A profile picture of Hyeonsu Kang
HyeonsuB. Kang
Industry Bio | Academic Bio

As a Human-AI Interaction specialist with a Ph.D. from Carnegie Mellon University (CMU), I focus on developing interactive technologies that enhance cognitive efficiency and creativity in human-AI collaboration. My research aims to address real-world challenges across domains including scientific discovery, engineering, product innovation, and design thinking. With years of experience, my expertise spans:

  • • Design, development, and deployment of ML models and LLM-infused full-stack interactive systems
  • • Data collection and analysis pipelines, including bespoke crowdsourcing systems and NLP techniques
  • • Design and execution of quantitative, qualitative, and mixed-method evaluations at various scales (e.g., case, laborotory, and field studies)

My work has led to tangible real-world impacts, including improving engagement with personalized email alerts for scientific research papers, benefiting thousands of users (deployed at the Allen Institute for Artificial Intelligence) and contributing to research allocating $2M in prize money for global conservation innovation contests (organized by Conservation X Labs, a conservation-focused non-profit).

Throughout my work, I've collaborated with professionals across various disciplines (e.g., engineers, designers, scientists, and teachers) and organizations (e.g., Toyota Research Institute, Conservation X Labs, Allen Institute for AI, MIT). My contributions have been recognized with a Best Paper Award at ACM CHI (2024) and a Google Cloud Innovator Award (2021). Additionally, my research findings have become required reading at Virginia Tech and CMU.

Hyeonsu Kang (Ph.D., Carnegie Mellon University, 2024) is a Human-AI Interaction researcher specializing in enhancing cognitive efficiency and creativity through collaborative AI systems. His work combines cognitive theories with cutting-edge AI to improve problem-solving and ideation for both experts and novices across various domains. Kang's research spans three key areas:

His work has resulted in real-world impacts, including improving personalized email alerts for scientific research papers (deployed at the Allen Institute for Artificial Intelligence) and contributing to the allocation of $2M in prize money for global conservation innovation contests (Conservation X Labs, a conservation-focused non-profit). His research has fostered collaborations with professionals across various disciplines (e.g., engineers, designers, scientists, and teachers) and organizations (e.g., MIT, the University of Maryland, the University of Washington, and KAIST, and industry partners such as Conservation X, the Allen Institute for Artificial Intelligence, and the Toyota Research Institute).

Kang's contributions have been recognized with a best paper award at ACM CHI (2024) and a Google Cloud Innovator Award (2021). His work has been published in premier NLP and HCI conferences and journals, including ACM CHI, UIST, TOCHI, AAAI, NAACL, and NeurIPS. His research has been funded by the National Science Foundation, the Allen Institute for Artificial Intelligence, the Office of Naval Research, the Toyota Research Institute, and Google Cloud. Prior to his Ph.D., Kang received his BS in Computer Science and Engineering at Seoul National University. He also worked and interned at MIT, the Allen Institute for AI, UC San Diego, and Tableau Software. He was previously supported by the South Korean National Scholarship for Science and Engineering.

