At #CVPR2026, 16,092 submissions underwent the review process (this number excludes papers withdrawn or desk-rejected during the review process). The program committee recommended 4,090 papers for acceptance, resulting in an acceptance rate of 25.42%.
21.02.2026 06:14 β π 11 π 4 π¬ 0 π 1
a volleyball player wearing a number 10 jersey
ALT: a volleyball player wearing a number 10 jersey
Christian, every time I mention android vs ios recently π
20.02.2026 22:43 β π 1 π 0 π¬ 1 π 0
Researcher morale after three rejections in a row
20.02.2026 22:37 β π 10 π 1 π¬ 0 π 0
Same here. My previous Android phone was tagging such numbers as potential spams and it was easy to just reject. No such service on iOS (at least not for free).
I donβt answer calls from unknown numbers anymore: if they really need me they call again or leave a voicemail.
20.02.2026 18:24 β π 2 π 0 π¬ 2 π 0
Energized and inspired after our annual meetup to brainstorm on new exciting ideas and plan the projects ahead of us this year!
As always this is an excellent occasion to fit (almost) the entire team in a single photo
20.02.2026 09:57 β π 11 π 1 π¬ 0 π 0
This year I'm teaching a new course on generative models for visual content (images, video, 3D, etc). It's mostly me rambling about recent papers, design choices I like/hate. The slides of the first lectures are here: davidpicard.github.io/teaching/
Use right arrow to navigate past the blank page.
17.02.2026 11:14 β π 34 π 9 π¬ 2 π 0
Yeah! I discovered lichess just recently as I was looking for some solutions for learning and practice with my 11yo.
15.02.2026 21:37 β π 3 π 0 π¬ 0 π 0
All the "you need to learn AI skills or you'll get left behind" things are patently nonsense. It's easy to use and only becomes easier to use over time. If there's skill it's in knowing what it does well and what is does poorly
14.02.2026 03:39 β π 307 π 17 π¬ 4 π 11
a man is laying on a couch and crying .
ALT: a man is laying on a couch and crying .
You caught me! Actually most of the times as AC I'm rather like that π
13.02.2026 21:39 β π 1 π 0 π¬ 0 π 0
Are any of the ACs getting the first impulse of ending their messages to late reviewers with "Thank you for your attention to this matter"? π
13.02.2026 09:59 β π 7 π 0 π¬ 1 π 0
Bluesky Map
Interactive map of 3.4 million Bluesky users, visualised by their follower pattern.
I made a map of 3.4 million Bluesky users - see if you can find yourself!
bluesky-map.theo.io
I've seen some similar projects, but IMO this seems to better capture some of the fine-grained detail
08.02.2026 22:59 β π 7152 π 2151 π¬ 656 π 4584
Hello nearest-neighbor! π
09.02.2026 09:39 β π 2 π 0 π¬ 0 π 0
An email found me, and I was well at the time.
03.02.2026 16:26 β π 19 π 2 π¬ 1 π 1
The ever increasing surge of verbosity.
Even authors are now more verbose than usual in message to ACs.
02.02.2026 22:34 β π 5 π 0 π¬ 0 π 1
And yet again for #ausopen
30.01.2026 19:28 β π 0 π 0 π¬ 0 π 0
Haha, I guess they use those non-formatted and messy references all the time on purpose to make sure I will never get to ask them to do that π
22.01.2026 21:31 β π 1 π 0 π¬ 0 π 0
yeah, but so convenient to just click on your google scholar plugin :)
22.01.2026 21:01 β π 0 π 0 π¬ 1 π 0
Yes, most often in fact. Now, other sources are not more accurate either, so you still have to check.
Changing `article={}` & journal={}` to `inproceedings={}` `booktitle={}` remains easier than parsing and deleting from other kB-sized bib entries
22.01.2026 21:00 β π 2 π 0 π¬ 0 π 0
still, google scholar does the shortest exports out of all (fairly easy to check & minimize further for the paper).
compare that with bib entries that my students find: some go to give you the street name of the conference venue and the names of the parents of the program chairs π
21.01.2026 23:47 β π 7 π 1 π¬ 1 π 0
Maybe the most important thing Iβve learned over the past few years is that the solution to what looks like a collective action problem is to just start solving it. People will show up.
18.01.2026 03:58 β π 515 π 96 π¬ 5 π 8
Seems like a bunch of people are joining BlueSky recently after the whole X situation, so maybe it's worth highlighting this again. Also, if you feel like you should be on this list, send me a message!
