TutorCaseBench: A Case-Grounded Benchmark for Evaluating LLM Tutors in Supporting Students with Challenging Behaviors
Yeon Su Park, Chanyoung Park, Tae Soo Kim, Seungju Kim, Hyunwoo Kim, Daho Jung, Jinsung Yoon, Juho Kim
Lab Publications: For complete lab publications, project demos, and ongoing research, visit KIXLAB Publications.
Yeon Su Park, Chanyoung Park, Tae Soo Kim, Seungju Kim, Hyunwoo Kim, Daho Jung, Jinsung Yoon, Juho Kim
Jaesang Yu, Seoyeon Byun, Yun Wang, Yan Lu, Juho Kim
Yoonsu Kim, Hayeon Doh, Eunhye Kim, Jinho Son, Juho Kim
Yoonsu Kim, Sean Kim, Kihoon Son, Saelyne Yang, Juho Kim
Heechan Lee, Juhyeon Choi, Tae Soo Kim, Juho Kim, Joseph Seering
Yeon Su Park, Nadia Arvi, Hae Ri Lee, Sehoon Lim, Qianou Ma, Juho Kim
Eunhye Kim, Bryan Min, Haijun Xia, Juho Kim
Minsun Kim, Seon Gyeom Kim, Suyoun Lee, Yoosang Yoon, Junho Myung, Haneul Yoo, Jieun Han, Hyunseung Lim, Yoonsu Kim, So-Yeon Ahn, Juho Kim, Alice Oh, Hwajung Hong, Tak Yeon Lee
Anjali Singh, Christopher Brooks, Warren Li, Juho Kim, Xu Wang
Kihoon Son, Hyewon Lee, DaEun Choi, Yoonsu Kim, Tae Soo Kim, Yoonjoo Lee, John Joon Young Chung, HyunJoon Jung, Juho Kim
Brandon Lepine, Juho Kim, Pamela Mishkin, Matthew Beane
💡 In a GPT-4o valuation study with finance professionals, transcript-based measures show extraneous cognitive load hurts quality far more than intrinsic load, with model-initiated task switching the strongest predictor of decline.
Tae Soo Kim, Yoonjoo Lee, Jaesang Yu, John Joon Young Chung, Juho Kim
💡 This paper introduces DiscoverLLM to broaden LLM use from executing clearly specified intents toward helping users discover, articulate, and refine their own goals through interaction.
Daeheon Jeong, Yoonjoo Lee, Eugene Choi, Sinie van der Ben, Juho Kim
💡 This paper shows that assistant bias in language model simulators can be identified and analyzed through model activations, helping improve the realism of simulations used to evaluate AI agents.
Hyeon-Woo Nam, Yoonsu Kim, Kihoon Son, Juho Kim, Tae-Hyun Oh
💡 This paper demonstrates that a new method, SciTX, improves the accuracy of explaining vision model errors, helping users better diagnose and address AI system failures.
Eunhye Kim, DaEun Choi, Bryan Min, Hyunjung Yi, Yue Jiang, Juho Kim
💡 This paper shows that using Information Architecture as a shared language helps maintain alignment between generative user interfaces and users' personal information structures, leading to more consistent user experiences over time.
Yoonsu Kim, Chanbin Park, Kihoon Son, Saelyne Yang, Juho Kim
💡 This paper demonstrates that capturing and organizing users' cognitive context during tasks enhances AI collaboration, improving task awareness and user control, which is crucial for effective human-AI interaction.
Heechan Lee, Jeonggyu Kang, Junho Myung, Jaywoong Jeong, Juho Kim, Joseph Seering
💡 This paper reveals that TIDES, a new bilingual dataset of real-world team interactions, enhances language models' understanding of multi-party dynamics, which is crucial for improving collaborative AI applications.
Yoonsu Kim, Kihoon Son, Seoyoung Kim, Brandon Chin, Juho Kim
💡 This paper maps four facets of intent communication in generative AI and shows that combining them in one writing probe helps people refine vague goals with less effort and stronger sense of control over outputs.
DaEun Choi, Kihoon Son, Jaesang Yu, Hyunjoon Jung, Juho Kim
💡 This paper introduces reusable "exploration blocks" so designers can express open-ended generative search spaces and revisit strategies, yielding broader and more diverse image exploration than standard prompting.
Saelyne Yang, Jaesang Yu, Yi-Hao Peng, Kevin Qinghong Lin, Jae Won Cho, Yale Song, Juho Kim
Also at: CVPR 2026 Workshop on Multi-Modal Reasoning for Agentic Intelligence (MMRAgI), Oral · 🏆 Outstanding Paper Award
💡 This paper releases a benchmark of real novice screen work plus think-alouds so models can be scored on noticing behavior, inferring goals, and knowing when to help in open-ended desktop tasks.
Hyehyun Chu, Seungju Kim, Chen Zhou, Yu-Kai Hung, Saelyne Yang, Hyun W. Ka, Juho Kim
💡 This paper documents how learners with borderline intellectual functioning struggle with pacing, density, and missing steps in how-to videos, and outlines content and UI changes to make video learning more cognitively accessible.
Yeon Su Park, Nadia Arvi, Seoyoung Kim, Juho Kim
💡 This large-scale study tracks how writers' confidence and trust shift turn by turn with an LLM, linking drops in self-efficacy to heavier AI editing and stable confidence to stronger felt ownership of the final text.
Kihoon Son, DaEun Choi, Tae Soo Kim, Young-Ho Kim, Sangdoo Yun, Juho Kim
💡 This paper shows that structuring UI designers' decisions into steps and having an AI probe weak spots can infer acceptable rationales most of the time and greatly strengthen explainability of creative work.
Jiangnan Xu, Haeseul Cha, Gosu Choi, Gyu-cheol Lee, Yeo-Jin Yoon, Zucheul Lee, Konstantinos Papangelis, Dae Hyun Kim, Juho Kim
💡 This system turns everyday written stories into playable interactive vignettes by extracting characters and scenes and auto-planning branches so casual authors avoid hand-building complex narrative graphs.
Tae Soo Kim, Heechan Lee, Yoonjoo Lee, Joseph Seering, Juho Kim
💡 This paper replaces single-number LLM judgments with fragment-level "functional" breakdowns so teams can see which parts of an output drive scores and catch almost half more evaluation mistakes.
Junho Myung, Hyunseung Lim, Hana Oh, Hyoungwook Jin, Nayeon Kang, So-Yeon Ahn, Hwajung Hong, Alice Oh, Juho Kim
💡 A six-week middle-school deployment finds LLM writing help improves grammar but can demotivate weaker students, increase dependence on the tool, and hide who needs the teacher's attention in busy classrooms.
