iiinova — where your digital self keeps evolving

Reposted by Lorenz Linhardt

Explainable AI Berlin @xai-berlin.bsky.social · 05/10/2026

🚨 New paper alert! Towards Fast and Disentangled Counterfactuals for Visual Foundation Models: arxiv.org/pdf/2610.00895

032

Reposted by Lorenz Linhardt

Explainable AI Berlin @xai-berlin.bsky.social · 14/08/2026

🚨 New paper alert! WaX, a method to explain what drives dataset shift by decomposing Wasserstein distances into exact instance- and feature-level attributions using XAI. doi.org/10.1109/TPAM...

031

Reposted by Lorenz Linhardt

Explainable AI Berlin @xai-berlin.bsky.social · 09/07/2026

🚨 New preprint alert! Distributed Sparse Interventions (DSI), a method to steer LLM behavior by intervening on as few as 8-64 neurons (as little as 0.01% of a model!), instead of whole layers or directions in activation space. 🔗 arxiv.org/abs/2607.07128

191

Reposted by Lorenz Linhardt

Explainable AI Berlin @xai-berlin.bsky.social · 02/04/2026

🔦Past Paper Highlight: Scaling Higher-Order Explanations for Graph Neural Networks 📄Efficient Higher-Order Subgraph Attribution via Message Passing 🔗 proceedings.mlr.press/v162/xiong22... 📄Relevant Walk Search for Explaining Graph Neural Networks 🔗 proceedings.mlr.press/v202/xiong23...

131

Reposted by Lorenz Linhardt

BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 23/03/2026

BIFOLD supports IEEE SaTML 2026. 🧵 🔔Program Chair: Konrad Rieck, alongside Rachel Cummings 🔔Web Chair: @eisenhofer.bsky.social & Stefan Czybik 🔔Part of the Program Committee: Thorsten Eisenhofer, @kirillbykov.bsky.social @tuberlin.bsky.social @tumunich.bsky.social @rieck.mlsec.org @satml.org

142

Reposted by Lorenz Linhardt

Explainable AI Berlin @xai-berlin.bsky.social · 22/12/2025

2025 marks the 10-year anniversary of Layer-wise Relevance Propagation (LRP)! 🥳 To celebrate a decade of this attribution method, we highlight key milestones from the past ten years in our LinkedIn post. Learn more here: www.linkedin.com/posts/xai-be...

191

Reposted by Lorenz Linhardt

Explainable AI Berlin @xai-berlin.bsky.social · 28/11/2025

🚀 Visit our #NeurIPS posters at @neuripsconf.bsky.social! Meet and interact with our authors at all locations — San Diego, Mexico City, and Copenhagen. Details in the thread. 👇👇👇

1124

Reposted by Lorenz Linhardt

Explainable AI Berlin @xai-berlin.bsky.social · 06/11/2025

We are grateful for the opportunity to present some of our work at the All Hands Meeting of the German AI Centers, hosted by @dfki.bsky.social in Saarbrücken. Andreas Lutz @eberleoliver.bsky.social Manuel Welte @lorenzlinhardt.bsky.social @lkopf.bsky.social #AI #XAI #Interpretability

183

Lorenz Linhardt @lorenzlinhardt.bsky.social · 20/10/2025

Had a great time visiting @darpsky.bsky.social at Technische Universität Wien last week. It's exciting to see him build up his new group! Many thanks to the whole Security & Privacy research unit for the welcoming atmosphere and interesting discussions!

0112

Reposted by Lorenz Linhardt

Laure Ciernik @lciernik.bsky.social · 16/07/2025

🎉 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!

openreview.net

Objective drives the consistency of representational similarity...

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...

093

Reposted by Lorenz Linhardt

BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 16/06/2025

Join us - we have four open positions for doctoral/postdoctoral researchers at BIFOLD, doing cutting edge research in data management and machine learning as well as their intersections. More information: www.bifold.berlin/about-us/opp...

044

Reposted by Lorenz Linhardt

Laure Ciernik @lciernik.bsky.social · 06/06/2025

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...

arxiv.org

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...

063

Lorenz Linhardt @lorenzlinhardt.bsky.social · 03/05/2025

🎉 Excited to have had the opportunity to present two posters at the ICLR2025 workshops! 🖼️🖼️ A big thanks to my coauthors and to everyone who dropped by to discuss! Also, thanks to the Re-Align and DeLTa organizers for hosting such an inspiring workshop day. ✨ @bifold.berlin @tuberlin.bsky.social

140

Reposted by Lorenz Linhardt

BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 03/02/2025

CALL FOR PAPERS: #XAI2025, Special Track: Actionable explainable AI. Submit your paper and check the Submission deadlines: xaiworldconference.com/2025/importa... Actionable Explainable AI xaiworldconference.com/2025/actiona...

051

Lorenz Linhardt @lorenzlinhardt.bsky.social · 13/01/2025

Thanks to everyone for the lively discussions on concept convexity and alignment in DL models at #NLDL (Northern Lights Deep Learning conference)! ❄️❄️ Had a great time in beautiful Tromsø connecting with fellow researchers 🤝 📜 Feel free to check out our preprint: arxiv.org/abs/2409.06362

071

Lorenz Linhardt @lorenzlinhardt.bsky.social · 13/01/2025

Happy to co-chair this year's special track on "Actionable Explainable AI" with a great team! 📄🦾 Please consider submitting! (Abstract deadline: February 10th) ☝️

041

Reposted by Lorenz Linhardt

Lukas Muttenthaler @lukasmut.bsky.social · 04/12/2024

Excited that Re-Align will have its second iteration at ICLR 2025 in Singapore! More soon! 🧠🤖

0192