Lorenz Linhardt
@lorenzlinhardt.bsky.social
PhD Student at the TU Berlin ML group + BIFOLD | BUA Fellow Model robustness/correction 🤖🔧 Understanding representation spaces 🌌✨
🚨 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
🔦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...
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
🚨 Final call: 10 PhD positions in ML & Data Science at BIFOLD Application deadline: February 13, 2025 – This Friday! #GraduateSchool 2026 www.jobs.tu-berlin.de/en/job-posti... #hiring #phd #AcademicJobs #PhDPosition #naturalscience #AI #phd #phdjobs #VacancyEdu #ScienceCareer
#graduateschool #datamanagement #machinelearning #phd #ai #machinelearning #datascience #research #berlin #bifold #academiccareers #doctoralresearch | BIFOLD - Berlin Institute for the Foundations of ...
🚨 Final call: 10 PhD positions in AI & Data Science at BIFOLD Berlin Application deadline: February 13, 2025 – This Friday! #GraduateSchool 2026 https://lnkd.in/duheJE8J The Berlin Institute for th...
linkedin.com
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...
🚀 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. 👇👇👇
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
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
a black background with green text that says `` hello , world ''
ALT: a black background with green text that says `` hello , world ''
media.tenor.com
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!
🎉 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!
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...
openreview.net
Laure Ciernik@lciernik.bsky.social · last yr.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
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...
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
🎉 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
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...
Lorenz Linhardt@lorenzlinhardt.bsky.social · 2y agoHappy to co-chair this year's special track on "Actionable Explainable AI" with a great team! 📄🦾 Please consider submitting! (Abstract deadline: February 10th) ☝️
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
Happy to co-chair this year's special track on "Actionable Explainable AI" with a great team! 📄🦾 Please consider submitting! (Abstract deadline: February 10th) ☝️
BIFOLD Berlin Institute for the Foundations of Learning and Data@bifold.berlin · 2y agoCALL FOR PAPERS: #𝗫𝗔𝗜20𝟮𝟱, 𝗦𝗽𝗲𝗰𝗶𝗮𝗹 𝗧𝗿𝗮𝗰𝗸: Actionable explainable AI. Submit your paper until February 15, 2025. xaiworldconference.com/2025/actiona... #XAI #LRP #counterfactuals #shapley #models #deeplearning #interpretability #decisionmaking @lorenzlinhardt.bsky.social @tuberlin.bsky.social
Excited that Re-Align will have its second iteration at ICLR 2025 in Singapore! More soon! 🧠🤖
Nezihe Merve Gürel@nmervegurel.bsky.social · 2y agoThe list of accepted workshops for ICLR 2025 is available at openreview.net/group?id=ICL... @iclr-conf.bsky.social We received 120 wonderful proposals, with 40 selected as workshops.