Jeongeon Park, Bryan Min, Kihoon Son, Jean Y. Song, Xiaojuan Ma, Juho Kim
💡 This paper shows that letting users directly orchestrate multiple AI agents—each representing different domain perspectives—helps people make more confident decisions in unfamiliar areas like choosing PhD programs or buying cameras.
Gionnieve Lim, Juho Kim, Simon Perrault
💡 This paper shows that a browser extension using fallacy detection and Socratic questioning can encourage readers to think more critically about online content, though some users resist tools that challenge their existing thinking habits.
Daeheon Jeong, Seoyeon Byun, Kihoon Son, Dae Hyun Kim, Juho Kim
💡 This paper introduces a benchmark for testing whether AI vision-language models can effectively use design software tools to create and edit user interfaces, revealing that current models show promising but inconsistent abilities in this collaborative design task.
Junyeong Park, Jieun Han, Yeon Su Park, Youngbin Lee, Suin Kim, Juho Kim, Alice Oh, So-Yeon Ahn
Yoonsu Kim, Hyoungwook Jin, Hayeon Doh, Eunhye Kim, Dong Yun Jung, Seungju Kim, Kiyoon Choi, Jinho Son, Juho Kim
💡 This benchmark shows today's LLMs still fail at teacher-style diagnosis of math thinking from messy handwritten work, especially when evidence is vague, and catalogs failure modes like overclaiming and hallucinated steps.
Hyungyu Shin, Jingyu Tang, Yoonjoo Lee, Nayoung Kim, Hyunseung Lim, Ji Yong Cho, Hwajung Hong, Moontae Lee, Juho Kim
💡 This paper reveals that AI systems generating peer reviews consistently overlook novelty assessment while overemphasizing technical validity, highlighting critical blind spots before these tools are trusted for scientific gatekeeping.
Hyunseung Lim, Sooyohn Nam, Sungmin Na, Ji Yong Cho, June Yong Yang, Hyungyu Shin, Yoonjoo Lee, Juho Kim, Moontae Lee, Hwajung Hong
💡 This paper reveals that while large language models can find relevant prior patents, they struggle to judge whether new patent claims are truly novel—a gap that matters for automating the costly patent examination process.
Jihyeong Hong, Eunyoung Ko, Juho Kim, Jeong-woo Jang
💡 This paper reveals that social media users rely on "Not Interested" buttons to filter out unwanted content but remain confused about whether their feedback actually shapes what they see, highlighting a need for clearer algorithm transparency.
Eun Jeong Kang, Haesoo Kim, Hyunwoo Kim, Susan Fussell, Juho Kim
💡 This paper shows that fans use AI-generated voice messages from K-Pop idols as a substitute for direct interaction, actively working to perceive these synthetic messages as authentic to strengthen their emotional connection with celebrities.
Tae Soo Kim, Yoonjoo Lee, Yoonah Park, Jiho Kim, Young-Ho Kim, Juho Kim
💡 This paper shows that even advanced AI chatbots struggle to remember and correctly apply user preferences across different conversation contexts, helping developers understand why personalized AI assistants often feel frustratingly inconsistent.
Yoonseo Choi, Eunhye Kim, Hyunwoo Kim, Donghyun Park, Honggu Lee, Jin Young Kim, Juho Kim
💡 This paper shows that evaluating search engines by generating diverse plausible user intents—rather than treating identical queries as having one goal—helps developers identify which user needs current systems fail to serve.
Juhoon Lee, Seoyoung Kim, Yeon Su Park, Juho Kim, Jeong-woo Jang, Joseph Seering
💡 This paper shows that players in online team games often view any teammate communication as a warning sign of conflict rather than collaboration, helping game designers understand why communication tools frequently backfire despite good intentions.
Yoonseo Choi, Eun Jeong Kang, Seulgi Choi, Min Kyung Lee, Juho Kim
💡 This paper shows that transforming audience comments into interactive AI personas helps content creators discover overlooked viewer segments and get actionable feedback on early drafts before publishing.
Hyoungwook Jin, Minju Yoo, Jeongeon Park, Yokyung Lee, Xu Wang, Juho Kim
💡 This paper shows that simulating diverse student personas to automatically test AI tutoring chatbots helps teachers more efficiently evaluate whether their tools adapt appropriately to students with different knowledge levels and motivations.
Dae Hyun Kim, Daeheon Jeong, Shahnoza Yadgarova, Hyungyu Shin, Jinho Son, Hari Subramonyam, Juho Kim
💡 This paper shows that structuring AI project planning around information dependencies helps non-technical clients articulate clearer, more actionable requirements before consulting AI experts, reducing miscommunication in collaborative development.
Saelyne Yang, Anh Truong, Juho Kim, Dingzeyu Li
💡 This paper shows that aggregating information from multiple how-to videos into organized summaries helps learners understand practical tasks more efficiently than watching videos separately.
Benjamin Newman, Yoonjoo Lee, Aakanksha Naik, Pao Siangliulue, Raymond Fok, Juho Kim, Daniel S. Weld, Joseph Chee Chang, Kyle Lo
💡 This paper shows that language models can automatically generate literature review tables comparing research papers, helping scientists synthesize large bodies of work more efficiently during systematic reviews.
Haechan Kim, Junho Myung, Seoyoung Kim, Sungpah Lee, Dongyeop Kang, Juho Kim
💡 This paper shows that speech recognition systems struggle with non-native learners' grammatical errors and hesitations, and provides a new dataset that cuts these recognition errors nearly in half.
Jihyeong Hong, Yokyung Lee, Dae Hyun Kim, DaEun Choi, Yeo-Jin Yoon, Gyu-cheol Lee, Zucheul Lee, Juho Kim
💡 This paper shows that answering newcomers' questions in virtual worlds requires tracking both their immediate surroundings and exploration history, helping designers create onboarding assistants that improve learning and immersion.
Dae Hyun Kim, Hyungyu Shin, Shakhnozakhon Yadgarova, Jinho Son, Hariharan Subramonyam, Juho Kim
💡 This paper provides a structured workbook that helps AI developers and their clients communicate requirements more clearly, reducing costly misunderstandings and project failures in custom AI application development.
Hyunseung Lim, Ji Yong Cho, Taewan Kim, Jeongeon Park, Hyungyu Shin, Seulgi Choi, Sunghyun Park, Kyungjae Lee, Juho Kim, Moontae Lee, Hwajung Hong
💡 This paper shows that while AI writing assistants help researchers create accessible Q&A articles about their work, they struggle to capture authors' unique intentions and may discourage careful revision, revealing key tensions in human-AI collaborative writing.
Yoonjoo Lee, Kihoon Son, Tae Soo Kim, Jisu Kim, John Joonyoung Chung, Eytan Adar, Juho Kim
💡 This paper shows that showing users multiple inconsistent AI-generated answers actually improves their comprehension of information, suggesting that revealing AI disagreements could help people use these tools more critically.
Jingchao Fang, Jeongeon Park, Juho Kim, Hao-Chuan Wang
💡 This paper shows that letting online learners annotate real-time lecture transcripts creates useful feedback signals for instructors, helping bridge the interaction gap caused by missing visual cues in educational live streams.
Seoyoung Kim, Yeon Su Park, Dakyeom Ahn, Jin Myung Kwak, Juho Kim
💡 This paper shows that listeners judge identical speech recognition errors differently based on speaker accent—blaming non-native speakers more for mistakes—revealing that equal AI performance doesn't guarantee equal perceived fairness.
Hyoungwook Jin, Juho Kim
💡 This paper shows that novice programmers can collectively create high-quality hierarchical explanations of code examples, reducing dependence on experts while improving their own learning outcomes.
Haesoo Kim, Juhoon Lee, Jeong-woo Jang, Juho Kim
💡 This paper shows that giving harassment targets tools to manage large-scale attacks and view summarized responses helps them feel safer and more in control, offering a path toward healthier online discourse.
Nayeon Lee, Chani Jung, Junho Myung, Jiho Jin, Jose Camacho-Collados, Juho Kim, Alice Oh
💡 This paper reveals that hate speech labels vary significantly across English-speaking countries—with only 56% agreement—showing that cultural context shapes what people consider hateful online.
Seulgi Choi, Hyewon Lee, Yoonjoo Lee, Juho Kim
💡 This paper shows that instructors can use AI tools to efficiently convert monologue-style online lectures into interactive dialogues, helping educators create more engaging learning experiences without the usual time-intensive effort.
Yoonjoo Lee, Hyeonsu B Kang, Matt Latzke, Juho Kim, Jonathan Bragg, Joseph Chee Chang, Pao Siangliulue
💡 This paper shows that enriching paper alerts with AI-generated explanations of how recommended papers connect to a researcher's existing work helps them evaluate relevance faster and more confidently.
DaEun Choi, Sumin Hong, Jeongeon Park, John Joon Young Chung, Juho Kim
💡 This paper shows that AI-generated keyword suggestions and sketch recombinations help graphic designers discover more creative ideas from reference images, offering a practical way to support early-stage design brainstorming.
Kihoon Son, DaEun Choi, Tae Soo Kim, Young-Ho Kim, Juho Kim
💡 This paper shows that integrating generative AI into visual search helps designers express vague or abstract ideas more precisely, leading to more satisfying and diverse creative exploration outcomes.
Kihoon Son, DaEun Choi, Tae Soo Kim, Juho Kim
💡 This paper identifies 123 examples of hard-to-articulate expert knowledge in graphic design, revealing which types remain unsupported by current tools and offering guidelines for making this hidden expertise more shareable.
Hyoungwook Jin, Seonghee Lee, Hyungyu Shin, Juho Kim
💡 This paper shows that large language models can be prompted to act as "teachable" student chatbots that strategically ask questions and simulate confusion, helping programming learners deepen their understanding by explaining concepts to an AI tutee.
Tae Soo Kim, Yoonjoo Lee, Jamin Shin, Young-Ho Kim, Juho Kim
💡 This paper shows that letting developers define custom evaluation criteria in natural language helps them refine AI prompts faster by revealing systematic weaknesses across many outputs at once.
Hyung-Kwon Ko, Hyeon Jeon, Gwanmo Park, Dae Hyun Kim, Nam Wook Kim, Juho Kim, Jinwook Seo
💡 This paper shows that large language models can automatically generate diverse natural language descriptions from chart specifications, helping researchers build better conversational interfaces for data visualization without manually creating training datasets.
Seonghyeon Ye, Doyoung Kim, Sungdong Kim, Hyeonbin Hwang, Seungone Kim, Yongrae Jo, James Thorne, Juho Kim, Minjoon Seo
💡 This paper shows that evaluating language models on specific skills (like reasoning or factual accuracy) rather than overall preference scores reveals clearer performance differences and produces more reliable assessments of model capabilities.
Yoonsu Kim, Jueon Lee, Seoyoung Kim, Jaehyuk Park, Juho Kim
💡 This paper reveals that most user frustrations with ChatGPT stem from the model misunderstanding intent rather than factual errors, and that 72% of these frustrations remain unresolved even when users try to fix them—suggesting chatbot interfaces need better tools for helping users recover from failures.
Bekzat Tilekbay, Saelyne Yang, Michal A. Lewkowicz, Alex Suryapranata, Juho Kim
💡 This paper shows that combining natural language and sketching lets novice video editors express and implement their ideas more easily, helping democratize video production by reducing the technical barriers to creating engaging informational content.
Hyunwoo Kim, Khanh Duy Le, Gionnieve Lim, Dae Hyun Kim, Yoo Jin Hong, Juho Kim
💡 This paper shows that guiding readers with LLM-generated questions and visualizations helps them better contextualize statistical claims in news articles, leading to deeper understanding of data-driven narratives.
Jeongeon Park, Eun-Young Ko, Yeon Su Park, Jinyeong Yim, Juho Kim
💡 This paper shows that crowdsourcing feedback on label definitions helps machine learning practitioners identify ambiguities and edge cases earlier, reducing costly iterations when building training datasets.
Anjali Singh, Christopher Brooks, Xu Wang, Warren Li, Juho Kim, Deepti Wilson
💡 This paper shows that students revising AI-generated hints produce better feedback than writing from scratch, offering educators a practical way to improve peer learning while teaching critical evaluation of AI outputs.
Tae Soo Kim, Yoonjoo Lee, Minsuk Chang, Juho Kim
💡 This paper introduces a design framework for writing interfaces that lets users easily create, combine, and compare different AI text generation settings, helping writers iterate more efficiently toward their goals.
Dae Hyun Kim, Seulgi Choi, Juho Kim, Vidya Setlur, Maneesh Agrawala
💡 This paper shows that charts and their captions often emphasize different information, causing readers to miss intended messages, and offers a tool to help authors align visual and textual emphasis.
Yoonseo Choi, Eun Jeong Kang, Min Kyung Lee, Juho Kim
💡 This paper shows that YouTube creators develop workarounds and folk theories to navigate opaque recommendation algorithms, revealing design opportunities for platforms to better support creative work instead of distracting from it.