13.01.2026 09:00 β π 21 π 7 π¬ 1 π 1
The bitter lesson of peer-reviewing?
13.01.2026 09:21 β π 1 π 0 π¬ 0 π 0
11.01.2026 22:19 β π 4 π 0 π¬ 0 π 0
1/π§΅ Q: Can we have both a simple and SOTA architecture in autonomous driving?
R: Yes! π
Introducing Driving on Registers (DrivoR):
a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation.
Here is how π
09.01.2026 16:55 β π 10 π 4 π¬ 1 π 1
The unreasonable magic of simplicity!
Meet DrivoR (Driving on Registers): our latest end2end autonomous driving model.
We teared down complex dependencies & modules from current models to
obtain a pure Transformer-based SOTA driving agent (NAVSIM v1 & v2, HUGSIM).
Find out more π
09.01.2026 17:02 β π 4 π 1 π¬ 0 π 0
Postdoctoral research position in Instance-level visual generation
Czech Technical University in Prague (CTU) offers a fellowship program, the CTU Global Postdoc Fellowship. This new and attractive two-year fellowship-program offers excellent researchers who have rec...
I have an opening for a two years post-doc position on instance-level (personalized) visual generation. Eligibility: (i) <=7 years from Ph.D. (ii) studies or 1 year outside of Czechia (ii) >=3 journal with IF or CORE A*/A conference papers. Deadline: 15 Feb.
Details: www.euraxess.cz/jobs/399390
08.01.2026 11:11 β π 12 π 10 π¬ 2 π 1
On some days when my digest arrives later in the day, it feels like the gods of scholar-inbox are punishing me for not checking my digest the prior day π
07.01.2026 09:00 β π 1 π 0 π¬ 0 π 0
asst prof of computer science at cu boulder
nlp, cultural analytics, narratives, communities
books, bikes, games, art
https://maria-antoniak.github.io
Announcing new open source releases, exploring projects, sharing how we approach FOSS, and supporting communities around the world.
A business analyst at heart who enjoys delving into AI, ML, data engineering, data science, data analytics, and modeling. My views are my own.
You can also find me at threads: @sung.kim.mw
MSCA Postdoctoral Fellow @ Visual Recognition Group, CTU in Prague. Deep Learning for Computer Vision. Former IARAI, Inria, Athena RC intern. Photographer. Crossfit freak.
πPrague, CZ. π http://users.ntua.gr/psomasbill/
Postdoc @ Princeton AI Lab
Natural and Artificial Minds
Prev: PhD @ Brown, MIT FutureTech
Website: https://annatsv.github.io/
ML Professor at Γcole Polytechnique. Python open source developer. Co-creator/maintainer of POT, SKADA. https://remi.flamary.com/
Official account of Saturday Morning Breakfast Cereal created by
@zachweinersmith.bsky.social.
Home of the ongoing webcomic SMBC, A City on Mars, and of little books featuring large concepts abridged beyond the point of usefulness.
Supporting EuroHPC supercomputer users with top-tier solutions powered by our partnersβ deep expertise and experience. https://epicure-hpc.eu/
I work on research problems combining generative models, computer graphics and computer vision. My primary focus is on learning a generative model that understands and represents the world around us.
www.anciukevicius.com
Assistant Professor of Computer Science at the University of British Columbia. I also post my daily finds on arxiv.
Interested in cognition and artificial intelligence. Research Scientist at Google DeepMind. Previously cognitive science at Stanford. Posts are mine.
lampinen.github.io
Incoming Assistant Professor at Johns Hopkins University | RAP at Toyota Technological Institute at Chicago | web: https://anandbhattad.github.io/ | Knowledge in Generative Image Models, Intrinsic Images, Image-based Relighting, Inverse Graphics
Understand complex biology through agentic AI.
Learn more at owkin.com
machine learning researcher @ Apple machine learning research
Assistant Prof at University of Waterloo, CIFAR AI Chair at Vector Institute. Formerly UWNLP, Stanford NLP, MSR, FAIR, Google Brain, Salesforce Research via MetaMind
#machinelearning, #nlp
victorzhong.com
Assistant Professor at Kyoto University, Japan. Topics: Vision + X, Human Perception Understanding, Visual Sentiment. EN/JP/DE/EO
head of product @bsky.app