Lydia Chilton

Computer Science Professor at Columbia

[Lydia Chilton @LydiaChilton]

AI has the surprising ability to discover abstract structure from examples. We use this for schema induction, but it can do so much more: find themes in data, discover templates, and generate design patterns. If you're working on structure discovery, pls msg me your ideas/work!

[Sitong Wang @sitong0926]

🧩 How do we go from examples to structural insight?
🎭 Surface variation in real-world examples makes it hard to spot deeper patterns.
✨ Introducing Schemex: a system for discovering structure through interactive abstraction & contrastive refinement.
📄https://t.co/2NZCFpAXQL

[Sitong Wang @sitong0926]

🚨⚠️Recently reviewed a paper that copied my CHI '24 work, ReelFramer https://t.co/XzkGGnUwLT, almost word-for-word. And they even cited ReelFramer! 😱
A friend mentioned they came across a similar situation. Is this common? What should the community do to prevent such incidents?

[Lydia Chilton @LydiaChilton]

Thanks, everyone. I'm very grateful to have gotten a Sloan Fellowship. But I also know how frequent and awful rejection is. Here is my rejected Sloan Research Statement (2023), and my awarded research statement (2025), and the difference between them: https://t.co/h3ugicWTd1

[Lydia Chilton @LydiaChilton]

@jeffbigham @plopesresearch @msbernst @merrierm @mitchellgordon @joon_s_pk @SaleemaAmershi I'm game :)

[Sitong Wang @sitong0926]

✨ Excited to introduce our #CHI24 work - *ReelFramer*: a system that transforms traditional news articles into engaging, narrative-driven IG Reels/TikToks - both fun and informative!
How does ReelFramer tackle this content retargeting challenge? 📰🔄🎥

[Michael Bernstein @msbernst]

Unlike typical SIGCHI workshops, UIST workshops will be open enrollment — limited spaces, first-come, first-served. There is no position paper. Just make sure to register early before it fills up.

Co-organizers: @joon_s_pk @merrierm @SaleemaAmershi @LydiaChilton @mitchellgordon

[Nicholas Diakopoulos @ndiakopoulos]

Here’s @savvas_petridis presenting AngleKindling at #chi2023 — for an overview of the work see here https://t.co/keqpWFYV9k

[Tao Long @CHI2026 @taolongg]

📖✍️⏳🫠 A writer sits in front of the desk for hours and then opens an AI writing tool 💻👀🙋‍♂️Feeling related? Ever wondered WHY??

See our #CHI2023 paper on the Social Dynamics of AI Support! How do writers perceive these tools? What leads to their usage? https://t.co/Cx1k0QEXVq

[Vivian Liu @viv_lavida]

🪩 Generated Disco helped express meaning through transitions in color, subject, style, time. Video could hold around certain images to encourage consistency + visual emphasis.

🎵 - Empire State of NY - Alicia Keys

Arxiv: https://t.co/VbQVdgTqb9 Youtube: https://t.co/Len9L7CNuW

[Sitong Wang @sitong0926]

📰🎥📈 Can AI help make news into TikTok videos? Introducing ReelFramer: co-creating “news reels” with GPT and DALL-E!
Arxiv: https://t.co/7GJ8WNx7Wx
Preview:

[katy ilonka gero @katyilonka]

After years of building writing support tools, I've always wondered why some people loved them (even when they're bad!) & others disliked them no matter what.

That's why I ran this study which is out with #CHI2023:

"Social Dynamics of AI Support in Creative Writing"

🧵

[Vivian Liu @viv_lavida]

🪩 Generative Disco is one of the first to explore human-computer interaction problems surrounding text-to-video systems and assist music visualization through generative AI.

Here are examples: 🎵 - Clair de Lune

Arxiv: https://t.co/VbQVdgTqb9 Youtube: https://t.co/OxWfHhpvUq

[Sitong Wang @sitong0926]

Wanna make a Star Wars-themed product ad, but don't know how? 🤔
Introducing *PopBlends*, an LLM-driven system that tackles this creative challenge and gives your ad an edge.
But can LLMs be creative on their own, or do they need help? See what we found in our #CHI23 paper... 🧵

[Vivian Liu @viv_lavida]

Videos are created by warping between start and end generations to the frequency of music. Disco builds on @_nateraw's brilliant stable-diffusion-videos repo.

🎵 - One More Time - Daft Punk

Arxiv: https://t.co/VbQVdgTqb9 Youtube: https://t.co/OxWfHhpvUq

[Nicholas Diakopoulos @ndiakopoulos]

Are you a journalist that has lots of press releases in their inbox? (I know, all of you!). Here's some new research on how generative AI can help brainstorm reporting angles on them: https://t.co/keqpWFYV9k

[Vivian Liu @viv_lavida]

@_akhaliq 💃 🪩 🕺🏻 introducing generative disco, a text-to-video system for music visualization.

thank you to collaborators 🌷 @taolongg @_nateraw @LydiaChilton

arxiv: https://t.co/XuiuEkVtRo youtube: https://t.co/OxWfHhpvUq

[Lydia Chilton @LydiaChilton]

Join the Grad Student Symposium at Creativity and Cognition 2023. Present your work, get feedback, meet like minded researchers, have fun! Submissions due April 13 AoE https://t.co/8FI9AVEJUr

[Nicholas Diakopoulos @ndiakopoulos]

Generative AI is a potentially powerful tool to help illustrate news articles and visually draw in readers. Check out @lydiachilton's new primer on how to get started: https://t.co/1qL5Ks827d

[Nicholas Diakopoulos @ndiakopoulos]

Here's how to start using Dall-E and Midjourney to help with news illustration: https://t.co/1qL5Ks827d