Saelyne Yang, Sangkyung Kwak, Juhoon Lee, Juho Kim
💡 This paper identifies 21 distinct types of information in how-to videos beyond step-by-step instructions, enabling better video navigation tools that help viewers quickly find specific knowledge like explanations or tips.
Seoyoung Kim, Donghoon Shin, Jeongyeon Kim, Soonwoo Kwon, Juho Kim
💡 This paper shows that older adults prefer practical over technical video content and interact less with video controls, helping designers create more accessible online learning platforms for aging populations.
Yoonjoo Lee, Tae Soo Kim, Sungdong Kim, Yohan Yun, Juho Kim
💡 This paper shows that breaking down complex explanations into interactive, step-by-step dialogues helps children better understand and enjoy answers to their "why" and "how" questions from voice assistants.
Jeongyeon Kim, DaEun Choi, Nicole Lee, Matt Beane, Juho Kim
💡 This paper shows that organizing surgical videos by their underlying step-by-step structure helps medical residents find and compare relevant techniques more efficiently than browsing videos manually.
Jean Y Song, Sangwook Lee, Jisoo Lee, Mina Kim, Juho Kim
💡 This paper shows that giving online moderators a "sandbox" to preview and debug automated content rules before deployment helps them catch errors faster and reduce both over-blocking and under-blocking of posts.
Hyung-Kwon Ko, Gwanmo Park, Hyeon Jeon, Jaemin Jo, Juho Kim, Jinwook Seo
💡 This paper reveals that visual artists across 35 domains use text-to-image AI tools primarily for automation, idea exploration, and communication—offering design guidelines for building more artist-friendly creative interfaces.
Haesoo Kim, Haeeun Kim, Juho Kim, Jeong-woo Jang
💡 This paper examines how online criticism escalates into harassment on Twitter, helping platform designers and users better understand where legitimate calling out crosses into harmful behavior.
Meng Xia, Yankun Zhao, Jihyeong Hong, Mehmet Hamza Erol, Taewook Kim, Juho Kim
💡 This paper shows that visualizing and grouping feedback from multiple online language tutors helps learners track their progress more effectively, addressing the challenge of inconsistent guidance in gig-economy tutoring platforms.
Eun-Young Ko, Yeonsu Kim, Juho Kim
💡 This paper shows that guiding readers through structured evaluation criteria with examples helps non-experts more accurately assess the quality and reliability of health news stories.
Eun-Young Ko, Eunseo Choi, Jeong-woo Jang, Juho Kim
💡 This paper shows that letting users create their own reaction labels instead of simple up/downvotes helps people express more nuanced opinions and better understand why others agree or disagree with comments.
Saelyne Yang, Jisu Yim, Aitolkyn Baigutanova, Seoyoung Kim, Minsuk Chang, Juho Kim
💡 Learning software from tutorial videos often means frustrating back-and-forth switching and missed steps—this system uses past learners' interaction patterns to flag difficult moments and help users catch errors before falling behind.
Meng Xia, Yankun Zhao, Mehmet Hamza Erol, Jihyeong Hong, Juho Kim
💡 This paper shows that language learners on gig-economy tutoring platforms frequently switch between different tutors, and this inconsistency correlates with slower improvement in speaking skills, suggesting platform designs should better support tutor-learner continuity.
Saelyne Yang, Jisu Yim, Juho Kim, Hijung Valentina Shin
💡 This paper shows that combining live stream content with viewer interaction data enables real-time summaries that help latecomers quickly catch up on what they missed without losing track of ongoing content.
Yoonjoo Lee, John Joon Young Chung, Tae Soo Kim, Jean Y. Song, Juho Kim
💡 This paper shows that combining human expertise with AI-powered knowledge graphs can generate diverse learning prompts at 40 times the scale of manual authoring, helping online educators better support learners with different backgrounds and knowledge levels.
Tae Soo Kim, DaEun Choi, Yoonseo Choi, Juho Kim
💡 This paper shows that translating natural language into CSS suggestions lets everyday users customize website styles 35% faster than traditional developer tools, making web personalization accessible without coding expertise.
Jeongyeon Kim, Yubin Choi, Minsuk Kahng, Juho Kim
💡 This paper shows that automatically extracting and rearranging visual elements from desktop lecture videos makes them significantly more readable on mobile phones, helping online learners better concentrate and engage with educational content on smaller screens.
Jeongyeon Kim, Yubin Choi, Meng Xia, Juho Kim
💡 This paper reveals that most online course videos fail basic mobile readability standards because creators overlook how learners actually watch on phones—in bright sunlight, while commuting—suggesting adaptive visual designs could significantly improve learning accessibility.
Kabdo Choi, Hyungyu Shin, Meng Xia, Juho Kim
💡 This paper shows that learners can generate high-quality solution structure labels through guided microtasks, helping programming novices develop more complete problem-solving plans without requiring scarce expert-created materials.
Mina Huh, YunJung Lee, Dasom Choi, Haesoo Kim, Uran Oh, Juho Kim
💡 This paper shows that reader comments on digital comics can guide accessible descriptions for visually impaired users, helping them control reading pace and engage socially like sighted readers.
Mohi Reza, Juho Kim, Ananya Bhattacharjee, Anna N. Rafferty, Joseph Jay Williams
💡 This paper shows that modular software components can turn online course elements into mini-laboratories for continuous testing and personalization, helping educators rapidly improve student experiences through real-time experimentation rather than waiting months for results.
Hyunwoo Kim, Haesoo Kim, Kyung Je Jo, Juho Kim
💡 This paper shows that organizing online opinions by demographic identity and semantic viewpoint helps users encounter perspectives outside their usual echo chambers, making public discourse on divisive social issues more representative and less polarized.
Tae Soo Kim, Nitesh Goyal, Jeongyeon Kim, Juho Kim, Sungsoo Ray Hong
💡 This paper shows that visual awareness tools can help small groups more efficiently build consensus when collaboratively creating sequences—like planning trips or scheduling courses—by making everyone's preferences and conflicts easier to recognize.
Minsuk Chang, Mina Huh, Juho Kim
💡 This paper shows that voice commands referencing video *content* (like "go back to the chopping step") let people follow hands-busy tutorials more efficiently than time-based controls, helping designers build smarter voice interfaces for instructional media.
Yoonjoo Lee, John Joon Young Chung, Jean Y. Song, Minsuk Chang, Juho Kim
💡 This paper shows that viewers use "study with me" videos to cheaply customize their environment, simulate peer pressure, and gain emotional support, helping educators and designers understand how people self-regulate learning when studying alone.
