#CVPR2023 is mostly posters this year, which is good! Poster sessions can be great. But a lot of people are not so great at presenting their poster. Here's some of the advice I give grad students when preparing for poster sessions.

“Make yourself be lucky!”- Alyosha Efros

Vision transformers need registers! Or at least, it seems they 𝘸𝘢𝘯𝘵 some… ViTs have artifacts in attention maps. It’s due to the model using these patches as “registers”. Just add new tokens (“[reg]”): - no artifacts - interpretable attention maps 🦖 - improved performances!

I've been told the traffic in Paris will be horrible, I didn't realize they were referring to the #ICCV poster session.

It in insane to me that F. Güney can get an EU research grant to fund her lab as a professor (very big deal) but cannot get a visa from the EU to come to a conference (should be a very small thing??!!!!!) Visa privilege is a real thing and smthg we don’t discuss enough in CV??l

Cartoon-like filter at the TikTok booth @ #ICCV2023

My lecture notes on regularization techniques in machine learning dropbox.com/scl/fi/ivyb3ws… Check out the section on double descent suggested by Yann LeCun :)

Here's a collection of my favorite #ICCV2023 papers on diffusion-based image editing. (1/4)

Silence on Gaza is no longer an option - after seeing those images, really seeing them, you still want to stay “neutral”, stay silent, or talk about “Islamist oppression” and “LGBT intolerance”, don’t call yourself a feminist. Because you are not one.

one of the most important things I know about deep learning I learned from this paper: "Pretraining Without Attention" this what I found so surprising: these people developed an architecture very different from Transformers called BiGS, spent months and months optimizing it and