Minsuk's profile picture
Minsuk Chang

I am a researcher at Naver AI Lab (We're hiring!). I am currently building a team around HCI x AI, exploring novel techniques in computational interaction powered by AI technologies. If you're passionate about making AI technologies useful for people by building novel interaction techniques, and/or if you are excited about building AI technologies from human-centered perspectives, please reach out to me!

I have a PhD in Computer Science from KAIST. During my PhD, I was advised by Juho Kim in the KIXLAB. Here's my CV (pdf).

Latest News and Travels
Sept 2020 : A new chapter begins at Naver!
Sept 2020 : Very excited to be invited on the Program Committee for CSCW 2021 and WWW 2021!
Sept 2020 : I have defended my thesis on "Mining Sequential Knowledge for Interation Design".
Aug 2020 : Invited on the panel for AI for Video-Based Learning Workshop at L@S 2020. See you there!
July 2020 : Attending ICML 2020 virtually. Excited to be an SV!
May 2020 : Happy to join the SIGCHI Operations Committee, an amazing team of people making sure SIGCHI processes work.
More News April 2020 : Attending ICLR 2020 virtually.
April 2020 : CHI2021 website is up! Happy to be on the organizing committee!
April 2020 : Workflow Graph has been accepted to the Graphics Interface conference(GI) 2020! Camera-ready and project website will be updated soon!
Jan 2020 : Honored and excited to serve as a program committee member for the Graphics Interface conference(GI) 2020!
Dec 11 2019 : Done with the PhD thesis proposal. Thanks to the committee again for the amazing experience!
Oct 26-29 2019 : Invited Talk at Berkeley Institute of Design - Fall 2019 Seminar Series
Oct 23-25 2019 : Visiting Harvard University + Invited Talk at MIT CSAIL HCI Seminar Series 2019
Oct 19-23 2019 : UIST 2019, New Orleans, LA
September 2019 : Honored and excited to serve as a program committee member for the web conference(WWW) 2020!
August 2019 :Data Structures for Designing Interactions with Contextual Task Support has been accepted to UIST 2019 Doctoral Symposium. See you in New Orleans!
July 2019 : Excited to serve as the Video Chair for ISS 2019! I just love videos.
June 3 2019 : Started summer internship at MSR+AI!
May 31 2019 : Invited to give a talk on data-driven techniques for user task modeling @ IBS
May 30 2019 : Invited as a panel to discuss "how to survive grad school" in Intro to Research class
May 28 2019 : Gave a talk on what HCI research is like for ~90 undergrads in Intro to HCI class
May 3-10 2019 : In Glasgow for CHI 2019! Let's meet!
Apr 2019 : Presented the upcoming CHI paper on looking at Voice UI and Video UI together at SIGCHI Korea Local Chapter spring workshop and received outstanding presentation award! The streak is now two years in a row!
Mar 2019 : My position paper on the two cultures of interface modeling(data-driven and algorithmic) has been accepted to the CHI 2019 Computational Modeling in Human-Computer Interaction Workshop.
Feb 2019 : RecipeScape featured in KAIST School of Computing's research highlight!
Feb 2019 : Our work on subgoal labeling as feedback intervention has been accepted for CHI 19 LBW!
Jan 2019 : Will be spending the summer at Microsoft AI + Research @ Redmond. Super excited!
Dec 2018 : Voice interfaces for video tutorials I worked on during the summer @ Adobe Research has been conditionally accepted to CHI 2019. See you @ Glasgow!
Nov 2018 : Started winter internship at Autodesk Research @ Toronto!
Oct 14-19 2018 : Traveling to UIST 18 @ Berlin, Germany. SV'ing again!
Aug 22 2018 : Visiting University of British Columbia to give a talk on voice+video interfaces.
Jun 2018 : Started research internship at Adobe Research @ Seattle! Seattle people, let's meet!.
Apr 2018 : at CHI 2018 in Montreal, QC, Canada! Presenting RecipeScape on thursday morning.
Apr 2018 : Will present RecipeScape at SIGCHI Korea Local Chapter 2018 Spring Academic Workshop
Mar 2018 : Invited to CHI 2018 Sensemaking Workshop.
Mar 2018 : Excited to spend the summer at Adobe Research @ Seattle!
Feb 2018 : Presented a poster on RecipeScape at HCI@KAIST Winter Workshop. Received best poster award!
Dec 2017 : Our RecipeScape paper is conditionally accepted to CHI 2018!
Oct 22 - 24, 2017 : Student Volunteering for UIST 2017 @ Quebec City, QC, Canada
May 06 - 11, 2017 : Student volunteering for CHI 2017 @ Denver, CO, USA
Feb 2017 Our LBW paper on large scale recipe mining as been accepted to CHI 2017!
Mar 2016 Started my journey in HCI research with Juho!
Less News
Conference Papers (Selected)
GI 2020
Workflow Graphs: A Computational Model of Collective Task Strategies for 3D Design Software