Tae Soo Kim, Seungsu Kim, Yoonseo Choi, Juho Kim
💡 This paper shows that linking voice recordings to clicked objects in design tools makes remote asynchronous collaboration feel as effortless as face-to-face conversation, helping distributed teams communicate design intentions more precisely than text alone.
Sungsoo Ray Hong, Rafal Kocilenik, Cecilia Aragon, Sarah Battersby, Juho Kim
💡 This paper shows that how interfaces display and collect user preferences significantly affects people's experience when making decisions involving multiple competing criteria, helping designers create tools that better support everyday comparison tasks like choosing products or services.
Saelyne Yang, Juho Kim
💡 This paper identifies four key factors—user skill, software complexity, tutorial quality, and user-tutorial interaction—that determine whether people can successfully follow software tutorial videos, guiding creators toward more effective instructional content.
Yoonseo Choi, Toni-Jan Monserrat, Jeongeon Park, Hyungyu Shin, Nyoungwoo Lee, Juho Kim
💡 This paper shows that integrating crowd feedback directly into chatbot design tools helps conversation designers quickly identify usability problems and iterate on their designs without the delays of traditional user recruitment.
Joon-Gyum Kim, Taesik Gong, Kyungsik Han, Juho Kim, JeongGil Ko, Sung-Ju Lee
💡 This paper introduces a system that automatically suggests relevant images during mobile chat conversations, helping users communicate more expressively without the friction of manually searching for visual content.
Minsuk Chang, Ben Lafreniere, Juho Kim, George Fitzmaurice, Tovi Grossman
💡 This paper shows that mapping how different users complete the same 3D design task reveals alternative strategies and decision points, helping software educators provide personalized feedback and guidance to learners.
Changhoon Oh, Seonghyeon Kim, Jinhan Choi, Jinsu Eun, Soomin Kim, Juho Kim, Joonhwan Lee, Bongwon Suh
💡 This paper shows that people interpret AI aesthetic judgments through the lens of their own expertise, helping designers understand how to build AI systems for subjective domains that diverse users can actually make sense of.
Hyunsung Cho, Jinyoung Oh, Juho Kim, Sung-Ju Lee
💡 This paper shows that letting messaging app users share context-specific availability and control whether messages trigger notifications reduces pressure to respond immediately while cutting unwanted interruptions.
Sung-Chul Lee, Jaeyoon Song, Seongho Park, Eun-Young Ko, Jihee Kim, Juho Kim
💡 This paper shows that AI-assisted tools can help online chat moderators track discussions, summarize opinions, and guide groups toward consensus with less effort, making community problem-solving more accessible to untrained facilitators.
Seoyoung Kim, Arti Thakur, Juho Kim
💡 This paper shows that automated personality detection in workplaces creates privacy concerns and changes how people naturally behave, helping system designers balance accuracy with user comfort and trust.
Saelyne Yang, Changyoon Lee, Hijung Valentina Shin, Juho Kim
💡 This paper shows that letting viewers capture and annotate screenshots during art livestreams leads to clearer communication and higher engagement, helping platform designers create more expressive real-time interaction tools.
Joon-Gyum Kim, Taesik Gong, Bogoan Kim, JaeYeon Park, Woojeong Kim, Evey Huang, Kyungsik Han, Juho Kim, JeongGil Ko, Sung-Ju Lee
💡 This paper shows that recommending emojis based on entire conversation context rather than just the current sentence helps users find desired emojis 38% faster and enables suggestions for emoji-only messages.
Henriette Cramer, Juho Kim
💡 This paper launches a forum for exploring the practical and ethical challenges designers face when creating user experiences powered by AI, bridging gaps between research insights and real-world implementation.
Sungsoo (Ray) Hong, Minhyang (Mia) Suh, Tae Soo Kim, Irina Smoke, Sang-Wha Sien, Janet Ng, Mark Zachry, Juho Kim
💡 This paper reveals that common search and filter tools fail group decision-making because they're designed for individuals, causing communication breakdowns and unequal workloads when people try to plan activities together.
John Joon Young Chung, Jean Y. Song, Sindhu Kutty, Sungsoo (Ray) Hong, Juho Kim, Walter S. Lasecki
💡 This paper shows that collecting diverse crowd opinions efficiently is possible by varying how annotators express their answers, helping researchers build machine learning datasets that better capture ambiguity without requiring massive annotation budgets.
Minsuk Chang, Ahn Truong, Oliver Wang, Maneesh Agrawala, Juho Kim
💡 This paper identifies seven distinct ways people want to navigate how-to videos by voice while their hands are busy, offering designers a framework to build more intuitive voice-controlled video interfaces.
Jean Y. Song, Stephan J. Lemmer, Michael Xieyang Liu, Shiyan Yan, Juho Kim, Jason J. Corso, Walter S. Lasecki
💡 This paper shows that combining crowdsourced annotations across video frames using particle filtering produces more accurate 3D reconstructions of traffic incidents, helping autonomous vehicle developers create training data from ordinary dashboard and surveillance footage.
Jean Y. Song, Raymond Fok, Juho Kim, Walter S. Lasecki
💡 This paper shows that using multiple different annotation tools reduces shared errors in crowdsourced image labeling, helping machine learning practitioners collect more accurate training data by offsetting the systematic biases each tool introduces.
Paul Grau, Babak Naderi, Juho Kim
💡 This paper shows that personalized messages supporting people's sense of autonomy, competence, and connection can help civic platforms better sustain volunteer participation in community problem-solving efforts.
Dae Hyun Kim, Enamul Hoque, Juho Kim, Maneesh Agrawala
💡 This paper shows that automatically highlighting connections between sentences and table cells helps readers navigate complex documents faster and more accurately, even when the linking isn't perfect.
Minsuk Chang, Leonore Guillain, Hyeungshik Jung, Vivian Hare, Juho Kim, Maneesh Agrawala
💡 This paper shows that cooking instructions can be computationally analyzed and clustered by procedural similarity, helping culinary professionals quickly identify distinct approaches and ingredient patterns across hundreds of recipes.
Hyungyu Shin, Eun-Young Ko, Joseph Jay Williams, Juho Kim
💡 This paper shows that pausing online lecture videos with reflective questions helps some learners check their understanding and gives instructors more specific feedback, though the timing and style of prompts significantly affects whether students find them helpful or distracting.
