About Me

Hello👋! My name is Yoonsu Kim, and I am a Ph.D. student of School of Computing at KAIST.
I am working with Prof. Juho Kim at KIXLAB (KAIST Interaction Lab), and I graduated from KAIST AI with a Master’s Degree.

My research is in Human-AI Interaction (HAI). I am particularly interested in 👀 understanding the difficulties users face when interacting with AI, and 🤖 designing human-centered AI systems that amplify people’s abilities.

I have been focused on designing cognitive collaboration with AI, along three aspects: 🎯 intent alignment, 🧩 context sharing, and 🤝 deliberate delegation for ensuring human agency.

I am also interested in 🎓 AI for education and learning at scale, such as diagnosing students’ problem-solving and cognitive skills with LLMs, and in 🔍 making AI behavior legible to people, such as explaining why vision models fail in natural language.

Through my work, I aim to contribute to helping people better utilize new technology 🌏❤️.

News

Publications

Preprints

  1. Reasoning annotation interface and the distribution of user- and AI-initiated reasoning steps.
    What Did the AI Take On? Characterizing Cognitive Delegation in LLM Reasoning
    Yoonsu Kim, Sean Kim, Kihoon Son, Saelyne Yang, Juho Kim
    Under Review
    Paper
  2. STEPwise interface showing a math problem alongside generated diagnostic sub-questions.
    STEPwise: Supporting Teachers in Diagnosing Students' Mathematical Problem-Solving Skills through LLM-Generated Questions and Rubrics
    Yoonsu Kim, Hayeon Doh, Eunhye Kim, Jinho Son, Juho Kim
    Under Review
    Paper
  3. A user changes a shared canvas to three columns while the agent reverts it to two, illustrating conflicting concurrent edits.
    "When to Hand Off, When to Work Together": Understanding Concurrent Human-Agent Interaction in Shared Co-Creative Workspaces
    Kihoon Son, Hyewon Lee, DaEun Choi, Yoonsu Kim, Tae Soo Kim, Yoonjoo Lee, John Joon Young Chung, HyunJoon Jung, Juho Kim
    Under Review
    Paper Project Page
  4. Benchmarking Large Language Models for Diagnosing Students' Cognitive Skills from Handwritten Math Work
    Benchmarking Large Language Models for Diagnosing Students' Cognitive Skills from Handwritten Math Work
    Yoonsu Kim, Hyoungwook Jin, Hayeon Doh, Eunhye Kim, Dongyun Jung, Seungju Kim, Kiyoon Choi, Jinho Son, Juho Kim
    Under Review
    Paper

Conferences and Journal Papers

  1. TMLR
    Hypothesize and Verify: Natural-Language Explanations of Vision Model Errors
    Hypothesize and Verify: Natural-Language Explanations of Vision Model Errors
    Hyeon-Woo Nam, Yoonsu Kim, Kihoon Son, Juho Kim, Tae-Hyun Oh
    Accepted to TMLR
  2. UIST
    Contexty: Capturing and Organizing In-situ Thoughts for Context-Aware AI Support
    Contexty: Capturing and Organizing In-situ Thoughts for Context-Aware AI Support
    Yoonsu Kim, Chanbin Park, Kihoon Son, Saelyne Yang, Juho Kim
    Accepted to UIST 2026
    Paper Project Page Video
  3. DIS
    IntentFlow: Investigating Fluid Dynamics of Intent Communication in Generative AI
    IntentFlow: Investigating Fluid Dynamics of Intent Communication in Generative AI
    Yoonsu Kim, Kihoon Son, Seoyoung Kim, Brandon Chin, Juho Kim
    DIS 2026
    Paper ACM DL Project Page Video
  4. IUI
    Understanding Users’ Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Level
    Understanding Users’ Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Level
    Yoonsu Kim, Jueon Lee, Seoyoung Kim, Jaehyuk Park, Juho Kim
    IUI 2024
    Paper ACM DL Project Page
  5. IMWUT
    AI-to-Human Actuation: AI Proactively Induces Humans towards Favorable Sensing Conditions
    AI-to-Human Actuation: AI Proactively Induces Humans towards Favorable Sensing Conditions
    Sungjae Cho, Yoonsu Kim, Jaewoong Jang, Inseok Hwang
    IMWUT 2023
    Paper ACM DL Video