Publications

🏆 CHI 2024
Nouran Soliman, Hyeonsu B. Kang, Matthew Latzke, Jonathan Bragg, Joseph Chee Chang, Amy X. Zhang, David R Karger
CHI 2024 (Best Paper Award 🏆) [PDF]
In communities with social hierarchies, fear of judgment can discourage communication. While anonymity may alleviate some social pressure, fully anonymous spaces enable toxic behavior and hide the social context that motivates people to participate and helps them tailor their communication. We explore a design space of meronymous communication, where people can reveal carefully chosen aspects of their identity and also leverage trusted endorsers to gain credibility. We implemented these ideas in a system for scholars to meronymously seek and receive paper recommendations on Twitter and Mastodon. A formative study with 20 scholars confirmed that scholars see benefits to participating but are deterred due to social anxiety. From a month-long public deployment, we found that with meronymity, junior scholars could comfortably ask "newbie" questions and get responses from senior scholars who they normally found intimidating. Responses were also tailored to the aspects about themselves that junior scholars chose to reveal.
CHI 2024
Yoonjoo Lee, Hyeonsu B. Kang, Matthew Latzke, Juho Kim, Jonathan Bragg, Joseph Chee Chang, Pao Siangliulue
CHI 2024 [PDF]
With the rapid growth of scholarly archives, researchers subscribe to "paper alert" systems that periodically provide them with recommendations of recently published papers that are similar to previously collected papers. However, researchers sometimes struggle to make sense of nuanced connections between recommended papers and their own research context, as existing systems only present paper titles and abstracts. To help researchers spot these connections, we present PaperWeaver, an enriched paper alerts system that provides contextualized text descriptions of recommended papers based on user-collected papers. PaperWeaver employs a computational method based on Large Language Models (LLMs) to infer users' research interests from their collected papers, extract context-specific aspects of papers, and compare recommended and collected papers on these aspects. Our user study (N=15) showed that participants using PaperWeaver were able to better understand the relevance of recommended papers and triage them more confidently when compared to a baseline that presented the related work sections from recommended papers.
UIST 2023
Hyeonsu B. Kang, Sherry Tongshuang Wu, Joseph Chee Chang, Aniket Kittur
UIST 2023 [PDF  ·  ACM DL  ·  BibTeX  ·  ACM Ref  ·  EndNote]
Efficiently reviewing scholarly literature and synthesizing prior art are crucial for scientific progress. Yet, the growing scale of publications and the burden of knowledge make synthesis of research threads more challenging than ever. While significant research has been devoted to helping scholars interact with individual papers, building research threads scattered across multiple papers remains a challenge. Most top-down synthesis (and LLMs) make it difficult to personalize and iterate on the output, while bottom-up synthesis is costly in time and effort. Here, we explore a new design space of mixed-initiative workflows. In doing so we develop a novel computational pipeline, Synergi, that ties together user input of relevant seed threads with citation graphs and LLMs, to expand and structure them, respectively. Synergi allows scholars to start with an entire threads-and-subthreads structure generated from papers relevant to their interests, and to iterate and customize on it as they wish. In our evaluation, we find that Synergi helps scholars efficiently make sense of relevant threads, broaden their perspectives, and increases their curiosity. We discuss future design implications for thread-based, mixed-initiative scholarly synthesis support tools.

A demo video of Synergi is available here.
CHI 2023
Hyeonsu B. Kang, Nouran Soliman, Matt Latzke, Joseph Chee Chang, Jonathan Bragg
CHI 2023 [PDF  ·  ACM DL  ·  BibTeX  ·  ACM Ref  ·  EndNote]
In order to help scholars understand and follow a research topic, significant research has been devoted to creating systems that help scholars discover relevant papers and authors. Recent approaches have shown the usefulness of highlighting relevant authors while scholars engage in paper discovery. However, these systems do not capture and utilize users’ evolving knowledge of authors. We reflect on the design space and introduce ComLittee, a literature discovery system that supports author-centric exploration. In contrast to paper-centric interaction in prior systems, ComLittee’s author-centric interaction supports curation of research threads from individual authors, finding new authors and papers with combined signals from a paper recommender and the curated authors’ authorship graphs, and understanding them in the context of those signals. In a within-subjects experiment that compares to an author-highlighting approach, we demonstrate how ComLittee leads to a higher efficiency, quality, and novelty in author discovery that also improves paper discovery.

