Lightnews — Scholar-powered news

Lukas Muttenthaler

@lukasmut.bsky.social

390 followers 230 following 35 posts

Senior Researcher in AI for Biotech & @eml-munich.bsky.social | Prev. SR at Google DeepMind | PhD in ML and NeuroAI from @tuberlin.bsky.social @bifold.berlin @mpicbs.bsky.social | Representations in 🧠 and 🤖 | #FirstGen 🌈 💻: https://lukasmut.github.io/

lukasmut.github.io

Posts Media Videos Starter Packs

Pinned

Lukas Muttenthaler @lukasmut.bsky.social · Nov 27

Reposting this because I just started using Bluesky 🦋 Excited to share what we’ve been working on during my time at DeepMind! We came up with an approach that can distill the hierarchical structure of human conceptual knowledge into vision foundation models via a surrogate teacher model. More below👇🏼

Andrew Lampinen @lampinen.bsky.social · Sep 13

What aspects of human knowledge are vision models missing, and can we align them with human knowledge to improve their performance and robustness on cognitive and ML tasks? Excited to share this new work (arxiv.org/abs/2409.06509) by @lukasmut.bsky.social! 1/10

Paper title: Aligning Machine and Human Visual Representations across Abstraction Levels

1 17

Reposted by Lukas Muttenthaler

Gregg Gonsalves @gregggonsalves.bsky.social · 25d

Though it’s traumatic for me to bring this up, I was targeted by a group allied with Turning Point USA in 2018, with the help of Tucker Carlson on Fox. My home address circulated online and I got death threats. 1/

92 1.1K 3K

Reposted by Lukas Muttenthaler

Erin Grant @eringrant.me · Aug 19

I’m recruiting committee members for the Technical Program Committee at #CCN2026.

Please apply if you want to help make submission, review & selection of contributed work (Extended Abstracts & Proceedings) more useful for everyone! 🌐

Helps to have: programming/communications/editorial experience.

Grace Lindsay @neurograce.bsky.social · Aug 15

Fill out the form here to be involved in #CCN2026
tinyurl.com/ccn26committee

And definitely fill out the #CCN2025 feedback form!
tinyurl.com/ccn25partici...

CCN 2025 Participant Survey

❗ This is the general CCN post-conference survey. For the application form for positions on the committees at CCN 2026, please see the CCN 2026 Committee Application. Thank you for participating in C...

tinyurl.com

14 19

Lukas Muttenthaler @lukasmut.bsky.social · Aug 14

w/ @eringrant.me @dotadotadota.bsky.social @sucholutsky.bsky.social @siddsuresh97.bsky.social

Lukas Muttenthaler @lukasmut.bsky.social · Aug 14

Join us for the Re-Align^{3} community event & hackathon at #CCN2025 in room A2.11! There will be lots of 🌶️ discussions on 🧠🤖

1 1 9

Reposted by Lukas Muttenthaler

Phillip Isola @phillipisola.bsky.social · Aug 6

Interesting reaction from ChatGPT to the HHS mRNA memo. It finds it so implausible that it thinks it's fake. From the perspective of a ~2024(?) trained model, 2025 policies are so absurd as to be unbelievable...

chatgpt.com/share/689364...

3 13 53

Reposted by Lukas Muttenthaler

Laure Ciernik @lciernik.bsky.social · Jul 16

🎉 Presenting at #ICML2025 tomorrow!
Come and explore how representational similarities behave across datasets :)

📅 Thu Jul 17, 11 AM-1:30 PM PDT
📍 East Exhibition Hall A-B #E-2510

Huge thanks to @lorenzlinhardt.bsky.social, Marco Morik, Jonas Dippel, Simon Kornblith, and @lukasmut.bsky.social!

3 9

Reposted by Lukas Muttenthaler

Laure Ciernik @lciernik.bsky.social · Jun 6

If two models are more similar to each other than a third on ImageNet, will this hold for medical/satellite images?

Our #icml2025 paper analyses how vision model similarities generalize across datasets, the factors that influence them, and their link to downstream task behavior. 🧵1/7

1 4 24

Reposted by Lukas Muttenthaler

Martin Hebart @martinhebart.bsky.social · Jun 23

What makes humans similar or different to AI? In a paper out in @natmachintell.nature.com led by @florianmahner.bsky.social & @lukasmut.bsky.social, w/ Umut Güclü, we took a deep look at the factors underlying their representational alignment, with surprising results.

www.nature.com/articles/s42...

Dimensions underlying the representational alignment of deep neural networks with humans - Nature Machine Intelligence

An interpretability framework that compares how humans and deep neural networks process images has been presented. Their findings reveal that, unlike humans, deep neural networks focus more on visual ...

www.nature.com

2 36 100

Reposted by Lukas Muttenthaler

Laure Ciernik @lciernik.bsky.social · Jun 6

I am deeply grateful to @lorenzlinhardt.bsky.social, Marco Morik, Jonas Dippel, Simon Kornblith, and @lukasmut.bsky.social for their great work and support in this project! We also thank our collaborators, @bifold.berlin and HFA 7/7
📄Paper: arxiv.org/abs/2411.05561
💻Code: github.com/lciernik/sim...

