Google Deepmind likes to publish one of these "can VFMs do physics" papers every so often. This year the conclusion is "not quite" last time the conclusion was "its promising"
Playing at home ? We're at best stuck and at worst going backwards.
video-zero-shot.github.io
physics-iq.github.io
Today’s the day ! Final paper submission deadline for SCA!
Let’s gooooo
sca.graphics
It's looking good for SCA 2026 ! If all the abstracts submitted are converted into full submissions it will be the most submissions to SCA in the last 10 years !!!!
Final submission deadline: April 17th
sca.graphics
<megaphone emoji>
Today’s the day ! SCA abstracts due by 23:59 UTC April 10th
Submit here: srmv2.eg.org/COMFy/Confer...
sca.graphics
Great thread! I also struggled (still struggle) with a lot of this stuff but Rook articulates it much better than I ever could.
And we're back !!!!! Submit those abstracts :)
Link: srmv2.eg.org/COMFy/Confer...
C’est la vie 😉
And it’s down again 😬
Will post when the issue is fixed (secretly hoping y’all crashed it with the volume of submissions)
For those submitting to SCA (sca.graphics) — the submission system (SRM) is back up after an outage yesterday.
Remember abstract deadline is tomorrrow :)
Submit here: srmv2.eg.org/COMFy/Confer...
agonizing over whether to fix that "for to" typo by deleting and reposting. Have decided to leave it there so you know I'm either the worst human writer or the best AI writer.
@rishit-dagli.bsky.social's amazing VoMP model is now available for to the people, including a fun demo on @hf.co. Check it out.
research.nvidia.com/labs/sil/pro...
Abstract deadline coming up fast (April 10)
Don’t forget to submit !!
And I also think the bbs discussion should be anonymized and made public so authors can really track the decision making process for their papers which can help target improvements for resubmission. Many summaries fail to outline the discussion in any meaningful way.
I’d much prefer a system where some of the reviews aren’t anonymous but that would require some care due to career implications especially for junior researchers
It at least allows us to analyze the reviews and get a real sense of of the system is working or not. Right now we don’t even have that.
That and I do think there’s some additional pressure to having even anonymous writing in public.
I’m just saying …
Effectively received a SIGGRAPH summary for a rejected paper that can be summed up as "waaaaaah don't show my open source simulation software has a failure case" 🫠
No love from #SIGGRAPH ? Submit those animation papers to the Symposium on Computer Animation computeranimation.org !
Abstract deadline: April 10th
Submission deadline: April 17h
Conference: Barcelona, Spain July 8th-10th
Be there!
SIGGRAPH needs to (at least) update its rebuttal policies in this regard. Reviewers ask for comparisons in reviews and cite them as reasons for rejection but unlike cvpr say, you aren’t supposed to put new results in a rebuttal. It technically gives reviewers an unaddressable avenue of criticism.
Last SIGGRAPH Asia and this SIGGRAPH have just been brutal. It feels like the ground shifted under my feet and all of a sudden I have no idea how to write a SIGGRAPH paper.
Called it.
@cemyuksel.com I’m with you, I definitely will not see you at SIGGRAPH Asia
No submissions, no reviewing, no service.
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
I guess every CS conference is a machine learning conference nowadays 🫠
Given my average SIGGRAPH review score vs those I've gotten in the last few months at ICLR, CVPR and ICML, I think maybe I do machine learning now ???
Our Rising Stars 2026 application campaign is currently open so we thought we would share some updates about our past rising stars 🌟 follow us in the next couple weeks to read more!
Learn more about the program and apply >> www.wigraph.org/events/2026-...
I dislike that people do this, I dislike that the academic career model forces people into this position but I also understand why it happens. I have no solutions to offer.
I think there’s a lot of career pressure. As a prof your external service counts towards your advancement and doing reviews leads to PC positions which are prestigious and help one’s career. Everyone’s busy, everyone feels they need these things, they end up short cutting it.
I emailed papersadmin@siggraph.org to avoid potential conflicts of interest. Let's see what the response will be.
Every one of my 3 #SIGGRAPH 2026 has one review (of four) that gptzero detects as 100% AI generated (not ai polished, or mixed, but 100% generated). 2/3 of those AI tagged reviews argue to reject the paper.