A demo video of ComLittee is available here.
a purpose query 'Facilitate heat transfer in semiconductors' is shown to match to two different papers with diverse mechanisms that inspired a user study participant to come up with creative adaptation and direct application ideas TOCHI 2022
Hyeonsu B. Kang, Xin Qian, Tom Hope, Dafna Shahaf, Joel Chan, and Aniket Kittur
TOCHI 2022 [PDF  ·  Dataset  ·  ACM DL  ·  BibTeX  ·  ACM Ref  ·  EndNote]
Analogies have been central to creative problem-solving throughout the history of science and technology. As the number of scientific papers continues to increase exponentially, there is a growing opportunity for finding diverse solutions to existing problems. However, realizing this potential requires the development of a means for searching through a large corpus that goes beyond surface matches and simple keywords. Here we contribute the first end-to-end system for analogical search on scientific papers and evaluate its effectiveness with scientists' own problems. Using a human-in-the-loop AI system as a probe we find that our system facilitates creative ideation, and that ideation success is mediated by an intermediate level of matching on the problem abstraction (i.e., high versus low). We also demonstrate a fully automated AI search engine that achieves a similar accuracy with the human-in-the-loop system. We conclude with design implications for enabling automated analogical inspiration engines to accelerate scientific innovation.
The first page of the paper PDF. CACM 2024
Kyle Lo, Joseph C. Chang, Andrew Head et al. (including Hyeonsu B. Kang)
Communications of the ACM (forthcoming, 2024) [PDF  ·  BibTeX]
Scholarly publications are key to the transfer of knowledge from scholars to others. However, research papers are information-dense, and as the volume of the scientific literature grows, the need for new technology to support scholars grows. In contrast to the process of finding papers, which has been transformed by Internet technology, the experience of reading research papers has changed little in decades. For instance, the PDF format for sharing papers remains widely used due to its portability but has significant downsides, inter alia, static content and poor accessibility for low-vision readers. This paper explores the question "Can recent advances in AI and HCI power intelligent, interactive, and accessible reading interfaces—even for legacy PDFs?" We describe the Semantic Reader Project, a collaborative effort across multiple institutions to explore automatic creation of dynamic reading interfaces for research papers. Through this project, we've developed many novel prototype interfaces and evaluated them with user study participants and real-world users to show improved reading experiences for scholars. We've also released a production research paper reading interface that will incorporate novel features as they mature. We structure this paper around five key opportunities for AI assistance in scholarly reading -- discovery, efficiency, comprehension, synthesis, and accessibility -- and present an overview of our progress and remaining open challenges.
UIST 2022
Hyeonsu B. Kang, Joseph Chee Chang, Yongsung Kim, Aniket Kittur
UIST 2022 [PDF  ·  ACM DL  ·  BibTeX  ·  ACM Ref  ·  EndNote]
Reviewing the literature to understand relevant threads of past work is a critical part of research and vehicle for learning. However, as the scientific literature grows the challenges for users to find and make sense of the many different threads of research grow as well. Previous work has helped scholars to find and group papers with citation information or textual similarity using standalone tools or overview visualizations. Instead, in this work we explore a tool integrated into users' reading process that helps them with leveraging authors' existing summarization of threads, typically in introduction or related work sections, in order to situate their own work's contributions. To explore this we developed a prototype that supports efficient extraction and organization of threads along with supporting evidence as scientists read research articles. The system then recommends further relevant articles based on user-created threads. We evaluate the system in a lab study and find that it helps scientists to follow and curate research threads without breaking out of their flow of reading, collect relevant papers and clips, and discover interesting new articles to further grow threads.
An example indirect author-based relevance message augmenting the incoming new paper recommendaiton. CHI 2022
Hyeonsu B. Kang, Rafal Kocielnik, Andrew Head, Jiangjiang Yang, Matt Latzke, Aniket Kittur, Daniel Weld, Doug Downey, and Jonathan Bragg
CHI 2022 [PDF  ·  ACM DL  ·  BibTeX  ·  ACM Ref  ·  EndNote]
Finding and engaging with the relevant scientific knowledge is foundational for intellectual progress in a society. Yet, with an exponential growth in publication rates, this becomes a challenging task. While personalized recommendations can help, they still may lack explanations of how certain papers are relevant and thus should be prioritized or attended to. To combat this, we developed a citation-based and two kinds of social relation-based approaches to boost user engagement with scholarly paper recommendations. For users who opted in, these approaches augmented paper recommendations included in email alerts with textual relevance descriptions underneath the recommendations. We evaluated our approaches in a randomized field experiment that ran for over two months and with 7,000+ users, and also in a controlled lab study (N=14) for deeper qualitative insights. We report on our findings and implications for the design of future approaches that aim to augment scholarly recommendations.
A functional graph representation using the extracted purposes of product ideas CHI 2022
Tom Hope, Ronen Tamari, Hyeonsu Kang, Daniel Hershcovich, Joel Chan, Aniket Kittur, and Dafna Shahaf
CHI 2022 [PDF  ·  ACM DL  ·  BibTeX  ·  ACM Ref  ·  EndNote]
