We introduce Sketch-Then-Generate — a new way to code with #LLM . It offers instant, *incremental* feedback via code sketches as you type prompts, and uses these sketches as outlines to guide LLMs in code generation

arxiv.org/abs/2405.03998
w/ Zeyu, Xiaoshuo, and Elena Glassman

One-way lectures are ineffective. What if we can transform any lecture video into a dialogue between a virtual learner and instructor? We present VIVID, an LLM-powered system that made this possible.

Project website🔗: vivid.kixlab.org
Preprint📃: arxiv.org/abs/2403.09168

Most educational chatbots are designed to teach learners. What if we instead enable learners to teach a bot? Our #CHI2024 paper w/ Honorable Mention award introduces techniques to simulate inquisitive learner behavior in LLM agents to aid human learning. Led by HyoungWook Jin.

How do programmers decide whether to use generative AI 🤖 or web search 🔍 when faced with a problem?

Check out our #CHI2024 LBW, 'To Search or To Gen? Exploring the Synergy between Generative AI and Web Search in Programming' to find out!

안녕하세요, 2년 째 프로그래밍기초 과목의 조교를 담당하고 있는 학생들과 함께, 새로운 연구를 준비하고 있습니다.
'공부와 학습에 ChatGPT를 사용하는 것'에 대한 우려나 의견이 있으신 교수자 및 다양한 교육자 분들의 고견을 듣고자 합니다. 설문 참여 부탁드립니다🙏

docs.google.com/forms/d/e/1FAI…

This work is also accepted to #CHI2024 ! yay 🥳

If you are interested in a design support tool using generative models, please check our paper!

Our paper shows how designers reveal their implicit design search intent through the GenAI-based interaction 😀

Design has long been considered mysterious, driven by intuition and creativity🧐 But we set out to demystify it!

Our paper investigates designers' tacit knowledge and proposes guidelines for systems that can capture and share it

This work got an Honorable Mention 🏆 #chi2024
🧵

I was lucky to be involved in 3 #CHI2024 papers. :-)

1. A project led by Fengyuan Zhu where we investigate spatial anchorings and interaction techniques for interacting with smartphones in virtual reality. With Fengyuan Zhu, Mauricio Sousa and Tovi Grossman. programs.sigchi.org/chi/2024/progr…

Are you interested in programming UIs that make programs feel more dynamic and alive?

Join us at LIVE, the research workshop about live programming! (submissions due July 7)

liveprog.org

Personal backstory on why LIVE matters to me:

Back in 2018 I was starting to…

New work from the lab!

A prompt is a blind probe of a single point in the vast problem/solution/design space. #Luminate illuminates the space you are in, and facilitates problem understanding and creative exploration.

Check out the paper, videos, & system!

<Summer Research Internship at KIXLAB>
I'm looking for undergrad research interns to join my research group (kixlab.org) this summer. Most projects this round are about human-AI interaction. Please share broadly!

juhokim.com/2024-summer-in…

Folks, try out Luminate! Among all HCI systems that I've been involved in over years, Luminate is the one that I personally find most useful and I naturally find reasons to use all the time. Kudos Sangho Suh Meng Chen Bryan Min for the system effort beyond a #chi2024 paper.

Congrats, Meng! A well-deserved accomplishment for your hard work. I look forward to seeing what you do Computer Science at UT Austin! Keep up the great work! :)

Looking to do a PhD in HCI? Going to #CHI2024 ? Look no further! The Montréal HCI lab is recruiting PhD students (hci.iro.umontreal.ca). I will be at CHI this year, reach out if you’d like to chat! 🤩✨

Congrats Ryan! Excited for your new journey MIT Visualization Group! :)

Are you going to #CHI2024 ? Consider signing up for our course, “Human-Computer Interaction and AI: What Practitioners Need to Know to Design and Build Effective AI Systems from a Human Perspective.”
We’re Course 07 to be held on Wednesday, May 15, 2024. sites.google.com/view/chi-2024-…