This paper introduces Workflow graphs, or W-graphs, which encode how the approaches taken by multiple users performing a fixed 3D design task converge and diverge from one another. The graph's nodes represent equivalent intermediate task states across users, and directed edges represent how a user moved between these states, inferred from screen recording videos, command log data, and task content history. Read More The result is a data structure that captures alternative methods for performing sub-tasks (e.g., modeling the legs of a chair) and alternative strategies of the overall task. As a case study, we describe and exemplify a computational pipeline for building W-graphs using screen recordings, command logs, and 3D model snapshots from an instrumented version of the Tinkercad 3D modeling application, and present graphs built for two sample tasks. We also illustrate how W-graphs can facilitate novel user interfaces with scenarios in workflow feedback, on-demand task guidance, and instructor dashboards. Read Less
CHI 2019
How to Design Voice Based Navigation for How-To Videos
When watching how-to videos related to physical tasks, users’ hands are often occupied by the task, making voice input a natural fit. To better understand the design space of voice interactions for how-to video navigation, we conducted three think-aloud studies using: 1) a traditional video interface, 2) a research probe providing a voice controlled video interface, and 3) a wizard-of-oz interface. Read More From the studies, we distill seven navigation objectives and their underlying intents: pace control pause, content alignment pause, video control pause, reference jump, replay jump, skip jump, and peek jump. Our analysis found that users’ navigation objectives and intents affect the choice of referent type and referencing approach in command utterances. Based on our findings, we recommend to 1) support conversational strategies like sequence expansions and command queues, 2) allow users to identify and refine their navigation objectives explicitly, and 3) support the seven interaction intents. Read Less
CHI 2018
RecipeScape: An Interactive Tool for Analyzing Cooking Instructions at Scale
Minsuk Chang, Leonore V. Guillain, Hyeungshik Jung, Vivian M. Hare, Juho Kim, Maneesh Agrawala
For cooking professionals and culinary students, understanding cooking instructions is an essential yet demanding task. Common tasks include categorizing different approaches to cooking a dish and identifying usage patterns of particular ingredients or cooking methods, all of which require extensive browsing and comparison. However, no existing system provides support for such in-depth and at-scale analysis. Read More We present RecipeScape, an interactive system for browsing and analyzing the hundreds of recipes of a single dish available online. We also introduce a computational pipeline that extracts cooking processes from recipe text and calculates a procedural similarity between them. To evaluate how RecipeScape supports culinary analysis at scale, we conducted a user study with cooking professionals and culinary students with 500 recipes for two different dishes. Results show that RecipeScape clusters recipes into distinct approaches, and captures notable usage patterns of ingredients and cooking actions. Read Less
Posters, Demos, Workshop Papers
UIST 2019 Doctoral Symposium
Data Structures for Designing Interactions with Contextual Task Support
Minsuk Chang
The diversity and the scale of available online instructions introduce opportunities but also user challenges in currently used software interfaces; Users have limited computational resources, and thus often make strategic decisions when browsing, navigating, and understanding instructions to accomplish a task. These strategic user interactions possess nuanced semantics such as users' interpretations, intents, and contexts in which the task is carried out. Read More My dissertation research introduces techniques in constructing data structures that capture the diverse strategies users employ in which the collective nuanced semantics across multiple strategies are preserved. These computational representations are then used as building blocks for designing novel interactions that allow users to effectively browse and navigate instructions, and provide contextual task guidance. Specifically, I investigate 1) structure of instructions for task analysis at scale, 2) structure of collective user task demonstrations, and 3) structure of object uses in how-to videos for tracking, guiding and searching task states. My research demonstrates that the user-centered organization of information extracted from interaction traces enables novel interfaces with contextual task support. Read Less
CHI 2019 Computational Modeling in Human-Computer Interaction Workshop
User Centered Graphical Models of Interaction
Minsuk Chang, Juho Kim
In this position paper, I present a set of data-driven techniques in modeling the learning material, learner workflow and the learning task as graphical representations, with which at scale can create and support learning opportunities in the wild. I propose the graphical models resulting from this bottom-up approach can further serve as proxies for representing learnability bounds of an interface. Read More I also propose an alternative approach which directly aims to "learn" the interaction bounds by modeling the interface as an agent's sequential decision making problem. Then I illustrate how the data-driven modeling techniques and algorithm modeling techniques can create a mutually beneficial bridge for advancing design of interfaces. Read Less