Ching Liu, Juho Kim, Hao-Chuan Wang
💡 This paper shows that crowdsourced concept maps help online learners navigate lecture videos by topic and understand how ideas connect, addressing the difficulty of finding and engaging with specific content in lengthy educational videos.
Joseph Jay Williams, Anna Rafferty, Dustin Tingley, Andrew Ang, Walter S. Lasecki, Juho Kim
💡 This paper shows that giving instructors easy-to-use tools for running randomized experiments on digital homework problems helps them systematically discover which hints and feedback actually work best for their students.
Sungsoo (Ray) Hong, Minhyang (Mia) Suh, Nathalie Henry Riche, Jooyoung Lee, Juho Kim, Mark Zachry
💡 This paper shows that displaying group members' preferences alongside filtering tools helps distributed teams reach consensus faster and communicate more effectively when making shared decisions remotely.
Sungsoo (Ray) Hong, Minjoon Yoo, Bonnie Chinh, Amy Han, Sarah Battersby, Juho Kim
💡 This paper shows that maps distorted to display travel time instead of geographic distance are perceived as intuitive and useful by real-world users, suggesting people can adapt to unconventional spatial representations when they solve practical problems.
Seokwoo Song, Juho Kim, Bumsoo Kang, Wonjeong Park, John Kim
💡 This paper shows that parents disagree on about 22% of child development screening questions, and a collaborative mobile app helping them share observations and resolve discrepancies increases awareness and accuracy of early developmental tracking.
Jean Y. Song, Raymond Fok, Alan Lundgard, Fan Yang, Juho Kim, Walter S. Lasecki
💡 This paper shows that giving different crowdworkers different annotation tools reduces shared mistakes that persist after combining responses, helping researchers collect more accurate image segmentation data for training computer vision systems.
Soon Hau Chua, Toni-Jan Keith Monserrat, Dongwook Yoon, Juho Kim, Shengdong Zhao
💡 This paper shows that a redesigned discussion interface can make it significantly easier to reference specific parts of videos or documents, helping online learners and collaborators engage more deeply with shared materials.
Sungsoo (Ray) Hong, Rafal Kocielnik, Min-Joon Yoo, Sarah Battersby, Juho Kim, Cecilia Aragon
💡 This paper shows that redesigning distance cartograms with context-preserving techniques and targeted interactions helps urban travelers quickly compare travel times to destinations without losing their sense of geographic orientation.
Chunjong Park, Junsung Lim, Juho Kim, Sung-Ju Lee, Dongman Lee
💡 This paper shows that smartphones can automatically detect natural pauses in face-to-face conversations to delay notifications, helping people stay more engaged in social interactions without missing important alerts.
Joseph Williams, Tania Lombrozo, Anne Hsu, Bernd Huber, Juho Kim
💡 Asking online learners to explain why surprising facts are true—rather than just think about them—helps correct statistical misconceptions without personalized instructor feedback, especially when multiple counterexamples challenge wrong beliefs simultaneously.
Joseph Williams, Juho Kim, Anna Rafferty, Samuel Maldonado, Krzysztof Z. Gajos, Walter Lasecki, Neil Heffernan
💡 This paper shows that combining student-generated explanations with machine learning can produce homework explanations as helpful as instructor-written ones, helping online learning platforms scale high-quality feedback without requiring expert effort.
Nam Wook Kim, Jonghyuk Jung, Eun-Young Ko, Songyi Han, Chang Won Lee, Juho Kim, Jihee Kim
💡 This paper shows that crowdsourcing issue-based tags for government budget items helps ordinary citizens better understand public spending by connecting abstract line items to social issues they care about.
Joseph Jay Williams, Juho Kim, Elena L. Glassman, Anna Rafferty, Walter S. Lasecki
Juho Kim, Elena L. Glassman, Andrés Monroy-Hernández, Meredith Ringel Morris
💡 This paper shows that embedding video, audio, and drawing exercises into lecture videos helps teachers see how students actually think through problems, revealing misconceptions that multiple-choice quizzes miss.
Elena L. Glassman, Juho Kim, Andrés Monroy-Hernández, Meredith Ringel Morris
💡 This paper shows that letting students mark confusing moments directly on lecture video slides helps both learners articulate their struggles and instructors pinpoint exactly where explanations need improvement.
Juho Kim, Eun-Young Ko, Jonghyuk Jung, Chang Won Lee, Nam Wook Kim, Jihee Kim
💡 This paper shows that augmenting news articles with government budget data and fact-checking tools helps citizens discuss public spending more critically and with better evidence, making complex fiscal information accessible for democratic participation.
Walter Lasecki, Juho Kim, Nick Rafter, Onkur Sen, Jeffery Bigham, Michael Bernstein
💡 This paper shows that combining real-time crowdsourcing with sketch recognition lets designers create working interactive prototypes as fast as they can draw and speak, dramatically accelerating the feedback cycle in interface design.
Sarah Weir, Juho Kim, Krzysztof Z. Gajos, Robert C. Miller
💡 This paper shows that learners watching how-to videos can collectively generate useful step-by-step outlines while learning, helping video platforms create better educational interfaces without requiring expert annotation.
Juho Kim, Philip J. Guo, Carrie J. Cai, Shang-Wen (Daniel) Li, Krzysztof Z. Gajos, Robert C. Miller
💡 This paper shows that visualizing how other learners navigate educational videos can make finding specific information feel more efficient, helping online learners and course designers understand which video moments attract the most attention.
Juho Kim, Amy X. Zhang, Jihee Kim, Robert C. Miller, Krzysztof Z. Gajos
💡 This paper shows that adding subtle resistance during scrolling at high-interest sections helps users find important content in long documents on touchscreens, reducing the cognitive effort of navigating cluttered web pages.
Anant Bhardwaj, Juho Kim, Steven P. Dow, David Karger, Sam Madden, Robert C. Miller, Haoqi Zhang
💡 This paper shows that collecting attendees' paper preferences before a conference reveals scheduling conflicts and session groupings that organizer and author input alone would miss, enabling better large-event planning.
Juho Kim, Phu Nguyen, Sarah Weir, Philip J. Guo, Robert C. Miller, Krzysztof Z. Gajos
💡 This paper shows that crowdsourced step-by-step annotations significantly improve how people learn from instructional videos, offering a scalable method to make millions of existing tutorials easier to navigate and follow.
Lydia Chilton, Juho Kim, Paul André, Felicia Cordeiro, James Landay, Dan Weld, Steven P. Dow, Robert C. Miller, Haoqi Zhang
💡 This paper shows that decomposing conference session planning into crowd-sourced metadata tagging and constraint satisfaction reduces a full-day task to 88 minutes, helping program committees organize papers more efficiently.
