Sunnie
S. Y. Kim
I am a PhD student in Computer Science at Princeton University advised by Olga Russakovsky. I also work closely with Andrés Monroy-Hernández, Ruth Fong, and Tania Lombrozo at Princeton, as well as Jenn Wortman Vaughan and Q. Vera Liao at Microsoft Research FATE who I previously interned with. My PhD is supported by the NSF Graduate Research Fellowship.
I work on responsible AI—specifically, on improving transparency, explainability, and fairness of AI systems and helping people have appropriate understanding and trust in them. I publish in both AI and HCI venues and enjoy organizing events that connect the two communities.
Previously, I received a BSc degree in Statistics and Data Science at Yale University where I worked with John Lafferty, Jay Emerson, and Woo-kyoung Ahn. I have also spent time at TTI-Chicago working with Greg Shakhnarovich.
My first name is pronounced as sunny🔆 and I use she/her/hers pronouns. In my free time, I like to run, play tennis, and read Korean books!
News
08/2024:
06/2024:
06/2024:
06/2024:
05/2024:
05/2024:
Selected Papers
See the full list of papers here
"I'm Not Sure, But...": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust
FAccT 2024 ●
PAPER ●
OSF
* Featured in Axios, ACM showcase, and the Human-Centered AI medium publication as Good Reads in Human-Centered AI.
"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction
CHI 2023 BEST PAPER HONORABLE MENTION ●
PAPER ●
WEBSITE ●
TALK
* Featured in the Human-Centered AI medium publication as CHI 2023 Editors' Choice. Selected as a panel presentation at the NeurIPS 2022 Human-Centered AI Workshop. Also presented at the CHI 2023 Human-Centered Explainable AI Workshop.
Humans, AI, and Context: Understanding End-Users’ Trust in a Real-World Computer Vision Application
FAccT 2023 ●
PAPER ●
WEBSITE ●
TALK
* Featured in the Montreal AI Ethics Institute's newsletter and website. Also presented at the CHI 2023 Trust and Reliance in AI-assisted Tasks Workshop.
Overlooked Factors in Concept-based Explanations: Dataset Choice, Concept Learnability, and Human Capability
CVPR 2023 ●
PAPER ●
CODE ●
TALK
HIVE: Evaluating the Human Interpretability of Visual Explanations
ECCV 2022 ●
PAPER ●
WEBSITE ●
CODE ●
TALK
* Selected as a spotlight talk at the CVPR 2022 Explainable AI for Computer Vision Workshop. Also presented at the CHI 2022 Human-Centered Explainable AI Workshop and the CVPR 2022 Women in Computer Vision Workshop.
Fair Attribute Classification through Latent Space De-biasing
CVPR 2021 ●
PAPER ●
WEBSITE ●
CODE ●
DEMO ●
TALK
* Featured in Coursera's GANs Specialization course and the MIT Press book Foundations of Computer Vision. Invited for talks at the CVPR 2021 Responsible Computer Vision Workshop and the CVPR 2021 Women in Computer Vision Workshop.
Organized Workshops
The 3rd Explainable AI for Computer Vision (XAI4CV) Workshop
CVPR 2024 ●
WEBSITE
The 4th Human-Centered Explainable AI (HCXAI) Workshop
CHI 2024 ●
WEBSITE ●
PROPOSAL
The 2nd Explainable AI for Computer Vision (XAI4CV) Workshop
CVPR 2023 ●
WEBSITE
The 11th Women in Computer Vision (WiCV) Workshop
CVPR 2023 ●
WEBSITE ●
REPORT
Other Important Things
Teaching & Outreach
●
●
●
●
●
Mentoring & Community Building
●
●
●
●
Reviewing
●
●
●
Volunteering
●
●
Committee
●
●