Ana Dodik
@anadodik.bsky.social
Graphics & Society @ MIT CSAIL. Prev. Meta, Disney Research. Yugo girl, mother of a half-dog, half-tornado, and a baby seal. 🐶🐶 she/her 🌈🌹
Charles Babbage intentionally designed the computer as an automation of mental labor. Today, computer graphics automates visual art production via privately governed generative models. How did we get here? Critical Labor History of Generative Models, SIGGRAPH Talks '26 🧵
I feel like you could make a fairly robust classifier of how old a SIGGRAPH paper is using the cost of ink required to print it as the only feature dimension.
Come to my talk at SIGGRAPH to find out what the field of Platform Studies says about generative models! "Critical Labor History of Generative Models" Tuesday, 5:05 PM, Room 403 A AI Reflections Session
Come to our Birds of a Feather if you are excited about working with (and not against) artists!
Emilie Yu@emxtyu.bsky.social · 2mo agoHow can we design tools for visual production that use novel techniques to support human creative processes rather than supplant or degrade them? At #SIGGRAPH we invite researchers and practitioners to come to our Birds of a Feather session about co-designing computer graphics technologies!
Next week at #SIGGRAPH2026, we'll present "Fast Sparse Matrix Permutation for Mesh-Based Direct Solvers," with Behrooz Zarebavani, Ana Dodik, Changcheng Yuan, Serban Porumbescu, John Owens, Maryam Mehri Dehnavi, and @justinmsolomon.bsky.social . Talk: Wed., July 22, 3:55 PM, Room 403-B (1/6)
Next week at #SIGGRAPH 2026, we'll present "Locality-Aware Automatic Differentiation on the GPU for Mesh-Based Computations," with Rahul Goel, Jonathan Ragan-Kelley, and @justinmsolomon.bsky.social . Talk: Mon., July 20, 2:50 PM, Room 403-B Paper: dl.acm.org/doi/10.1145/... More below (1/7):
"Attention is just XYZ". Attention is actually a Rorschach test for researchers.
There's no way this VAR thing is accurate enough to catch someone being offside with their knee, right? Almost certain there are no body pose estimators that precise in such uncontrolled conditions. Why aren't they integrating uncertainty in the estimates?
If you're at FAccT, I would love to grab a coffee with you! Just shoot me a message.
Arrived to beautiful Saint Malo for the Curves and Surfaces conference! Let me know if you wanna chat about curves OR surfaces. Or heck, even volumes, why not, let's get nutty with it!
We are excited to announce the 2026 cohort of Rising Stars in Computer Graphics 🌟 These 9 young researchers will participate in a workshop at Siggraph 2026, about the wide range of career trajectories in graphics. Thank you to all applicants and to our selection committee for all the hard work.
"Coding Models Are Doing Too Much" nrehiew.github.io/blog/minimal...
Coding Models Are Doing Too Much | wh
nrehiew.github.io
Wish there was a way to donate the SIGGRAPH conference registration discount to help bring in more folks from underrepresented communities if none of the authors can make use of it. I have two that are about to go to waste :(
Been playing around with vibe coding for a few days and it really takes away any joy building software had. It's awe inspiring how quickly it can get something going, but after that point it's just a slog. Feeling depressed about the whole enterprise and the world broadly after the experience.
Puzzled by the trend in the humanities of picking and hyper fixating on one mathematical component of Gen AI and reading into it like tea leaves. In an attempt to demystify models, they mystify themselves with the math. Mathstification, if you will.
I hope we'll all wake up from this fever dream one day soon.
This DLSS stuff is what you get when you view art as a metric to optimize, when you reify the most human of endeavors into a force of nature to be studied, to be dominated. You cannot fix another person's art because art isn't a number in a table to improve upon.
Chugging water at the airport water fountain to help eliminate waste from as many plastic bottles as I can.
EGSR 2026's call for papers is out: egsr2026.inria.fr/call-for-pap...
Call for papers – EGSR 2026
egsr2026.inria.fr
In the era of AI generated review slop, you really learn to appreciate the hand crafted artisanal low-effort reviews.
The Symposium on Computer Animation is Coming! BARCELONA, SPAIN. JULY 8 - 10, 2026! Papers Abstract Deadline: April 10, 2026 Poster Deadline: June 1, 2026 Website: sca.graphics Call for papers : computeranimation.org/instructions... Barcelona > LA (Come on: en.wikipedia.org/wiki/Sagrada...)
The 25th annual Symposium on Computer Animation (SCA) will take place in Barcelona, Spain, from July 8 to July 10, 2026.
sca.graphics
One of our dogs starts barking like crazy if someone knocks on anything and I've realized I have developed a stress response any time I hear a knock now, even when she's not around. I think my dog inverse Pavloved me.
The ACM Digital Library, where a LOT of computing-related research is published (I'd say at least 75% of my own publications), is now not only providing (without consent of the authors and without opt-in by readers) AI-generated summaries of papers, but they appear as the *default* over abstracts.
newspaper covers were the original clickbait
Thor Benson@thorbenson.bsky.social · 9mo agoI guess it's fitting that it's a reimagined, worse version of someone else's artwork
Catch me talking about Meschers at the NeurIPS @neur_reps workshop! anadodik.github.io/publication/meschers
Tired of senior folks dragging people's posters on socials. Has contentification cooked our sociality so much? Consider alternatives: 1. In-person feedback. 2. Broadly construed feedback. 3. Make resources. 4. Post positive examples. 5. Censor the name. 6. Laugh about it in a groupchat if you must.