iiinova — where your digital self keeps evolving

Jan van Gemert @jvgemert.bsky.social · 25/09/2026

I love those visual abstracts!

Jan van Gemert @jvgemert.bsky.social · 25/09/2026

Haha, old paradigm love? 😅

100

Reposted by Jan van Gemert

Dan Goodman @neural-reckoning.org · 20/09/2026

I'm not sure I agree with @giorgio.gilest.ro's logic that this ends up with technofeudalism. Yes LLM-written papers are flooding journals, but that's because journals are and always were a bad tool for filtering for insight. Our response should be to try something different.

2155

Jan van Gemert @jvgemert.bsky.social · 19/09/2026

Scientific enshittification? Or is that term already used for something else? (highly likely, unfortunately)

Jan van Gemert @jvgemert.bsky.social · 19/09/2026

Its 2x45=90 min. Where lectures (1,2) (2,3) are taught together. I focus on the essence. Ie: I had to cut my content in half, twice. Students only remembered 25%, so, they might as well remember the 25% that matters 🙂. I aim to teach slow and in-depth, vs shallow, fast, and broad.

020

Jan van Gemert @jvgemert.bsky.social · 19/09/2026

Wow! This website is incredible! It's so vague, repetitive, unexplained, sometimes wrong, and even including marketing, that I hope my students can see through this, because critical thinking is a learning objective 😅 It actually means that the slides are timely, in a world filled with blur.

000

Reposted by Jan van Gemert

Nicolas Audebert @nshaud.bsky.social · 03/08/2026

I'm burnt out of discussing "AI". I don't care for the press releases from big companies. I hate having to comment immediately. I dislike "hot takes". I'm worried we, as scientists, are losing touch with scientific values. We've become customers, salivating at ads marketed to investors. 1/15

49135

Reposted by Jan van Gemert

Dr. Martin Skrodzki @msmathcomp.bsky.social · 17/09/2026

Open Position for an Assistant/Associate Professor in Visual Analytics: careers.tudelft.nl/job/Delft-As.... Apply if you are excited about interactive exploration, analysis, and interpretation of complex data. Please also forward this position to anyone in your network who is interested.

careers.tudelft.nl

Assistant/Associate Professor in Visual Analytics

046

Jan van Gemert @jvgemert.bsky.social · 18/09/2026

I never wanted to share my slides before the lecture because it ruins my Socratic teaching style 🍵 But.. I found out they are circling in the interwebs, so, I might as well share them myself then 🙂. Then at least they are up to date 😊. jvgemert.github.io/teach.html

jvgemert.github.io

teaching | Jan van Gemert

Academic website of Jan van Gemert, Computer Vision and Deep Learning research, TU Delft.

1123

Jan van Gemert @jvgemert.bsky.social · 16/09/2026

1: you are forced by your organization to use it.

150

Jan van Gemert @jvgemert.bsky.social · 14/09/2026

Our fifth workshop on Meta-science for Machine Learning is on Sept 22. metascienceforml.github.io Registration info in the link.

metascienceforml.github.io

Metascience for Machine Learning

A repository for collecting information about Metascience for machine learning.

044

Jan van Gemert @jvgemert.bsky.social · 12/09/2026

A Delfie at the European Conference on Computer Vision #ECCV2026 :)

1100

Jan van Gemert @jvgemert.bsky.social · 11/09/2026

Ok. Scholar-inbox seems a good solution to navigating the posters.

020

Jan van Gemert @jvgemert.bsky.social · 11/09/2026

Posters are not findable anyway @eccv.bsky.social #ECCV2026 the app is unusable, and the website has no poster numbers at the papers. Moving poster boards around seems not a big issue if posters aren't findable anyway 😂

120

Jan van Gemert @jvgemert.bsky.social · 10/09/2026

Haha an AI workaround for deficiencies in an AI conference 😂

Jan van Gemert @jvgemert.bsky.social · 09/09/2026

@eccv.bsky.social #ECCV2026 How can I organize which posters to see where? The app cuts off paper titles (ie: unreadable and unusable). The website's schedule is great, but has no poster IDs next to the titles. Will we get a handy hardcopy program, with titles, times, and ids?

110

Jan van Gemert @jvgemert.bsky.social · 06/09/2026

Anyone interested here for pooling together some money to increase @emilymbender.bsky.social 's fee? 😊 (I looked up the fee, and Im hoping this message is widely shared 😅)

Jan van Gemert @jvgemert.bsky.social · 04/09/2026

This is why I work on data efficiency: to allow AI training for the long tail of SMEs and universities who don't have the huge resources. I don't believe AI will go away. Let's make training more accessible. It's aligning my research with my values.

