Lightnews — Scholar-powered news

Christian Wolf

@chriswolfvision.bsky.social

6.1K followers 740 following 1.3K posts

Principal Scientist at Naver Labs Europe, Lead of Spatial AI team. AI for Robotics, Computer Vision, Machine Learning. Austrian in France. https://chriswolfvision.github.io/www/

chriswolfvision.github.io

Posts Media Videos Starter Packs

Reposted by Christian Wolf

Grant Sanderson @3blue1brown.com · 15h

Ever since I made a video about Fourier Transforms, one of the most requested topics on the channel has been its close cousin, the Laplace Transform.

I've been having a lot of fun animating a mini-series about this topic, and the main part is now out.

youtu.be/j0wJBEZdwLs

But what is a Laplace Transform?

YouTube video by 3Blue1Brown

youtu.be

9 60 360

Christian Wolf @chriswolfvision.bsky.social · 2d

Congrats! 🎉

1 13

Reposted by Christian Wolf

Andreas Geiger @andreasgeiger.bsky.social · 2d

Personal programs for ICCV 2025 are now available at:
www.scholar-inbox.com/conference/i...

6 22

Christian Wolf @chriswolfvision.bsky.social · 3d

Congrats Dr. Edstedt !
😀

Christian Wolf @chriswolfvision.bsky.social · 3d

Computer vision will not only save robotics, it will save AI 😆

Chaz Firestone @chazfirestone.bsky.social · 3d

This is a big one! A 4-year writing project over many timezones, arguing for a reimagining of the influential "core knowledge" thesis.

Led by @daweibai.bsky.social, we argue that much of our innate knowledge of the world is not "conceptual" in nature, but rather wired into perceptual processing. 👇

Screenshot of a paper abstract:

“Core knowledge” refers to a set of cognitive systems that underwrite early representations of the physical and social world, appear universally across cultures, and likely result from our genetic endowment. Although this framework is canonically considered as a hypothesis about early emerging conception — how we think and reason about the world — here we present an alternative view: that many such representations are inherently perceptual in nature. This “core perception” view explains an intriguing (and otherwise mysterious) aspect of core-knowledge processes and representations: that they also operate in adults, where they display key empirical signatures of perceptual processing. We first illustrate this overlap using recent work on “core physics”, the domain of core knowledge concerned with physical objects, representing properties such as persistence through time, cohesion, solidity, and causal interactions. We review evidence that adult vision incorporates exactly these representations of core physics, while also displaying empirical signatures of genuinely perceptual mechanisms, such as rapid and automatic operation on the basis of specific sensory inputs, informational encapsulation, and interaction with other perceptual processes. We further argue that the same pattern holds for other areas of core knowledge, including geometrical, numerical, and social domains. In light of this evidence, we conclude that many infant results appealing to precocious reasoning abilities are better explained by sophisticated perceptual mechanisms shared by infants and adults. Our core-perception view elevates the status of perception in accounting for the origins of conceptual knowledge, and generates a range of ready-to-test hypotheses in developmental psychology, vision science, and more.

Christian Wolf @chriswolfvision.bsky.social · 4d

Thanks! I knew julia's blogpost on git and her wonderful graphs.

But this was more a rant than a serious question 😉 I do these every now and then, specifically on git, and they always have a triggering event.

Christian Wolf @chriswolfvision.bsky.social · 4d

What PhD do I need to get and from which institution to fully understand git?

2 1 4

Reposted by Christian Wolf

Giorgos Tolias @gtolias.bsky.social · 6d

The Visual Recognition Group at CTU in Prague organizes the 50th Pattern Recognition and Computer Vision Colloquium with
Torsten Sattler, Paul-Edouard Sarlin, Vicky Kalogeiton, Spyros Gidaris, Anna Kukleva, and Lukas Neumann.
On Thursday Oct 9, 11:00-17:00.

cmp.felk.cvut.cz/colloquium/

2 6 23

Reposted by Christian Wolf

Oded Rechavi @odedrechavi.bsky.social · 8d

Thanking the reviewers

1 12 130

Christian Wolf @chriswolfvision.bsky.social · 9d

What does really matter in {Object,Image}Goal-Navigation:
ObjectGoal: arxiv.org/abs/2510.01830
ImageGoal: arxiv.org/abs/2507.01667

1 9

Christian Wolf @chriswolfvision.bsky.social · 9d

There is no training in the paper.

Christian Wolf @chriswolfvision.bsky.social · 9d

Julius Cesar walks into a bar and says
- "I'll have a Martinus"
- "I guess you mean a Martini?"
- "If I wanted more than one I would have said so"

Christian Wolf @chriswolfvision.bsky.social · 10d

a man standing in a pile of shredded paper in front of a bulletin board

ALT: a man standing in a pile of shredded paper in front of a bulletin board

media.tenor.com

Christian Wolf @chriswolfvision.bsky.social · 10d

Looks good !!

arxiv.org/abs/2510.00978

Christian Wolf @chriswolfvision.bsky.social · 10d

LOL, ok I understand!

Christian Wolf @chriswolfvision.bsky.social · 10d

What do we think of this?

(will not provide the reference of the paper)

1 2

Christian Wolf @chriswolfvision.bsky.social · 10d

"The success rate is defined as the fraction of ... that solved the task (as determined by the authors). A SR greater than 0 suggests that the model possesses the ability to solve the task while a SR closer to 1 indicates that the task is solved reliably irrespective of the random seed."

😬

3 2

Christian Wolf @chriswolfvision.bsky.social · 10d

Ok, now I am really experiencing FOMO. Is this trolling or did I miss something important?

Christian Wolf @chriswolfvision.bsky.social · 10d

I have not checked Scholar Inbox today, what are the effects on my career? Will I survive this? What did I miss?

2 5

Christian Wolf @chriswolfvision.bsky.social · 10d

Neurips: the influence of space constraints was neglectable.

NeurIPS Conference @neuripsconf.bsky.social · 12d

NeurIPS decisions have now been released! To provide transparency into our reviewing and decision-making process, we asked chairs from the Main Program and Dataset and Benchmarks Tracks to write a blog post reflecting on their process this year (links in🧵)

blog.neurips.cc

2 3

Christian Wolf @chriswolfvision.bsky.social · 11d

😱

Christian Wolf @chriswolfvision.bsky.social · 11d

Oh ... okay.
I didn't like the movies a lot actually.

1 1

Christian Wolf @chriswolfvision.bsky.social · 11d

I stopped after the second, which I didn't like. I loved the first though.

1 1

Christian Wolf @chriswolfvision.bsky.social · 11d

Try Dune. This might be the counter example 😉

2 1

Christian Wolf @chriswolfvision.bsky.social · 11d

TIL: 🤔

Extreme Ironing is an extreme sport in which people take ironing boards to remote locations and iron items of clothing.

"the latest dangerous sport that combines the thrills of an extreme outdoor activity with the satisfaction of a well-pressed shirt."

en.wikipedia.org/wiki/Extreme...

4 3 23