CHI 2019 LBW
SolveDeep: A System for Supporting Subgoal Learning in Online Math Problem Solving
Hyoungwook Jin, Minsuk Chang, Juho Kim
Learner-driven subgoal labeling helps learners form a hierarchical structure of solutions with subgoals, which are conceptual units of procedural problem solving. While learning with such hierarchical structure of a solution in mind is effective in learning problem solving strategies, the development of an interactive feedback system to support subgoal labeling tasks at scale requires significant expert efforts, making learner-driven subgoal labeling difficult to be applied in online learning environments. We propose SolveDeep, a system that provides feedback on learner solutions with peer-generated subgoals. Read More SolveDeep utilizes a learnersourcing workflow to generate the hierarchical representation of possible solutions, and uses a graph-alignment algorithm to generate a solution graph by merging the populated solution structures, which are then used to generate feedback on future learners' solutions. We conducted a user study with 7 participants to evaluate the efficacy of our system. Participants did subgoal learning with two math problems and rated the usefulness of system feedback. The average rating was 4.86 out of 7 (1: Not useful, 7: Useful), and the system could successfully construct a hierarchical structure of solutions with learnersourced subgoal labels. Read Less
CHI 2018 Sensemaking Workshop
Sensemaking around How-to-cook Videos
Minsuk Chang, Seayeon Lee, Kyungje Jo, Juho Kim
We conducted a series of exploratory studies on sensemaking behaviors people exhibit while watching how-to-cook videos. The three different scenarios we examined are a) when people seek for alternatives in ingredients, tools and actions, b) when people seek for explanations or more detail on certain instructions, and c) when people use text search and when people use video when learning how to cook a dish. Read More We found a) people often make arbitrary decisions on substituting ingredients, cooking tools, or cooking actions while following instructions, b) people satisfice by verifying knowledge with little data and not wanting to deviate from the initially chosen video, and c) people use text search for definitions and confirmation of substitutions while they use video search for explanations and precise details for instruction steps Read Less
CHI 2017 LBW
RecipeScape: Mining and Analyzing Diverse Processes in Cooking Recipes
Minsuk Chang, Vivian M. Hare, Juho Kim, Maneesh Agrawala
In culture analytics, it is important to ask fundamental questions that address salient characteristics of collective human behavior. This paper explores how analyzing cooking recipes in aggregate and at scale identifies these characteristics in the cooking culture, and answer fundamental questions like ”what makes a chocolate chip cookie a chocolate chip cookie?”. Read More Aspiring cooks, professional chefs and cooking hobbyists share their recipes online resulting in thousands of different procedural instructions towards a shared goal. However, existing approaches focus merely on analysis at the ingredient level, for example, extracting ingredient information from individual recipes. We introduce RecipeScape, a prototype interface which supports visually querying, browsing and comparing cooking recipes at scale. We also present the underlying computational pipeline of RecipeScape that scrapes recipes online, extracts their ingredient and instruction information, constructs a graphical representation, and computes similarity between pairs of recipes. Read Less
Organizing Committee
SIGCHI Operations Committee
CHI 2021 Video Capture Co-Chair
ISS 2019 Video Chair
Program Committee
CSCW 2021
GI 2020
WWW 2020, 2021
CHI 2019 LBW
CHI 2017, 2018, 2019, 2020
CSCW 2018, 2019, 2020 (Outstanding Review)
UIST 2017, 2018, 2020
MobileHCI 2019
IMWUT 2020 (Outstanding Review)
Student Volunteer
CHI 2017
UIST 2017, 2018
ICML 2020
In the past,

I studied Computer Science, Financial Engineering from KAIST, Finance from Simon Business School @ University of Rochester, and Statistics from Rutgers University. I have worked at an Hedge Fund in NYC trying to beat the market by relentlessly crunching numbers prior to coming (back) to KAIST. I've spent two years in the reinforcement learning (as a subfield of machine learning) research group at KAIST as a Ph.D student before joining KIXLAB (the KAIST Interaction Lab).

I taught lab sessions for the mandatory Introduction to Programming course at KAIST from 2015-2018 as a Head TA. I enjoyed working with 40 TAs and interacting with 450-500 students each semester.