I still post here because so much of my community is still here. But I urge you to try elsewhere, we need critical mass in a place that doesn't thrive on spreading hate and threatening freedom and democracy. I'm on all the other main sites with the same username, details below

Wednesday, November 5th at 11 AM CT: TTIC's Distinguished Lecture Series presents Aaron Hertzmann of Adobe Research with a talk titled "Can Computers Create Art?" Please join us in Room 530, 5th floor.

Here's a recording of my talk on how perspective works! If you're interested in learning about how picture perspective works in human vision, this is the video to watch. https://t.co/Mnb98GLaOc

Wrapping up our first Drawing & Sketching workshop at #SIGGRAPH2025 🙌! Thanks to everyone who joined us. We were thrilled to see so much excitement for this field! Huge thanks to our interdisciplinary line of speakers for sharing their valuable insights. See you next year :)

I'm very excited to announce our #SIGGRAPH2025 workshop: Drawing & Sketching: Art, Psychology, and Computer Graphics 🎨🧠🫖 🔗 https://t.co/iagFGSxMrZ 📅 Sunday, August 10th Join us to explore how people draw, how machines draw, and how the two might draw together! 🤖✍️

This week at @CVPR , we present the paper with my favorite acronym: MaDCoW, for rendering wide-angle photographs without marginal distortion. Details: https://t.co/LwFFLooQt9

🖌️ On creativity (6/19, 11am-12pm PT): @AaronHertzmann @manishsaggar & Aaron Kozbelt Register here: https://t.co/v2VeZYT8NC

I'm excited to announce publication of our new paper that can help answer age old questions of perspective in art history and #visionscience .

📺Now available: Watch the recording of @AaronHertzmann's talk, "Can Computers Create Art?" on YouTube: https://t.co/1ze7BVwgyt @UofTArtSci

Meet us at the intersection of creativity and AI. Join us on April 1 for, “Can computers create art?” with @AaronHertzmann of @AdobeResearch & @uwcse as part of the C.C. "Kelly" Gotlieb Distinguished Lecture Series. Register to attend: https://t.co/RXKvEWraQh

a view from my latent window: is it spring yet? #thisviewdoesnotexist ™

Generative models create an image inspired by the training data. But which training data are used to synthesize an image? Our #NeurIPS2024 work attributes a generated image to influential training data -- by unlearning *synthesized* images. Page: https://t.co/3viIXACzce 1/7

There appear to be orange and magenta spirals, though they are the same red.

Advice to beginning grad students: The Secret of Happiness Story [Sufi, Turkey]. Nasrudin is known as much for his wisdom as his foolishness, and many are those who have sought out his teaching. One devotee tracked him down in the marketplace. 1/3

6 years ago, in the days of GAN art, I wrote an article called "Can Computers Create Art?", arguing that computers should not be considered artists, regardless of how good image generation gets. Over on B***s***, I've posted a thread about how my views have and have not changed.

There are numerous leaderboards for AI capabilities and risks, for example fairness. In new work, we argue that leaderboards are misleading when the determination of concepts like "fairness" is always contextual. Instead, we should use benchmark suites.

This, from @marielgoddu, @alvanoe and @evantthompson's "LLMs don’t know anything: reply to Yildirim and Paul".

So far, BlueSky seems most promising. Mastodon has too much friction and Threads is mostly click-bait. But I do prefer an open platform (Mastodon) on principle.

I still post here because so much of my community is still here. But I urge you to try elsewhere, we need critical mass in a place that doesn't thrive on spreading hate and threatening freedom and democracy. I'm on all the other main sites with the same username, details below

This halloween I was the intersection of Art & Technology

Here are some observations about perspective in my own paintings. https://t.co/qZFuc8NwPh