Come check out our work on LightShop, which will be presented by @gfxptr and Andrew Arena in the 11am session today at #UIST2026! We build an interactive tool for super high precision computational light painting!
Excited to share LightShop (UIST 2026)! We created an interactive, computational system that enables the creation of high-precision light paintings.
What makes it really neat is that it combines light painting's physically accurate lighting with computational precision.
Come see Chao's talk on Narrative Keyframing in the Authoring w AI session Tues 11am @ #UIST2026!
We create a system that lets you keyframe generative prose the way you would an animation. You can use keyframes to control plotlines, character arcs, and narrative perspective!
Excited to share 𝘕𝘢𝘳𝘳𝘢𝘵𝘪𝘷𝘦 𝘒𝘦𝘺𝘧𝘳𝘢𝘮𝘪𝘯𝘨, a new interaction technique for AI-assisted creative writing! #UIST2026
It’s inspired by a familiar idea from animation: 𝘬𝘦𝘺𝘧𝘳𝘢𝘮𝘪𝘯𝘨. (1/5)
Check out @megatran23's talk tomorrow at #UIST2026 on MicroEdits (Best Paper Honorable Mention 🏆), w Mackenzie Leake and Valentina Shin!
We look at a type of video editing that human experts do much better than AI, and build a human-AI tool to make exploring these edits easier!
Excited to share MicroEdits (#UIST2026 Best Paper Honorable Mention 🏆) from my @AdobeResearch internship with Mackenzie Leake, Valentina Shin & @AbeDavis (@CornellCIS).
AI can make rough cuts, but fine-cut editing still takes time and skill 🧵 [1/n]
🔗 https://t.co/eWcx8AXE6f
Come check out papers from our group at #UIST2026 ! @zhangchaodesign will show Narrative Keyframing @ 11:20am Tues, @megatran23 will show MicroEdits @ 4pm Tues (*Best Paper Honorable Mention!*), and @gfxptr + Andrew Arena will show LightShop @ 11am Thurs!
https://t.co/2ElvIgFpDc
AI often decouples knowledge—which is about access to information—from understanding—which is about mastery. There is danger in settling for the former when what one needs is the latter. Understanding is harder to gain and quantify, but ultimately much more important.
If you ask Claude to “identify any potential issues or opportunities for improvement” in your old code, be prepared for an unnecessarily judgmental response. It’s like, “we get it Claude, you know how to implement a serializer…” 🫷🙄���
AI in creative writing raises a lot of complicated questions, including what meaningful human creative control should look like. Our #UIST2026 paper on Narrative Keyframing led by @zhangchaodesign explores this with inspiration from classic automation strategies used in animation
Excited to share 𝘕𝘢𝘳𝘳𝘢𝘵𝘪𝘷𝘦 𝘒𝘦𝘺𝘧𝘳𝘢𝘮𝘪𝘯𝘨, a new interaction technique for AI-assisted creative writing! #UIST2026
It’s inspired by a familiar idea from animation: 𝘬𝘦𝘺𝘧𝘳𝘢𝘮𝘪𝘯𝘨. (1/5)
I know a lot of people were hoping @taylorswift13 and I would date so we could find secret messages about Noise-Coded Illumination and Interactive Explainable Ranking in her next album, but she seems happy with her new beau and I really think we should try to support them...
@jon_barron This feels like very specific advice for people writing a very specific type of paper… I also don’t think “stop listening to your advisor” is ever really a good strategy. You don’t always need to do what your adviser says, but it’s generally a good idea to listen.
Feature in the Chronicle about our work on Interactive Explainable Ranking, which won a Best Paper Award at #CHI2026! We use optimization, AI, and interaction design to help people make more explainable and consistent decisions. Huge congrats to first author @zhangchaodesign!
A new AI tool, Interactive Explainable Ranking, developed at @Cornell_Bowers, is designed to help users rank a set of choices – job applicants, graduate schools, even Oscar candidates. VIDEO @acm_chi@AbeDavis@CornellGrad https://t.co/ZJlCv6lESS
Come check out our papers at #CHI2026 this year!
- "Narrix" | Thu, 16 Apr | 9:00 AM | P1 R127
- "Interactive Explainable Ranking" *Best Paper Award!* | Thu, 16 Apr | 11:15 AM | Area 1+2+3 Theatre
- "CineCraft" | Fri, 17 Apr | 9:48 AM | P1 R128
More on each project to follow!
Honored to be named a Sloan Fellow! So much gratitude for all of my collaborators and others who have supported me! And, of course, a very special thanks to my amazing research group! I am so fortunate to work with such awesome students! #SloanFellow
Congrats to the 126 early-career scholars awarded a 2026 Sloan Research Fellowship, whose creativity and innovation set them apart as the next generation of scientific leaders! Our Fellows represent 7 fields and 44 institutions across the US and Canada.
https://t.co/8ENNQ2s6Ov
@MattNiessner Clear dissemination is part of scientific merit, and what is a paper if not text and visuals?
LLMs tend to polish by misrepresenting, which should not be confused with good presentation. Academic slop has mostly just raised the noise floor and made good science harder to do.
@jon_barron Ok, but does this factor in the cost of all those unplayed games sitting in people’s Steam library that were purchased on sale because “surely I’ll have time to play that, someday…”?
AI is powerful, but its biggest impact so far has been to erase *useful* friction: proof-of-work we used to assess candidates, curate content, confirm (human) learning, and make fraud harder to scale. "AI slop" is a cute term for something with potentially terrifying consequences
@IanArawjo It's very hard to raise the bar of a publication, so when new tools makes it easy to meet old standards, you get a lot of obvious, opportunistic papers. Criteria like "was this interesting?" or "did I learn something?" are often tragically under-valued in reviews...
Come see our talk on "Pocket Time-Lapse" at SIGGRAPH today at 4pm in the Image Representation, Editing, & Generation session!
West Building, Rooms 118-120.
With @zzigakovacic , @madhavaggar and @AbeDavis