141

Reposted by Jan van Gemert

Evangelos Kazakos @ekazakos.bsky.social · 02/09/2026

Computer vision people, where are you??? 👀

163

Reposted by Jan van Gemert

Victoria Bosch @initself.bsky.social · 28/08/2026

Are brains and artificial neural networks converging onto universal representations? There is a seductive idea making the rounds in NeuroAI / machine learning: train systems well enough, and they all converge on the same representation of reality (i.e. a unique world model). We have thoughts™ 1/n

cell.com

The Umwelt Representation Hypothesis: rethinking Universality

Recent studies reveal striking representational alignment between artificial neural networks (ANNs) and biological brains, leading to proposals that all sufficiently capable systems converge on univer...

818175

Jan van Gemert @jvgemert.bsky.social · 02/09/2026

#ECCV2026 Workshop on Empirical Theory: tracing back the causal relationships in our scientific papers. Untroubling the "troubling trends in machine learning scholarship" empiricaltheory.github.io @eccv.bsky.social

Jan van Gemert @jvgemert.bsky.social · 23/08/2026

093

Thank you for sharing. It takes courage to open up like you do.

000

Jan van Gemert @jvgemert.bsky.social · 19/08/2026

Transformers for Transformers!

120

Jan van Gemert @jvgemert.bsky.social · 16/08/2026

I feel very much the same. This is one the reason why we started the Empirical Theory in Representation Learning workshop. Wouldn't it be great to have a venue full of interesting papers!? 🤩 empiricaltheory.github.io

Jan van Gemert @jvgemert.bsky.social · 14/08/2026

This is one of our reasons for starting a new research style initiative: Empirical Theory: empiricaltheory.github.io

Jan van Gemert @jvgemert.bsky.social · 12/08/2026

132

And how CNNs learn to break translation equivariance as the cheri on top ;)

030

Reposted by Jan van Gemert

ML for Science @ml4science.bsky.social · 06/08/2026

📢 We're hiring: Tenure-Track Professor for Philosophy of Machine Learning for Science @unituebingen.bsky.social! We're looking for an outstanding researcher with a strong profile in #philosophy and strong connections to #ML and #AI. Deadline: 30 Sept 2026; more info: uni-tuebingen.de/en/128980 1/3

This graphic displays the following text on a colored background: Open Position: Tenure-Track Professor of Philosophy of Machine Learning for Science. Application Deadline: September 30, 2026.

2106

Jan van Gemert @jvgemert.bsky.social · 31/07/2026

Partly a reason why I just try to scan *all* arXiv entries in CV 😁. Its also a source of research papers outside of other bubbles which I might be in 🙂.

020

Jan van Gemert @jvgemert.bsky.social · 31/07/2026

@vele.bsky.social @cscv-bot.bsky.social I love your arXiv bot ♥️. But.. reading it is difficult due to the author names coming first, so the most important thing is difficult to find: the paper title 🙂. If it was up to me, I would remove the author list completely 😁.

240

Jan van Gemert @jvgemert.bsky.social · 24/07/2026

NeurIPS reviewers not liking understanding-based ML work? Consider submitting to our workshop: empiricaltheory.github.io - R1: Reject. Not state of the art. - R2: Reject. Just small toy datasets. - R3: Reject. After reading the paper it's trivial.

Empirical Theory in Representation Learning

0103

Jan van Gemert @jvgemert.bsky.social · 15/07/2026

Great respectful science-based discussion. This is why I am on BlueSky 💙.

Jan van Gemert @jvgemert.bsky.social · 15/07/2026

This on-point quote could have been taken straight from academia. Probably holds for any large enough organisation (?). Be the change you want to see.

000

Reposted by Jan van Gemert

David Picard @davidpicard.eurosky.social · 07/07/2026

The E.T.👽 workshop submission is finally open! We aim at promoting scientific theory building in deep representation learning 2 tracks: 1p storyline & regular 14p full paper Deadline: Aug 1st 🖥️ empiricaltheory.github.io 📜 openreview.net/group?id=the... Let's do science! @eccv.bsky.social #ECCV

Jan van Gemert @jvgemert.bsky.social · 13/07/2026

0116

Understand-based research vs BOLD numbers. Submit your work to our ECCV workshop on Empirical Theory: empiricaltheory.github.io @davidpicard.eurosky.social @a-lucic.bsky.social m.loog, h.hung, h.pinson.