Finding videos on my Mac Pre-AI: Type name of file into search, click on video Post-AI: Type name of file into search, no results. Try a few permutations, nothing. Open finder, type filename into search bar, nothing. OPEN DAVINCI RESOLVE, find project with video, click reveal in finder.

Dog walks through open gate. Branded existential thread to humanity. News at 11.

Eryk Salvaggio@eryk.bsky.social · 3w ago

Really important to note that in no way shape or form did Anthropic’s models in this incident “escape containment,” and not just in the word-policing sort of way. The model stumbled through an open, misconfigured gap. From Anthropic’s incident report:

The talk I presented at #SIGGRAPH2026 is now available on YouTube, for anyone who couldn’t attend or would like to revisit it :) youtu.be/OFJYBUArVPc?...

Dual Contouring of Signed Distance Data - SIGGRAPH 2026 [Technical paper presentation]

YouTube video by Xiana Carrera

youtu.be

Xiana Carrera@xianacarrera.bsky.social · 2mo ago

1/6 Excited to share our #SIGGRAPH2026 paper, Dual Contouring of Signed Distance Data! We propose a new method for reconstructing sharp meshes from discrete samples of signed distance functions (SDFs) that does not require gradients. Project page: gatc.cs.columbia.edu/projects/dua...

Casual observation backed up by no data (yet). Lots of people I work with are using coding agents to write lots of code but so far producing the same amount (or less) of useful output (papers, products, shippable features) Cost of token maxing looks bleak unless you count half working demos.

you might wonder why I am posting edited quotes from reviews lately. Well to quote Popeye:

“<blocked> cannot be a technical contribution as this modification could be used by previous work to achieve the similar results” Dear reviewers, if a paper proposes a new modification in the present that would also improve algorithms from the past, it is indeed a contribution.

Pivot to subterranean AI data centers in 3,2 …. You’ve heard of Deep Learnjng but this can be DEEP Learning

TechCrunch@techcrunch.com · 4w ago

Elon Musk's tunneling startup is reportedly in talks for a major new funding round.

"For example, incorporating <blank> into <blank> or <blank> is a well-established idea in the <blank> community and should not be presented as a novel contribution..." Dear Reviewers: Be evidence-based.If you write this but provide no citations then maybe <blank> isn't that common.

Cool to see some nice follow up work on this stuff. When we published this paper a reviewer said it had no useful purpose and now we are getting flamed on Bluesky. Take that R3 :)

ponder@ponder.ooo · 4w ago

your teeth: - discontinuous - full of holes - straight up spongiform - also a weird blobby one my tooth: - just a normal tooth lol

At SIGGRAPH 2026 I saw this absolute banger of a paper by James and James. Beautiful imagery, matched by beautiful technical work, by a father and son team, which won a best paper award. I've always loved marbleization patterns. dougjam.github.io/mixwell-2026/ www.linkedin.com/feed/update/...

We have the same hobby :) Love seeing these kinds of tests. Time for DeepMind to put out another paper claiming VFMs are one shot physics learners 🙄

Tomer Ullman@tomerullman.bsky.social · last mo.

every time there's a new video model I try some basic physics on it. So, here's the recent Google Omni tasked with continuining an image of a man throwing a mug at a tower of skulls. will the mug hit the skulls? see for yourself.

Fun poster at #SIGGRAPH2026 with incoming PhD student Yixin Lok. Sadly the paper is there but Yixin isn't due to visa issues.

After some encouragement from various people I decided to make a GitHub repo for my ongoing Newton's Cradle benchmark of Google's Veo video model. All videos (spanning about a year) are available here for all your cradling needs: github.com/dilevin/newt...

@otmanon.bsky.social 's simkit has been supremely useful for a bunch of simulation tasks, not the least of which is using the many useful reduced-order parameterizations he's developed over the years. github.com/otmanon/simkit

GitHub - otmanon/simkit: Physics Based Animation Library

Physics Based Animation Library . Contribute to otmanon/simkit development by creating an account on GitHub.

github.com

Sheldon Andrews (profs.etsmtl.ca/sandrews/) is running for the ACM Executive Committee this year. I've known Sheldon for a long time and I think he will do a great job ! I voted for him, you should too www.acm.org/elections/si...

