Lenka Tětková
@lenkatetkova.bsky.social
Postdoc at Technical University of Denmark working on ExplainableAI.
On Dec 2, I’ll present our Nature Communications paper “On convex decision regions in deep network representations” at the #ELLIS UnConference co-located with #EurIPS.
We show that human & machine learning may share the same geometry — convexity.
👉 eurips.cc/ellis
@ellis.eu @euripsconf.bsky.social
We show that human & machine learning may share the same geometry — convexity.
👉 eurips.cc/ellis
@ellis.eu @euripsconf.bsky.social
October 24, 2025 at 8:16 AM
On Dec 2, I’ll present our Nature Communications paper “On convex decision regions in deep network representations” at the #ELLIS UnConference co-located with #EurIPS.
We show that human & machine learning may share the same geometry — convexity.
👉 eurips.cc/ellis
@ellis.eu @euripsconf.bsky.social
We show that human & machine learning may share the same geometry — convexity.
👉 eurips.cc/ellis
@ellis.eu @euripsconf.bsky.social
Reposted by Lenka Tětková
Large Vision Models Can Solve Mental Rotation Problems
Sebastian Ray Mason, Anders Gjølbye, Phillip Chavarria Højbjerg, Lenka Tětková, Lars Kai Hansen
tl;dr: DINOv3,CLIP know 3D geometry, but only in middle layers. MAE bad, ImageNet bad, cls token bad.
arxiv.org/abs/2509.15271
Sebastian Ray Mason, Anders Gjølbye, Phillip Chavarria Højbjerg, Lenka Tětková, Lars Kai Hansen
tl;dr: DINOv3,CLIP know 3D geometry, but only in middle layers. MAE bad, ImageNet bad, cls token bad.
arxiv.org/abs/2509.15271
September 22, 2025 at 10:19 AM
Large Vision Models Can Solve Mental Rotation Problems
Sebastian Ray Mason, Anders Gjølbye, Phillip Chavarria Højbjerg, Lenka Tětková, Lars Kai Hansen
tl;dr: DINOv3,CLIP know 3D geometry, but only in middle layers. MAE bad, ImageNet bad, cls token bad.
arxiv.org/abs/2509.15271
Sebastian Ray Mason, Anders Gjølbye, Phillip Chavarria Højbjerg, Lenka Tětková, Lars Kai Hansen
tl;dr: DINOv3,CLIP know 3D geometry, but only in middle layers. MAE bad, ImageNet bad, cls token bad.
arxiv.org/abs/2509.15271
Reposted by Lenka Tětková
New work on how human brains and AI systems organize knowledge is out in Nature Communications
www.nature.com/articles/s41...
Great work,
@lenkatetkova.bsky.social and team!
www.nature.com/articles/s41...
Great work,
@lenkatetkova.bsky.social and team!
On convex decision regions in deep network representations - Nature Communications
Understanding how machine learning models form internal representations remains a fundamental challenge. Here, the authors explore the geometric property of convexity in latent spaces as a lens to bet...
www.nature.com
July 2, 2025 at 10:03 AM
New work on how human brains and AI systems organize knowledge is out in Nature Communications
www.nature.com/articles/s41...
Great work,
@lenkatetkova.bsky.social and team!
www.nature.com/articles/s41...
Great work,
@lenkatetkova.bsky.social and team!
🧠 New paper alert!
Our study in Nature Communications shows that both human & machine learning may rely on the same geometry: convexity.
It could be a key to shared concept formation.
👉 www.nature.com/articles/s41...
#AI #CognitiveScience #Explainability
Our study in Nature Communications shows that both human & machine learning may rely on the same geometry: convexity.
It could be a key to shared concept formation.
👉 www.nature.com/articles/s41...
#AI #CognitiveScience #Explainability
www.nature.com
July 2, 2025 at 9:10 AM
🧠 New paper alert!
Our study in Nature Communications shows that both human & machine learning may rely on the same geometry: convexity.
It could be a key to shared concept formation.
👉 www.nature.com/articles/s41...
#AI #CognitiveScience #Explainability
Our study in Nature Communications shows that both human & machine learning may rely on the same geometry: convexity.
It could be a key to shared concept formation.
👉 www.nature.com/articles/s41...
#AI #CognitiveScience #Explainability
Reposted by Lenka Tětková
🎥 The recording of the 2nd ELLISxUniReps Speaker Series session with @mtoneva.bsky.social and @lenkatetkova.bsky.social is now available at: youtu.be/qXBT_-w3Mfs
June 24, 2025 at 1:43 PM
🎥 The recording of the 2nd ELLISxUniReps Speaker Series session with @mtoneva.bsky.social and @lenkatetkova.bsky.social is now available at: youtu.be/qXBT_-w3Mfs
Reposted by Lenka Tětková
🎉 Get ready for our second @ellis.eu × UniReps Speaker Series session! 🔥
🗓️ When: June 20, 2025 – 16:00 CET
📍 Where: ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by @mtoneva.bsky.social & Flash Talk by @lenkatetkova.bsky.social
👉 Join our Google group: groups.google.com/u/2/g/ellis-...
🗓️ When: June 20, 2025 – 16:00 CET
📍 Where: ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by @mtoneva.bsky.social & Flash Talk by @lenkatetkova.bsky.social
👉 Join our Google group: groups.google.com/u/2/g/ellis-...
June 11, 2025 at 11:48 AM
🎉 Get ready for our second @ellis.eu × UniReps Speaker Series session! 🔥
🗓️ When: June 20, 2025 – 16:00 CET
📍 Where: ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by @mtoneva.bsky.social & Flash Talk by @lenkatetkova.bsky.social
👉 Join our Google group: groups.google.com/u/2/g/ellis-...
🗓️ When: June 20, 2025 – 16:00 CET
📍 Where: ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by @mtoneva.bsky.social & Flash Talk by @lenkatetkova.bsky.social
👉 Join our Google group: groups.google.com/u/2/g/ellis-...
Reposted by Lenka Tětková
We are thrilled to welcome an incredible lineup of invited speakers to the 4th Explainable AI for Computer Vision (XAI4CV) Workshop, held as part of #CVPR2025 — which kicks off next week, from Wednesday, June 11th to Sunday, June 15th in Nashville, TN!
June 5, 2025 at 12:59 PM
We are thrilled to welcome an incredible lineup of invited speakers to the 4th Explainable AI for Computer Vision (XAI4CV) Workshop, held as part of #CVPR2025 — which kicks off next week, from Wednesday, June 11th to Sunday, June 15th in Nashville, TN!