Artificial Intelligence

Teaching Experience

school University of Wisconsin-Madison ^{2020.09 -}

• Teaching assistant for CS 839 (Foundation Models and the Future of Machine Learning), Fall 2023
• Teaching assistant for CS 300 (Programming II), Fall 2022, Spring 2023
• Teaching assistant for CS 760 (Machine Learning), Fall 2021, Spring 2022
• Teaching assistant for CS 320 (Data Programming II), Spring 2021
• Teaching assistant for CS 220 (Data Programming I), Fall 2020