Janet Yi-Ching Huang

Assistant Professor at TU/e, Human-AI Co-Learning, Crowdsourcing, Creativity & Learning Support, CSCW.

[Janet Yi-Ching Huang @janetyc]

My PhD student, Peng-Kai Hung, did a great job on presenting our work today :) GAI as a playful yet offensive tourist! #CHI2025

[Janet Yi-Ching Huang @janetyc]

If you're exploring the role of Generative AI in design, especially in public or urban contexts, we’d love to meet and exchange thoughts. Looking forward to seeing familiar faces and making new connections! 🥰
(4/4)

[Janet Yi-Ching Huang @janetyc]

🎉 Our paper, "Generative AI as a Playful yet Offensive Tourist: Exploring Tensions Between Playful Features and Citizen Concerns in Designing Urban Play," will be presented at #CHI2025 on Tue April 29.

preprint: https://t.co/FRJuqoU9Xf
(1/4)

[Janet Yi-Ching Huang @janetyc]

Our findings reveal the dynamic relationship between users, GAI, and urban spaces---showing how generative AI can enable playful urban experiences through generative agency, meaningful unpredictability, social performativity, and sometimes provocative or offensive elements.
(3/4)

[Golan Levin @golan]

Announcing p5.plotSvg — a new plotter-oriented SVG export library for @p5xjs! p5.plotSvg makes it easier than ever to generate vector files specifically tailored for pen-plotters like those from @bantamtools! https://t.co/jOXu1FKdum #creativeCoding #generativeArt #plotterTwitter

[Janet Yi-Ching Huang @janetyc]

@HariSubramonyam @JoelChan86 @imadityav @arvindsatya1 Thank you Hari for sharing this note!!! 🙏

[Janet Yi-Ching Huang @janetyc]

My phd student, Mihnea Calota, will attend #CSCW2024 next week and present our recent work as a poster. We are exploring collaboration and data sensemaking in nurse practices for Remote Patient Monitoring. :) Reach out him to know more!!

pre-print: https://t.co/yxQdgGp9uY

[Jon Friedman @designjon]

There’s a new editorial hub for #design at #Microsoft 🎉 https://t.co/MVZNLSYIMO

Make sure to check it out and let us know what you think ⬇️

[Mathias Funk @matsfunk]

Do you want to improve the lives of patients and medical doctors? Do you want to use your design skills or your software concept development skills to co-create the future of healthcare? 🌟 #hiring

[Janet Yi-Ching Huang @janetyc]

#2: AI Cat Narrator

This project introduces AI Cat Narrator, a new tool that can offers a unique perspective on the shared lives of humans and cats. This tool enables a co-exploration practice among humans, cats, and AI.

pre-print: https://t.co/hcEBg1czut

#DIS2024

[Janet Yi-Ching Huang @janetyc]

On July, I will attend #DIS2024 conference to present two on-going projects. Both of them are good examples to showcase how generative AI can be used to explore "defamiliarization" as design materials.

#1: Re.Dis.Cover Place with Generative AI
#2: AI Cat Narrator

[Janet Yi-Ching Huang @janetyc]

#1: Re.Dis.Cover Place with Generative AI
This work explores how image-to-image AI can support playfulness, reimaginations, and rediscoveries of places through defamiliarizing and familiarizing cityscapes.

pre-print: https://t.co/0NZXNVtEhy

[Janet Yi-Ching Huang @janetyc]

My student, Jun Li Jeung, will be presenting our interesting exploration on personal reminiscing through LLM at #CHI2024 as a LBW. If you're interested in this, feel free to approach her for a discussion :)
(Regrettably, I won't be there this year.)
https://t.co/xZ7tdjZJKu

[jin @dankvr]

It totally works, only tested with a Sora sample video but making generative gaussian splats will be a thing: https://t.co/oVsLHwHXbF

[Nat Friedman @natfriedman]

Ten months ago, we launched the Vesuvius Challenge to solve the ancient problem of the Herculaneum Papyri, a library of scrolls that were flash-fried by the eruption of Mount Vesuvius in 79 AD.

Today we are overjoyed to announce that our crazy project has succeeded. After 2000 years, we can finally read the scrolls:
This image was produced by @Youssef_M_Nader, @LukeFarritor, and @JuliSchillij, who have now won the Vesuvius Challenge Grand Prize of $700,000. Congratulations!!

These fifteen columns come from the very end of the first scroll we have been able to read and contain new text from the ancient world that has never been seen before. The author – probably Epicurean philosopher Philodemus – writes here about music, food, and how to enjoy life's pleasures. In the closing section, he throws shade at unnamed ideological adversaries – perhaps the stoics? – who "have nothing to say about pleasure, either in general or in particular."

This year, the Vesuvius Challenge continues. The text that we revealed so far represents just 5% of one scroll.

In 2024, our goal is to from reading a few passages of text to entire scrolls, and we're announcing a new $100,000 grand prize for the first team that is able to read at least 90% of all four scrolls that we have scanned.

The scrolls stored in Naples that remain to be read represent more than 16 megabytes of ancient text. But the villa where the scrolls were found was only partially excavated, and scholars tell us that there may be thousands more scrolls underground. Our hope is that the success of the Vesuvius Challenge catalyzes the excavation of the villa, that the main library is discovered, and that whatever we find there rewrites history and inspires all of us.

It's been a great joy to work on this strange and amazing project. Thanks to Brent Seales for laying the foundation for this work over so many years, thanks to the friends and Twitter users whose donations powered our effort, and thanks to the many contestants whose contributions have made the Vesuvius Challenge successful!

Read more in our announcement: https://t.co/rUlrdGXBMs

[Kwon Ko @hyungkwonko]

Our paper about Vega-Lite dataset and NL dataset (e.g., caption, utterance, question) generation framework is accepted to #CHI2024. See you in Hawaii. Please refer to our dataset and paper: https://t.co/Pv9yljfCHp

[Sherry Tongshuang Wu @tongshuangwu]

Slides available! https://t.co/UNemViBi4F Thx everyone for coming and for all the fruitful questions! Online participants -- again very sorry for the poor/non-existent WIFI connection...We will try to post a recorded version afterwards, stay tuned!

[Martin Nebelong @MartinNebelong]

Here's a quick test of a new tool called Krea. It's like the Real-time latent consistency model tests I've done with my photoshop and Dreams creations, but instead in a single application with faster refresh rates and higher quality output. I find that it strays too far from the drawing, and the editor is still quite limited but it's interesting to see nonetheless. It's not too difficult to imagine tech like this built right into Photoshop.

And yes, I do know how to draw even if it doesn't show here 😅, I've been sculpting, painting and drawing for most of my life and I think it's exciting that tools like this will eventually help us break down some of the technical walls between our imagination and the visuals we create. And I'm not necessarily talking about drawing alone here because I don't see that going away as an art form, and I wouldn't want it to.

But a hybrid of different art forms merging into a new, immersive art medium where anything is possible. Want to change the camera angle of your painting? Sure, go ahead. Want to make an animation of moving the camera around and seeing the light change in the scene as you do?

In the example here, being able to move things around, change lighting and see it all reflected in the resulting image, is pretty amazing. Like a combination of the benefits of working in 3D, but with 2d tools.

The moving version at the end of the video was made using Runways Gen-2.

#art #ai

[Michael Bernstein @msbernst]

Spotlight talk slides from the #uist2023 workshop on interaction with generative AI are now online: