Bryan Min
@bryandhmin
Building malleable interfaces | HCI PhD Student at UCSD
Malleable Overview-Detail Interfaces at #CHI2025 How do we design malleable interfaces in the age of GenAI? How can we pull information instead of navigating to find it? How can we create our own abstractions of information? Check out our preprint: arxiv.org/abs/2503.07782
Had one of the most rewarding experiences developing Sensecape with @sangho_suh. Feel free to reach out for any questions!
Sensecape is ON ARXIV 📖! Why nonlinear #GPT? Why a 3D hierarchy? What did users think? Check our paper to learn about the motivation, design considerations, users’ feedback on Sensecape and ways it can be used for other types of knowledge work! arxiv.org/abs/2305.11483
🚨 The #DynamicAbstractions Reading Group returns next Friday! 🔍 The Creation, Evolution, and Formalization of New Notational Systems 🎙️ Ian Arawjo (@IanArawjo) 🗓️ July 25, 12pm EST / 9am PST ➕ Add to Calendar: shorturl.at/P4DYc ✉️ Full letter: shorturl.at/JcsBS 🧵
🚨Calling all HCI researchers!—Have you authored a paper involving an LLM-integrated system over the past two years? Care to speak about your experiences with the publication process? 📃 DM or email me—we are running a study around this topic, and would love to hear from you.
The #DynamicAbstractions Reading Group returns this Friday! 🎉 📍Topic: Simulations and Understanding 🗓️ Date & Time: June 27, 12pm EST / 9am PST 🎙️ Speaker: Andy Matuschak (andymatuschak.org) ✉️ Full letter: buttondown.com/dynamic_abstra… 🔁 Please #RT to share! 🧵 More:
AI should not replace browsing, but scale it. #Orca turns the web into your canvas and personal workspace. Work across dozens of pages, delegate to AI agents by your side, and synthesize on the fly. Welcome to 𝗕𝗿𝗼𝘄𝘀𝗶𝗻𝗴 𝗮𝘁 𝗦𝗰𝗮𝗹𝗲 hci.ucsd.edu/orca w/@HaijunXia
🌸 #CHI2025 meetup! At CHI'24, we had an informal meetup for folks into dynamic abstractions and more. Since then: UIST'24 workshop, reading group, and Discord chats. This year, we'll have small-group lunches on Mon 4/28. Add your name by Sun 04/27: shorturl.at/QZ3Cw 🧵
Want to reimagine how we interact with computers in the age of AI? And excited about ... 🪜 #abstraction_ladder, 🌊 #dynamic_medium, 🔣 #notations, and 🔀 #diagrams? 🌴 Join us for Monday (05/13) lunch at #CHI2024! shorturl.at/noxU1 🚀 Learn more: dynamicabstractions.github.io
🎥 New Talk: “Generative, Malleable, and Personal User Interfaces”. This talk describes our work toward the long-held vision in the field of human-computer interaction. Talk Link: youtu.be/MbWgRuM-7X8 We are committed to making it as real as we can.
💼 I'm on the job market for tenure-track faculty positions or industry research scientist roles, focusing on HCI, Human-AI interaction, Creativity Support, and Educational Technology. Please reach out if hiring or aware of relevant opportunities! RT appreciated! 🧵 (1/n)
My team will present a few papers and demos on LLM, UI composition, creativity support, and more at #UIST2023! Details on creativity.ucsd.edu Looking forward to learning and discussing exciting future research directions related to HCI & AI. See you in SF soon!
After an amazing year at @DesignLabUCSD, working with @HaijunXia and forging friendships @UCSanDiego, I've joined @ToviGrossman's group in the DGP Lab @UofT as a postdoc. I'd like to thank @HaijunXia and @DesignLabUCSD members for the wonderful friendships and memories. (1/4)
Can generative models replace designers' reference search tools? Why not harness the power of both! 🔮GenQuery supports three generative features that allow users to express their visual search intents more easily (🎞️➡️🧵) 🔗 genquery.kixlab.org (1/n)
Why manage windows when you can manage content instead? We demonstrate Masonview, a desktop environment that lets you do just that. Come try it out at the #UIST2023 demos!
Graphologue is now open-source - Learn more about inline annotations and how we built interactive diagrams in our GitHub repo github.com/ucsd-creativit…. Also, check out the LIVE DEMO here at graphologue.app. See you at #UIST2023!
📢 Looking for participants for a 1-hr Zoom study on online decision-making situations! 🙋♀️ Participants above 26, who are familiar with making decisions online 💰 $15 Amazon Gift Card for compensation Details at: docs.google.com/document/d/1Gc… Sign up here! forms.gle/1dmq5Yy5xmmgFd…
If LLMs can change how we write, shouldn't our writing interfaces change as well? 🤔 We propose a design framework that conceptualizes how interfaces can represent LLM inputs, parameters, and outputs as interactive objects: Cells, Generators, & Lenses 🟦
Tons of LLM-powered apps are built but few help users fluidly "experiment & iterate" w/ various configurations, limiting usability & utility. In our upcoming #uist2023 paper we introduce "Cells, Generator, & Lenses", a design framework for LLM apps to easily add this support. 1/3
Excited to share #Sensecape - an interactive system that lets you explore complex information using LLMs in a 3D space.🚀 Unlock new levels of understanding and decode relationships between information.🔍 Stay tuned for details and updates. Full video at creativity.ucsd.edu/ai
What if #ChatGPT were 3D? Structure #GPT4's responses in 3D with #Sensecape to better understand large amounts of text. New Human-Computer Interaction #HCI research makes #AI easier to use. More at creativity.ucsd.edu/ai.
Excited to share #Graphologue - with interactive diagrams, it unleashes the power of LLMs with real-time inline annotations, self correction, prompting through actions, and more! Stay tuned for details and updates. Full video at creativity.ucsd.edu/ai
Stop reading the text !!! Have a graphic dialogue with OpenAI’s #GPT4 with #Graphologue. It turns GPT4-generated text into interactive node-link diagrams in real-time. New Human-Computer Interaction #HCI research makes #AI easier to use. More at creativity.ucsd.edu/ai