2026 ACM SIGGRAPH Election

Voting page for SIGGRAPH Elections

acm.org

<megaphone> The incredible @rishit-dagli.bsky.social took VoMP, his volumetric material predictor, and made it adaptive! This increases the detail of SimReady assets dramatically <see below>

rishit dagli@rishit-dagli.bsky.social · 2mo ago

What if we can take a few photos and turn it into an interactive physically realistic virtual world🌎? 📢Introducing AdaVoMP (ICML 26): generates volumetric physics fields at high spatial resolution making objects interactive and deformable🦾 🦣16^3x higher res (1024^3) ⚡️more accurate

I recently completed my PhD thesis, where I developed algorithms for making geometric inferences from imperfect data (i.e. incomplete and inaccurate observations/representations of shapes, like broken meshes or point clouds). A thread 🧵:

<megaphone> #SCA2026 News Deadline for submitting revisions of provisionally accepted papers has been extended to June 10th due to delays getting reviewer comments out to authors. computeranimation.org

Something something chickens something something home to roost

Ed Zitron@edzitron.com · 3mo ago

Today Microsoft moved all its GitHub copilot subscribers to token-based billing. If you want to see what happens when people have to pay the actual costs of AI, the day is finally here. It's obvious that every customer sees the deep, meaningful value and isn't angry at all.

New paper by the incredible Donglai Xiang (xiangdonglai.github.io) at CVPR 2026 using RKPM inside a data free training framework to compute reduced elastic models. Trains faster, works better than competing Neural Network approaches. Check it out: research.nvidia.com/labs/sil/pro...

I've been using github.com/Yixin-Hu/Tet... to mesh some truly crazy shapes and I am again reminded how amazing this software is and how much of my research it enables. Incredible.

One more great SCA keynote … Danny Kaufman of Adobe Research will talk about his foundational work in contact simulation and more! computeranimation.org/program.html

We have a fun new paper to appear at SIGGRAPH 2026, led by Columbia PhD student Xiana Carrera, that extends dual contouring to work nicely with [pure] signed distance samples. It avoids classic DC's additional requirement of providing accurate Hermite / […] [Original post on mastodon.acm.org]

The poster deadline for SCA is coming up on June 1st! Posters are a great way to be apart of SCA and let the animation community know about your new, hot off the presses research. computeranimation.org

More SCA Keynote news! Moritz Bächer, Lab Director of Disney Research Imagineering in Zurich, will be joining us ! If you've seen Disney's robotic Olaf and BDX Star Wars droids, you've seen Moritz's work in action. computeranimation.org/program.html

To everyone who submitted to SCA .. thank you ! We ended up with the second most submissions in 13 years !!!! Bad news - we have a hiccup releasing reviews back to you. We are working on it and our plan is to adjust the rebuttal deadline to compensate (once it's sorted). sca.graphics #SCA2026

Remember it's not too late to get on board with this. I think it's important to stand up for underrepresented people even in minor ways. You can always send your submissions to TOG which has a new EIC and new faster turn around times. #SIGGRAPHAsia 2026

Cem Yuksel@cemyuksel.com · 5mo ago

About 6 months ago, I publicly announced that I would be boycotting #SIGGRAPHAsia 2026. Today, I released a video explaining my rationale and calling on others to do the same, because I believe it is important. Here it is: youtu.be/bZ6s0-EQp8M

The wonderful Nicole Feng, defending her PhD thesis on generalized distances & winding numbers. So proud of her, and very excited about all the places she will go. nzfeng.github.io (Also that text outline shaded by the surface is some galaxy brain diagramming. 🤯🧠🌌)

What a twist !

Big SCA 2026 update! The incomparable A.M. Darke (news.ucsc.edu/2024/10/am-d...) will be one of our keynote speakers. Professor Darke is one of the leading voices on diversity in games and we are thrilled she will be joining us in Barcelona. computeranimation.org/program.html More news soon ...