Juho Kim, Philip J. Guo, Daniel T. Seaton, Piotr Mitros, Krzysztof Z. Gajos, Robert C. Miller
💡 This paper shows that analyzing second-by-second viewing patterns from 862 online course videos reveals why students drop out or replay specific moments, helping educators design more effective instructional videos.
Philip J. Guo, Juho Kim, Rob Rubin
💡 This paper shows that shorter, informal videos with tablet-style drawings keep online learners watching longer than polished lecture recordings, helping educators design more effective educational content.
Paul André, Haoqi Zhang, Juho Kim, Lydia B. Chilton, Steven P. Dow, Robert C. Miller
💡 This paper shows that crowdsourcing paper groupings from committee members and authors produces conference sessions as good as or better than traditional manual organizing, while revealing hidden connections between papers that make scheduling more flexible.
Juho Kim, Haoqi Zhang, Paul André, Lydia B. Chilton, Wendy Mackay, Michel Beaudouin-Lafon, Robert C. Miller, Steven P. Dow
💡 This paper shows that involving conference attendees and authors in providing scheduling preferences helps organizers resolve conflicts more effectively, making large academic conferences better organized through community input rather than top-down planning alone.
Michael Nowak, Juho Kim, Nam Wook Kim, Clifford Nass
💡 This paper shows that real-time displays of emotional arousal during negotiations can backfire—helping high-status individuals but undermining others—revealing how power dynamics shape whether biofeedback tools help or harm performance.
Juho Kim, Benjamin Malley, Joel Brandt, Mira Dontcheva, Diana Joseph, Krzysztof Z. Gajos, Robert C. Miller
💡 This paper shows that people learning graphic design online struggle to search effectively, recognize useful resources, and apply what they find, revealing key barriers that better learning tools could address.
Juho Kim, Chen-Hsiang Yu, Robert C. Miller, Krzysztof Z. Gajos
💡 This paper shows that embedding natural-language help requests directly into blog drafts can streamline writing by automatically routing tasks to software, crowds, or readers, helping bloggers maintain creative flow while getting timely feedback.
Eser Kandogan, Juho Kim, Thomas P. Moran, Pablo Pedemonte
💡 This paper shows that freeform spatial interfaces help people solve problems more effectively than spreadsheets by letting them flexibly arrange information, track progress visually, and reduce mental effort.
Kyungyoon Jung, Donggun Lee, Hyun Seung Moon, Eunji Shin, Seon Gyeom Kim, SeongWon Hong, Juho Kim, Tak Yeon Lee
Donggun Lee, Kyungyoon Jung, Hyun Seung Moon, Jaywoong Jeong, Eunji Shin, Seon Gyeom Kim, SeongWon Hong, Juho Kim, Tak Yeon Lee
Chaemin Jang, Junsik Min, Jaewoo Choi, Donggyu Lee, Haiin Lee, Junyoung Park, Namhee Kim, Hyunwoo Kim, Jungwon Kim, Juho Kim, Nuri Kim, Jihee Kim
Chaemin Jang, Junsik Min, Jaewoo Choi, Donggyu Lee, Haiin Lee, Junyoung Park, Namhee Kim, Hyunwoo Kim, Jungwon Kim, Juho Kim, Nuri Kim, Jihee Kim
Hyehyun Chu, Yuri Lee, Yeon Su Park, Saelyne Yang, Juho Kim
Yoonsu Kim, Hayeon Doh, Eunhye Kim, Jinho Son, Juho Kim
DaEun Choi, Kihoon Son, Jaesang Yu, Hyunjoon Jung, Juho Kim
Yoonsu Kim, Brandon Chin, Kihoon Son, Seoyoung Kim, Juho Kim
DaEun Choi, Kihoon Son, Hyunjoon Jung, Juho Kim
Minju Yoo, Hyoungwook Jin, Juho Kim
Hyoungwook Jin, Haesoo Kim, Nathan Mekuria Haile, Soyeong Min, Juho Kim
Hyoungwook Jin, Yoonsu Kim, Yeon Su Park, Bekzat Tilekbay, Jinho Son, Juho Kim
Steven Moore, Anjali Singh, Xinyi Lu, Hyoungwook Jin, Hassan Khosravi, Paul Denny, Christopher Brooks, Xu Wang, Juho Kim, John Stamper
Hyunwoo Kim, Yoonseo Choi, Taehyun Yang, Honggu Lee, Chaneon Park, Yongju Lee, Jin Young Kim, Juho Kim
Saelyne Yang, Jaesang Yu, Jae Won Cho, Juho Kim
Yoonsu Kim, Kihoon Son, Seoyoung Kim, Juho Kim
Kihoon Son, Jinhyeon Kwon, DaEun Choi, Tae Soo Kim, Young-Ho Kim, Sangdoo Yun, Juho Kim
Jeongeon Park, Bryan Min, Jean Y. Song, Xiaojuan Ma, Juho Kim
Yoonjoo Lee, Tae Soo Kim, Juho Kim
Hyungyu Shin, Seulgi choi, Ji Yong Cho, Sahar Admoni, Hyunseung Lim, Taewan Kim, Hwajung Hong, Moontae Lee, Juho Kim
Jieun Han, Haneul Yoo, Junho Myung, Minsun Kim, Hyunseung Lim, Yoonsu Kim, Tak Yeon Lee, Hwajung Hong, Juho Kim, So-Yeon Ahn, Alice Oh
Gionnieve Lim, Hyunwoo Kim, Yoonseo Choi, Toby Jia-Jun Li, Chinmay Kulkarni, Hariharan Subramonyam, Joseph Seering, Michael S. Bernstein, Amy X. Zhang, Elena L. Glassman, Simon Perrault, Juho Kim
