Kosta Derpanis

#CS Associate Prof @YorkUniversity, #ComputerVision Researcher, @VectorInst Affiliate, @UofT status only, @ELLISforEurope Member

[Kosta Derpanis @CSProfKGD]

I’ve launched 2 new course websites for my Introduction to #ComputerVision and #DeepLearning in Computer Vision courses.

🆕 Gaussian Splatting
🆕 Flow Matching
🆕 Sparse Autoencoders
🆕 Lecture Notes (work in progress)

The videos don’t include voiceovers, but that’s coming in a future revision 🤞

Share your feedback in the thread.

[Kosta Derpanis @CSProfKGD]

@menhguin I was waiting for that 🤓

[Kosta Derpanis @CSProfKGD]

@letyrodri 😅

[Kosta Derpanis @CSProfKGD]

@PlisSergey @ieee_mlsp Hotlanta is very tempting 😉

[Kosta Derpanis @CSProfKGD]

@roeiherzig @HildeKuehne Appears to follow the lottery logic that you have to play to win. People have lost their sense of holding back incomplete or ill-fitting work.

[Kosta Derpanis @CSProfKGD]

@YuXiang_IRVL @RoboticsSciSys From one publicity chair to another: thank you for your service 🫡

[Yu Xiang @YuXiang_IRVL]

Nice milestone for @RoboticsSciSys: 10K followers!

Glad to have served as Publicity Chair for RSS 2026 and helped share the exciting work from our community. Now it’s time to hand the account over to the next Publicity Chair. Looking forward to seeing RSS continue to grow!

[Kosta Derpanis @CSProfKGD]

@bibek_poudel_ 😂

[Kosta Derpanis @CSProfKGD]

I predict a crime spree is coming.
Nothing stolen, just random #ICLR2027 submissions left behind. Stay vigilant 👀

[Georgia Chalvatzaki @GeorgiaChal]

https://t.co/yGjRDKdY0q

[Kosta Derpanis @CSProfKGD]

@LucaAmb Trend setter 😅

[Kosta Derpanis @CSProfKGD]

@HildeKuehne @roeiherzig It’s going to be a BIG number, even dropping the 3k and the abandoned IDs.

[Kosta Derpanis @CSProfKGD]

@PavanBuilds … and authors! The pool is not deep enough of topic experts to support this number.

[Kosta Derpanis @CSProfKGD]

We’ve entered the first full conference cycle with capable AI agents.

Submission numbers at AI conferences are going to be scary 😱

[Jonathan Schlosser @jonathanschloss]

Seeing numbers of ~50k submissions for @iclr_conf. That's insane!

Yes, probably a lot of AI papers. And yes, it'll probably need AI review at that scale. But @NeurIPSConf just ran into this exact wall, and the results were... interesting.

Based on some blogs that have come out, NeurIPS screened all 969 submissions through an AI detector. Out of those, 42.7% of submissions initially scored in the 90-100% AI-generated range, and 273 papers hit a full 100%. The chairs re-ran it with a narrower text window and that number dropped to 12.7%. Same papers. Same tool. One settings change, and the flag rate fell by 70%.

Resultantly, 178 papers were desk-rejected with no appeal and 123 were told to produce version histories or also be desk-rejected. Then a rejected author ran the track chairs' own recent papers through the same detector and got back ranges from 24% to 69% of AI-generated content.

That's with 969 submissions.

Now let's consider ICLR. There are reports that people's submission numbers are getting real close to 50k. The one that I saw plainly stated was 47647.

Compared to last year, there were 19,525 valid submissions to ICLR, with 779 desk rejected and 5,042 withdrawn. This left 13,763 papers that needed a decision.

To do this, ICLR organized 76,139 reviews from 18,054 reviewers. They also ran their hallucinated-reference checks through at least three humans per flagged paper before any desk rejection, putting in a check to any AI review processes.

Now what is this going to look like with a potential 2.5x jump in volume?

At ~50k submissions, ICLR is definitely going to have to use some AI review processes, but can the human-review layer scale as well, or is it something that may end up getting dropped?

This is speculation at this point, and is based solely on the abstract submissions so far, but the final paper deadline is Sept 25th, and it will sure be interesting how this all plays out.

If you want some advice though, maybe save your drafts, keep your version history, and be specific about any AI use in your attestation. That could come in handy if you get a rejection...

Anybody have thoughts here? Gonna be an impressive feat nonetheless. 🤔

NeurIPS Info: https://t.co/heCi0dAZvU
ICLR Info: https://t.co/eXY5mwUhUA
ICLR Conference Page: https://t.co/ajHoQG6dTY
Graph: https://t.co/Q1eVrsIIJE

[Sander Dieleman @sedielem]

Retweeting this now that Jev is making waves! This is really worth a watch to understand the motivation behind it (and also for the hot takes 🤭)

[Sasha Gusev @SashaGusevPosts]

interesting reversal happening where typos are now a sign of effort

[Kosta Derpanis @CSProfKGD]

@roeiherzig Let’s keep in mind these are paper ids not real submissions yet! Includes many “double submissions” from NeurIPS. But yes, I expect a GIANT number 😱

[Kosta Derpanis @CSProfKGD]

@HamidRezatofigh Or start a new agent focused conference and watch from the sidelines.

[Kosta Derpanis @CSProfKGD]

Winter is coming 😢 #Toronto

[Kosta Derpanis @CSProfKGD]

@y_m_asano These periodic reminders are important. Strong research needs a strong mind and body 💪

[Kosta Derpanis @CSProfKGD]

@y_m_asano I support this initiative!