We explore a novel representation for automatically breaking up product ideas described in natural language into fine-grained functional aspects. This representation can capture the core purposes and mechanisms in ideas, and support the backbone interactions (e.g., functional search of ideas, mapping and exploration of the design space around a focal problem) for augmenting human intelligence and accelerating the rate of innovation.
A diagrammatic representation of the idea of Paragon CHI 2018
Hyeonsu B. Kang, Gabriel Amoako, Neil Sengupta, Steven Dow
CHI 2018 [PDF  ·  ACM DL  ·  BibTeX  ·  ACM Ref  ·  EndNote]
“A picture is worth a thousand words.” We developed Paragon, a system that supports crowdworkers and peers during feedback exchange by enabling search of design examples that supplement the written feedback. In two lab studies, we found that i) feedback providers select poster examples that complement their feedback and align with a provided rubric and that ii) feedback providers give significantly more specific, actionable, and novel input when using an example-centric approach, as opposed to text alone.
An example of bidirectional code and visualization linking. UIST 2017
Hyeonsu Kang, Philip Guo
UIST 2017 [PDF  ·  ACM DL  ·  BibTeX  ·  ACM Ref  ·  EndNote]
We developed Omnicode, a programming environment with an always-on run-time visualization that helps novice programmers directly see how the variables and their relations change in real-time, in response to the changes they make in the program code. In our lab study, we found Omnicode to be useful for debugging, forming proper mental models, explaining their code to others, and discovering moments of serendipity that would not have been likely within an ordinary IDE.
BioSpark main interface featuring a board of biological analogical mechanism images with four interaction features: Explain, Compare, Combine, and Critique. NeurIPS 2023
Hyeonsu B. Kang, David Chuan-En Lin, Nikolas Martelaro, Aniket Kittur, Yan-Ying Chen, Matthew K. Hong
NeurIPS 2023 Creativity Workshop [PDF coming soon]
Nature is often used to inspire solutions for complex engineering problems, but achieving its full potential is challenging due to difficulties in discovering relevant analogies and synthesizing from them. Here, we present an end-to-end system, BioSpark, that generates biological-analogical mechanisms and provides an interactive interface to comprehend and synthesize from them. BioSpark pipeline starts with a small seed set of mechanisms and expands it using an iteratively constructed taxonomic hierarchies, overcoming data sparsity in manual expert curation and limited conceptual diversity in automated analogy generation via LLMs. The interface helps designers with recognizing and understanding relevant analogs to design problems using four main interaction features. We evaluate the biological-analogical mechanism generation pipeline and showcase the value of BioSpark through case studies. We end with discussion and implications for future work in this area.
A diagrammatic representation of the system implementation consisting of three main components: Aspect-based querying; Global domain cluster generation; Local domain cluster generation NAACL 2022
Hyeonsu B. Kang*, Sheshera Mysore*, Kevin Huang*, Haw-Shiuan Chang, Thorben Prein, Andrew McCallum, Aniket Kittur, Elsa Olivetti
NAACL 2022 Workshop [PDF  ·  BibTeX]
Exposure to ideas in domains outside a scientist's own may benefit her in reformulating existing research problems in novel ways and discovering new application domains for existing solution ideas. While improved performance in scholarly search engines can help scientists efficiently identify relevant advances in domains they may already be familiar with, it may fall short of helping them explore diverse ideas outside such domains. In this paper we explore the design of systems aimed at augmenting the end-user ability in cross-domain exploration with flexible query specification. To this end, we develop an exploratory search system in which end-users can select a portion of text core to their interest from a paper abstract and retrieve papers that have a high similarity to the user-selected core aspect but differ in terms of domains. Furthermore, end-users can 'zoom in' to specific domain clusters to retrieve more papers from them and understand nuanced differences within the clusters. Our case studies with scientists uncover opportunities and design implications for systems aimed at facilitating cross-domain exploration and inspiration.
A 2-D distribution of project ideas based on their similarity to the source project's problem and solution ideas CI 2019
Matching Open Innovation Projects for Analogical Feedback Exchange
Hyeonsu Kang, Felicia Ng, Aniket Kittur
Collective Intelligence 2019
We developed an algorithm for matching teams in open innovation contests that tackle related conservataion challenges using diverse approaches, thereby encouraging the transfer of analogical inspirations between teams. To this end, our algorithm used pre-trained language models to encode the natural language text descriptions of team challenges and their solution approaches into a vector similarity space, then computed semantic similarity between them to systematically find teams tackling similar problems using diverse approaches, shown as a conducive mechanism for the transfer.
a While block program block in Starlogo Nova SIGPLAN 2018
Custom Blocks in StarLogo Nova: A Template-Based Approach to Abstraction for Improved Ease of Use and Expressive Power
Hyeonsu Kang, David Wu, David Wendel
SIGPLAN 2018
We developed a general extension to the StarLogo Nova language to support end-user programming in various disciplines such as evolutionary biology, physics, and ecosystem sciences. This extension allowed end-users to select blocks that correspond to low-level programming constructs such as looping and variable assignment statements, and group them to create abstraction blocks that hide the low-level implementation details that oft-times distract learners from disciplinary learning objectives and system-level conceptual understanding. Using such abstraction blocks can also reduce the complexity of the programming language itself and lower the barrier to entry for novice learners.