Jieun Han, Haneul Yoo, Yoonsu Kim, Junho Myung, Minsun Kim, Hyunseung Lim, Juho Kim, Tak Yeon Lee, Hwajung Hong, So-Yeon Ahn, Alice Oh
Juhoon Lee, Juho Kim, Jeong-woo Jang
Haesoo Kim, Juhoon Lee, Juho Kim, Jeong-woo Jang
Tae Soo Kim, Arghya Sarkar, Yoonjoo Lee, Minsuk Chang, Juho Kim
Saelyne Yang, Sangkyung Kwak, Tae Soo Kim, Juho Kim
Jeongyeon Kim, DaEun Choi, Matthew Beane, Juho Kim
Hyungyu Shin, Nabila Sindi, Yoonjoo Lee, Jaeryoung Ka, Jean Y. Song, Juho Kim
Eun Jeong Kang, Haesoo Kim, Hyunwoo Kim, Juho Kim
Yoonjoo Lee, Tae Soo Kim, Minsuk Chang, Juho Kim
Haesoo Kim, Inhwa Song, Juho Kim
Hyoungwook Jin, Juho Kim
Yoonseo Choi, Eun Jeong Kang, Juho Kim
Jeongeon Park, Eunyoung Ko, Donghoon Han, Jinyeong Yim, Juho Kim
Jeongyeon Kim, Juho Kim
Jeongyeon Kim, Juho Kim
Taewook Kim, Hyunwoo Kim, Juho Kim, Xiaojuan Ma
Donghoon Han, Juho Kim, Alice Oh
Kabdo Choi, Sally Chen, Hyungyu Shin, Jinho Son, Juho Kim
Yoonseo Choi, Hyungyu Shin, Toni-Jan Keith Monserrat, Nyoungwoo Lee, Jeongeon Park, Juho Kim
Yoonseo Choi, Hyungyu Shin, Toni-Jan Keith Monserrat, Nyoungwoo Lee, Jeongeon Park, Juho Kim
Tae Soo Kim, Sungsoo (Ray) Hong, Nitesh Goyal, Jeongyeon Kim, Juho Kim
Yoonseo Choi, Toni-Jan Monserrat, Jeongeon Park, Hyungyu Shin, Nyoungwoo Lee, Juho Kim
Seoyoung Kim, Arti Thakur, Juho Kim
Kyung Je Jo, Hyeonggeun Yun, Juho Kim
Hyunsung Cho, Jinyoung Oh, Juho Kim, Sung-Ju Lee
Joon-Gyum Kim, Taesik Gong, Bogoan Kim, JaeYeon Park, Woojeong Kim, Evey Huang, Kyungsik Han, Juho Kim, JeongGil Ko, Sung-Ju Lee
Minsuk Chang, Juho Kim
Eun-Young Ko, Ching Liu, Hyuntak Cha, Juho Kim
Hyunwoo Kim, Eun-young Ko, Donghoon Han, Sung-chul Lee, Simon Perrault, Jihee Kim, Juho Kim
Hyoungwook Jin, Minsuk Chang, Juho Kim
Jibon Naher, Taehyeon An, Juho Kim
Hyeungshik Jung, Valentina Hijung Shin, Juho Kim
Hyeungshik Jung, Valentina Hijung Shin, Juho Kim
Shayan Doroudi, Joseph Jay Williams, Juho Kim, Thanaporn Patikorn, Korinn S. Ostrow, Douglas Selent, Neil T. Heffernan, Thomas Hills, Carolyn P. Rosé
Sung-chul Lee, Jihee Kim, Juho Kim
Seoyoung Kim, Jiyoun Ha, Juho Kim
Kyungje Jo, John Joon Young Chung, Juho Kim
Kyungje Jo, John Joon Young Chung, Juho Kim
Ching Liu, Hao-Chuan Wang, Juho Kim
Joseph Jay Williams, Anna Rafferty, Andrew Ang, Dustin Tingley, Walter Lasecki, Juho Kim
Minsuk Chang, Vivian Hare, Juho Kim, Maneesh Agrawala
Seokwoo Song, Juho Kim, John Kim
Joseph Jay Williams, Anna Rafferty, Andrew Ang, Dustin Tingley, Walter Lasecki, Juho Kim
Joseph Jay Williams, Anna Rafferty, Samuel Maldonado, Andrew Ang, Dustin Tingley, Juho Kim
Hongjun Lim, Choongho Chung, Jihee Kim, Juho Kim, Sue Moon, Meeyoung Cha
Sungchul Lee, Jihee Kim, Juho Kim
Brian McInnis, Alissa Centivany, Juho Kim, Marta Poblet, Karen Levy, Gilly Leshed
Jihyeon (Janel) Lee, Juho Kim, Maneesh Agrawala
Sherry Ruan, Dae Hyun Kim, Juho Kim, Maneesh Agrawala
Juho Kim
Chunjong Park, Junsung Lim, Juho Kim, Sung-Ju Lee, Dongman Lee
Juho Kim
Piotr Mitros, Juho Kim
Nam Wook Kim, Jihee Kim, Juho Kim, Chang Won Lee, Eun-Young Ko, Jonghyuk Jung
Nam Wook Kim, Chang Won Lee, Jonghyuk Jung, Eun-Young Ko, Juho Kim, Jihee Kim
Soon Hau Chua, Juho Kim, Toni-Jan Keith Monserrat, Shengdong Zhao
Joseph Jay Williams, Juho Kim, Brian C. Keegan
Joseph Jay Williams, Korinn Ostrow, Xi Xiong, Elena Glasman, Juho Kim, Samuel Maldonado, Justin Reich, Neil Heffernan
Joseph Jay Williams, Markus Krause, Praveen Paritosh, Jacob Whitehill, Justin Reich, Juho Kim, Piotr Mitros, Neil Heffernan, Brian C. Keegan
Soon Hau Chua, Juho Kim, Toni-Jan Keith Monserrat, Shengdong Zhao
Joseph Jay Williams, Na Li, Juho Kim, Jacob Whitehill, Samuel Maldonado, Mykola Pechenizkiy, Larry Chu, Neil Heffernan
Juho Kim
Juho Kim, Shang-Wen (Daniel) Li, Carrie J. Cai, Krzysztof Z. Gajos, Robert C. Miller
Juho Kim
Juho Kim
Juho Kim, Haoqi Zhang, Paul André, Lydia B. Chilton, Anant Bhardwaj, David Karger, Steven P. Dow, Robert C. Miller.
Juho Kim, Phu Nguyen, Robert C. Miller, Krzysztof Z. Gajos
Juho Kim, Robert C. Miller, Krzysztof Z. Gajos
Phu Nguyen, Juho Kim, Robert C. Miller
Haoqi Zhang, Paul André, Lydia Chilton, Juho Kim, Steven P. Dow, Robert C. Miller, Wendy MacKay, Michel Beaudouin-Lafon
Matthew Lease, Jessica Hullman, Jeffrey P. Bigham, Michael S. Bernstein, Juho Kim, Walter S. Lasecki, Saeideh Bakhshi, Tanushree Mitra, Robert C. Miller
Juho Kim, Benjamin Malley, Joel Brandt, Mira Dontcheva, Diana Joseph, Krzysztof Z. Gajos, Robert C. Miller
Juho Kim, Ranjitha Kumar, Scott R. Klemmer
Ranjitha Kumar, Juho Kim, Scott R. Klemmer