Objective drives the consistency of representational similarity across datasets

The Platonic Representation Hypothesis claims that recent foundation models are converging to a shared representation space as a function of their downstream task performance, irrespective of the obje...

arxiv.org

3 6

Lukas Muttenthaler @lukasmut.bsky.social · Jun 6

🚨Have a look at our most recent work on the driving factors of representational similarities! This work will be presented at ICML 2025! See thread below 🧵

Laure Ciernik @lciernik.bsky.social · Jun 6

1 5

Lukas Muttenthaler @lukasmut.bsky.social · May 22

Please everyone gather and go outside, protest, march, do something! We cannot let science and academia be destroyed by the worst administration the US has ever had.

The New York Times @nytimes.com · May 22

Breaking News: The Trump administration halted Harvard’s ability to enroll international students, a major escalation in its battle with the school.

Trump Administration Halts Harvard’s Ability to Enroll International Students

www.nytimes.com

Reposted by Lukas Muttenthaler

Andrew Lampinen @lampinen.bsky.social · May 2

How do language models generalize from information they learn in-context vs. via finetuning? In arxiv.org/abs/2505.00661 we show that in-context learning can generalize more flexibly, illustrating key differences in the inductive biases of these modes of learning — and ways to improve finetuning. 1/

arxiv.org

4 21 78

Reposted by Lukas Muttenthaler

Dota Tianai Dong @dotadotadota.bsky.social · Apr 28

That’s a wrap for Re²-Align 🤖 🧠👤 at #ICLR2025 🦁🥳— thanks for being part of it! We’re probably just getting started… see you all at Re³-Align🌷😉

2 27

Reposted by Lukas Muttenthaler

Siddharth Suresh @siddsuresh97.bsky.social · Apr 28

✨ Come join us at the Second edition of the Re-Align workshop
@iclr_conf
! 🚀🧠 The workshop explores the fascinating question of how artificial and biological systems align in their representations of the world. #ReAlign #ICLR2025

3 5 16

Reposted by Lukas Muttenthaler

Barack Obama @barackobama.bsky.social · Apr 15

Harvard has set an example for other higher-ed institutions - rejecting an unlawful and ham-handed attempt to stifle academic freedom, while taking steps to make sure students can benefit from an environment of intellectual inquiry, rigorous debate and mutual respect. Let’s hope others follow suit.

1.6K 18K 90K

Lukas Muttenthaler @lukasmut.bsky.social · Apr 17

The trump administration is the worst that could have happened.

Lukas Muttenthaler @lukasmut.bsky.social · Apr 12

This is terrible

Lukas Muttenthaler @lukasmut.bsky.social · Apr 11

Here’s an extended version of my PhD defense talk about our work on *representational alignment between humans 🧠 and machines 🤖 for computer vision* that I gave two weeks ago at the Max Planck Institute for Human Cognitive and Brain Sciences

www.cbs.mpg.de/cbs-coconut/...

video-muttenthaler

Lukas Muttenthaler (Google DeepMind, TU Berlin)

www.cbs.mpg.de

3 10

Reposted by Lukas Muttenthaler

Eric Schulz @ericschulz.bsky.social · Apr 11

🚨 We're hiring! If you're excited about 🤖 ML/LLMs, 🧠 cognitive science, or 💭 computational psychiatry, come join us in Munich. Two fully funded PhDs @www.helmholtz-munich.de: tailored mentorship, international vibe, lots of room to grow.
📅 May 16th
🔗 hcai-munich.com/PhDHCAI.pdf

10 24

Lukas Muttenthaler @lukasmut.bsky.social · Apr 7

Thank you, Rob! 🙏🏼

Lukas Muttenthaler @lukasmut.bsky.social · Apr 6

Thank you Desmond! Copenhagen definitely played a big part in preparing me for the PhD.

Lukas Muttenthaler @lukasmut.bsky.social · Apr 6

Thank so much, Andrew! You know you played a big part in all of this and I am grateful that I got to know you during my PhD and can call you both a mentor and a friend.

1 1

Lukas Muttenthaler @lukasmut.bsky.social · Apr 6

Oh wow, then congrats Dr. Greta!! How did I miss this? I probably saw it and said congrats but forgot about this lol. For some reason I was under the impression that you and I will defend at about the same time 🤔 Very happy for you!!

1 1

Lukas Muttenthaler @lukasmut.bsky.social · Apr 6

Thank you Greta! 🫶🏼 When’s your turn?

Lukas Muttenthaler @lukasmut.bsky.social · Apr 6

Thanks a lot for your kind words, Dota! 🙏🏼🫶🏼