Minsuk Chang

Minsuk Chang

Auto-generated profile, based on publicly available information

Minsuk Chang

Google, United States

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 June 2023
Verified
Conference Paper
Open access
MCMinsuk Chang
Minsuk Chang
SDStefania Druga
Stefania Druga
AFAlexander J. Fiannaca
Alexander J. Fiannaca
PVPedro Vergani
Pedro Vergani
CKChinmay Kulkarni
Chinmay Kulkarni
MTMichael Terry
Michael Terry
This paper examines the art practices, artwork, and motivations of prolific users of the latest generation of text-to-image models. Through interviews, observations, and a user survey, we present a sampling of the artistic styles and describe the developed community of practice around generative AI. We find that: 1) artists hold the text prompt and the resulting image can be considered collectively as a form of artistic expression (prompts as art), and 2) prompt templates (prompts with “slots” for others to fill in with their own words) are developed to create generative art styles. We discover that the value placed by this community on unique outputs leads to artists seeking specialized vocabulary to produce distinctive art pieces (e.g., by reading architectural blogs to find phrases to describe images). We also find that some artists use “glitches” in the model that can be turned into artistic styles of their own right. From these findings, we outline specific implications for design regarding future prompting and image editing options.

29 October 2023
Verified
Conference Paper
Open access
TKTae Soo Kim
Tae Soo Kim
YLYoonjoo Lee
Yoonjoo Lee
MCMinsuk Chang
Minsuk Chang
JKJuho Kim
Juho Kim
Large Language Models (LLMs) have become the backbone of numerous writing interfaces with the goal of supporting end-users across diverse writing tasks. While LLMs reduce the effort of manual writing, end-users may need to experiment and iterate with various generation configurations (e.g., inputs and model parameters) until results meet their goals. However, these interfaces are not designed for experimentation and iteration, and can restrict how end-users track, compare, and combine configurations. In this work, we present “cells, generators, and lenses”, a framework to designing interfaces that support interactive objects that embody configuration components (i.e., input, model, output). Interface designers can apply our framework to produce interfaces that enable end-users to create variations of these objects, combine and recombine them into new configurations, and compare them in parallel to efficiently iterate and experiment with LLMs. To showcase how our framework generalizes to diverse writing tasks, we redesigned three different interfaces—story writing, copywriting, and email composing—and, to demonstrate its effectiveness in supporting end-users, we conducted a comparative study (N=18) where participants used our interactive objects to generate and experiment more. Finally, we investigate the usability of the framework through a workshop with designers (N=3) where we observed that our framework served as both bootstrapping and inspiration in the design process.

1 December 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Open access
JPJeongeun Park
Jeongeun Park
SLSeungwon Lim
Seungwon Lim
JLJoonhyung Lee
Joonhyung Lee
SPSangbeom Park
Sangbeom Park
MCMinsuk Chang
Minsuk Chang
SCSungjoon Choi
Sungjoon Choi
In this letter, we focus on inferring whether the given user command is clear, ambiguous, or infeasible in the context of interactive robotic agents utilizing large language models (LLMs). To tackle this problem, we first present an uncertainty estimation method for LLMs to classify whether the command is certain (i.e., clear) or not (i.e., ambiguous or infeasible). Once the command is classified as uncertain, we further distinguish it between ambiguous or infeasible commands leveraging LLMs with situational aware context prompts. For ambiguous commands, we disambiguate the command by interacting with users via question generation with LLMs. We believe that proper recognition of the given commands could lead to a decrease in malfunction and undesired actions of the robot, enhancing the reliability of interactive robot agents. We present a dataset for robotic situational awareness consisting of pairs of high-level commands, scene descriptions, and labels of command type (i.e., clear, ambiguous, or infeasible). We validate the proposed method on the collected dataset and pick-and-place tabletop simulation environment. Finally, we demonstrate the proposed approach in real-world human-robot interaction experiments.

2 May 2024
Verified
Conference Paper
Open access
MKMinsuk Kahng
Minsuk Kahng
ITIan Tenney
Ian Tenney
MPMahima Pushkarna
Mahima Pushkarna
MLMichael Xieyang Liu
Michael Xieyang Liu
JWJames Wexler
James Wexler
LDLucas Dixon
Lucas Dixon
Automatic side-by-side evaluation has emerged as a promising approach to evaluating the quality of responses from large language models (LLMs). However, analyzing the results from this evaluation approach raises scalability and interpretability challenges. In this paper, we present LLM Comparator, a novel visual analytics tool for interactively analyzing results from automatic side-by-side evaluation. The tool supports interactive workflows for users to understand when and why a model performs better or worse than a baseline model, and how the responses from two models are qualitatively different. We iteratively designed and developed the tool by closely working with researchers and engineers at Google. This paper details the user challenges we identified, the design and development of the tool, and an observational study with participants who regularly evaluate their models.


19 April 2023
Verified
Conference Paper
Open access
MCMinsuk Chang
Minsuk Chang
JCJohn Joon Young Chung
John Joon Young Chung
KGKaty Ilonka Gero
Katy Ilonka Gero
THTing-Hao Kenneth Huang
Ting-Hao Kenneth Huang
DKDongyeop Kang
Dongyeop Kang
TWThiemo Wambsganss
Thiemo Wambsganss
In recent years, writing assistants have become increasingly sophisticated and ubiquitous, fueled by advances in artificial intelligence, particularly large language models. As new use cases and models emerge, we expect the adoption rate to accelerate. In this interdisciplinary workshop, we, as a diverse group of researchers and practitioners interested in intelligent and interactive writing assistants, will create a taxonomy of writing assistants and discuss their desirable features and potential consequences. We invite writers, educators, researchers, industry practitioners, students, and anyone interested in creating, using, and testing future writing assistant technologies to join the conversation.