Plain language: we are recording and stimulating neurons in working brains (#mechinterp !), using two high-powered lasers, one to measure activity and one to change it. Getting both proteins inside cells is hard. And this is a solution.
Here's a paper using it:
www.pnas.org/doi/10....
🧠 🤖🧪
Different seeds with same training loss doesn't always mean same solution. When do neural nets converge vs diverge? What are the implications for inverse problems, #AI4Science & #MechInterp?
#NeurIPS2025 poster 2001 (“a space odyssey”), 4:30–7:30pm today 12/5:
Some of the #NeurIPS 2025 papers our lab contributed to. Curious, please reach out to Thomas Dooms who is on site or just drop us an email
#Interpretability #explainability #MechInterp #XAI #AI #ML
#sqIRL #IDLab #UAntwerp
Kudos to Thomas and the involved collaborators for the solid contributions to the field.
Curious about our work, have a look at our website: sqirllab.github.io/
#Interpretability #mechinterp #compinterp #xai #AI #ML
#sqIRL #UAntwerp #IDLab
At the MI workshop (spotlight), we show how Bilinear Autoencoders ease the analysis of neural representations through their decomposition into polynomial latents.
Paper and the cool demos at tdooms.github.io/research/bae
#Interpretability #mechinterp #compinterp #xai #AI #ML
#UAntwerp #IDLab
Have a look at the work our lab will be presenting at #NeurIPS '25.
On the main track, SimpleStories, a dataset full of simple yet diverse stories which has the potential of becoming the MNIST for language.
openreview.net/pdf?id=sVh3e...
#Interpretability #mechinterp #xai #AI #ML
#sqIRL #UAntwerp
We just launched a #linkedin page. Please help us spread the word and share it with people that might be interested.
linkedin.com/company/sqir...
#RepresentationLearning #interpretability #explainability #XAI #mechinterp #AI #ML #sqIRL #ComputerVision #HSI #IDLab #UAntwerp
This is the eXplainable AI research channel of the machine learning group of Prof. Klaus-Robert Müller at Technische Universität Berlin @tuberlin.bsky.social & BIFOLD @bifold.berlin.
Let's connect!
#XAI #ExplainableAI #MechInterp #MachineLearning #Interpretability
Happy to share that our PRISM paper has been accepted at #NeurIPS2025 🎉
In this work, we introduce a multi-concept feature description framework that can identify and score polysemantic features.
📄 Paper: arxiv.org/abs/2506.15538
#NeurIPS #MechInterp #XAI
This year's edition of the #AIMLAI workshop is a wrap. Thanks to our participants, paper contributors, reviewers and Prof. Cynthia Rudin (@DukeU) for closing the event with a memorable keynote.
#ECMLPKDD2025 #XAI #interpretability #ML #AI #mechinterp #ECMLPKDD
We will be presenting the paper at #ACL2025NLP 🇦🇹. Feel free to stop by the poster to say hello!
📅 29/07 (Tue) 10:30-12:00
📍 Hall 4/5
#NLProc #interpretability #XAI #mechinterp #MLSky
The deadline for the #AIMLAI workshop held jointly with #ECMLPKDD2025 has been extended until June 21st.
Looking forward to last-minute submissions on work around #interpretability and #explainability of #AI / #ML
project.inria.fr/aimla
#mechinterp #xai
A week left for the submission deadline for the #AIMLAI workshop to be held jointly with #ECMLPKDD2025
We welcome long and short papers covering work around #interpretability and #explainability of #AI/#ML
Submission deadline: 14/06/25
project.inria.fr/aimlai
#mechinterp #xai #ECMLPKDD2025
Many thanks to my amazing co-authors: @reduanachtibat.bsky.social, Thomas Wiegand, Wojciech Samek, @slapuschkin.bsky.social !
#NLProc #interpretability #XAI #mechinterp #MLSky
It is confirmed, the #AIMLAI workshop will be held jointly with @ecmlpkdd.org.
We invite the submissions of long and short papers covering work around #interpretability and #explainability of #AI/#ML.
Deadline: 14/06/25
CfP: shorturl.at/yYQ9G
Website: shorturl.at/W9r1A
#XAI #mechinterp #ECMLPKDD
Thomas Dooms will show how to bilinear MLPs can server as more transparent component that provides a better lens to study the relationships between inputs, outputs and the weights that define the models. #mechinterp #interpretability #ML #AI #XAI #ICLR2025 #sqIRL
openreview.net/forum?id=gI0...
Our 405b pilot program is accepting applications through December 31st, 2024. Take a few minutes before the holiday season to fill out an application at ndif.us/405b.html
#mechinterp #llama405b #NDIF #NNsight #airesearch
Want to know more about CoSy?
📄 Paper: arxiv.org/abs/2405.20331
💻 Code: github.com/lkopf/cosy
🔗 Poster: neurips.cc/virtual/2024...
#NeurIPS2024 #MechInterp #ExplainableAI #Interpretability
I am not attending #NeurIPS2024, but I encourage everyone interested in #XAI and #MechInterp to check out our paper on evaluating textual descriptions of neurons!
Join @lkopf.bsky.social, Anna Hedström, and Marina Marie-Claire Höhne on Thu 09.12, 1 p.m. to 4 p.m. CST at East Exhibit Hall A-C #3107!
Some things that I am interested in: #meditation, #machinelearning, #aialignment, #learning, #claude, #claudeai, #mindfulness, #buddhism, #theravada, #mahayana, #vajrayana, #mechinterp, #sf, #bayarea, #nyc, #japan, #tpot, #shinzen, #awakening, #zen, #sleep, #consciousness, #texttovideo, #photography
This surprising mechanism shows that there’s still a lot of work to do in very “low level” #mechinterp . Sophisticated computation can happen within each layer! But studying the weights and activations to reverse engineer the algorithm wasn't easy.