Posters, Demos, Workshop Papers

  1. ICML
    NEMO: Benchmarking Natural-Language Explanations of Vision Model Errors
    NEMO: Benchmarking Natural-Language Explanations of Vision Model Errors
    Hyeon-Woo Nam, Yoonsu Kim, Kihoon Son, Juho Kim, Tae-Hyun Oh
    ICML 2026 Workshop on AI4GOOD
    Paper
  2. AIED
    STEPwise: Diagnosing Students’ Math Problem-Solving Skills via LLM-Generated Stepwise Sub-Questions
    STEPwise: Diagnosing Students’ Math Problem-Solving Skills via LLM-Generated Stepwise Sub-Questions
    Yoonsu Kim, Hayeon Doh, Eunhye Kim, Jinho Son, Juho Kim
    AIED 2026 Interactive Events Track
    Paper Video
  3. CHI
    Applying the Gricean Maxims to a Human-LLM Interaction Cycle: Design Insights from a Participatory Approach
    Applying the Gricean Maxims to a Human-LLM Interaction Cycle: Design Insights from a Participatory Approach
    Yoonsu Kim, Brandon Chin, Kihoon Son, Seoyoung Kim, Juho Kim
    CHI 25 LBW
    Paper ACM DL
  4. EMNLP
    LLM-as-a-tutor in EFL Writing Education: Focusing on Evaluation of Student-LLM Interaction
    LLM-as-a-tutor in EFL Writing Education: Focusing on Evaluation of Student-LLM Interaction
    Jieun Han, Haneul Yoo, Junho Myung, Minsun Kim, Hyunseung Lim, Yoonsu Kim, Tak Yeon Lee, Hwajung Hong, Juho Kim, So-Yeon Ahn, Alice Oh
    EMNLP 2024 Workshop on CustomNLP4U
    Paper
  5. EMNLP
    LLM-Driven Learning Analytics Dashboard for Teachers in EFL Writing Education
    LLM-Driven Learning Analytics Dashboard for Teachers in EFL Writing Education
    Jieun Han, Haneul Yoo, Junho Myung, Minsun Kim, Hyunseung Lim, Yoonsu Kim, Tak Yeon Lee, Hwajung Hong, Juho Kim, So-Yeon Ahn, Alice Oh
    EMNLP 2024 Workshop on CustomNLP4U
    Paper
  6. L@S
    Using Large Language Models to Diagnose Math Problem-Solving Skills at Scale
    Using Large Language Models to Diagnose Math Problem-Solving Skills at Scale
    Hyoungwook Jin*, Yoonsu Kim*, Yeon Su Park, Bekzat Tilekbay, Jinho Son, Juho Kim (* Corresponding authors)
    L@S 2024 WiP
    Paper ACM DL
  7. CHI
    Beyond Prompts: Learning from Human Communication for Enhanced AI Intent Alignment
    Beyond Prompts: Learning from Human Communication for Enhanced AI Intent Alignment
    Yoonsu Kim, Kihoon Son, Seoyoung Kim, Juho Kim
    CHI 2024 Workshop on Getting Back Together: HCI and Human Factors Joining Forces to Meet the AI Interaction Challenge
    Paper
  8. L@S
    RECIPE: How to Integrate ChatGPT into EFL Writing Education
    RECIPE: How to Integrate ChatGPT into EFL Writing Education
    Jieun Han, Haneul Yoo, Yoonsu Kim, Junho Myung, Minsun Kim, Hyunseung Lim, Juho Kim, Tak Yeon Lee, Hwajung Hong, So-Yeon Ahn, Alice Oh
    L@S 2023 WiP
    Paper ACM DL
  9. KCC
    Towards Understanding the Challenges and Remedies in AI Application Development
    Towards Understanding the Challenges and Remedies in AI Application Development
    Dae Hyun Kim*, Yoonsu Kim*, Hyungyu Shin, Jinho Son, Juho Kim (* Corresponding authors)
    KCC 2023
    Paper
  10. UbiComp/ISWC
    Demonstrating AHA: Boosting Unmodified AI's Robustness by Proactively Inducing Favorable Human Sensing Conditions
    Demonstrating AHA: Boosting Unmodified AI's Robustness by Proactively Inducing Favorable Human Sensing Conditions
    Sungjae Cho, Jaewoong Jang, Yoonsu Kim, Inseok Hwang
    UbiComp/ISWC '23 Adjunct
    Paper ACM DL

© 2025 Yoonsu Kim. Powered by Jekyll and Minimal Light theme.