🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited to share our latest #NeurIPS2023 paper "Labeling Neural Representations with Inverse Recognition." (arxiv.org/abs/2311.13594) We present INVERT — new global explanation method that explains neurons with human-understandable concepts they detect! A thread 🧵(1/8)

Exciting news: Our latest work “Sanity Checks Revisited” is accepted at NeurIPS XAI_in_Action_Workshop Kudos to authors: Anna Hedström Leander Weber Sebastian Lapuschkin Marina M.-C. Höhne (née Vidovic) 📖 Paper: openreview.net/pdf?id=vVpefYm… 🔎 Code: github.com/annahedstroem/… BIFOLD Universität Potsdam Fraunhofer HHI

Great times at NeurIPS Conference this week Soon we’ll be presenting some interpretability works 👉 Thu, 14 Dec, 5-7 PM CST (Great Hall & Hall B1+B2) neurips.cc/virtual/2023/p… 👉 Sat, 16 Dec, 4.30 PM CST (Room 271 - 273) neurips.cc/virtual/2023/w… Come chat with me!

If you are at #NeurIPS2023 check out our poster — happening now at Great Hall & Hall B1+B2 (level 1) #1519! I am not there — but my co-authors, and Anna Hedström from Understandable Machine Intelligence Lab will be there 😊

📣 Excited to announce our new preprint - "Manipulating Feature Visualizations with Gradient Slingshots”! We show that feature visualizations can be manipulated without altering the model architecture or significantly affecting performance. #ExplainableAI 🧵(1/6)

Excited to share our preprint: "CoSy: Evaluating Textual Explanations of Neurons"! 📄 arxiv.org/abs/2405.20331 There are various methods to explain neurons, but what makes a good explanation? Introducing CoSy, a method for evaluating textual explanations of neurons. 🧵 (1/8)

🚨 We're hiring! 🚨 We have 2 PhD positions available: 1️⃣ Focus on AI for Soil Health & Peat Substitution (Horizon Europe, SPIN-FERT) 2️⃣ Focus on Mechanistic Interpretability in Foundation Models (BMBF, REFRAME) 📅 Apply by August 25, 2024 🔗 loai-comramo.pi-asp.de/bewerber-web/?…

Thats us, the Data Science team at Leibniz-Institut für Agrartechnik und Bioökonomie! And we are searching 2 new PhD students - If you're passionate about research & coding, become part of our team and make an impact🌍💻 1️⃣ PhD for AI & Bias Detection 2️⃣ PhD for AI & Soil Quality Apply here: atb-potsdam.de/en/career/vaca…

We are pleased to announce that our paper by Laura Kopf Philine Bommer Anna Hedström Sebastian Lapuschkin Marina M.-C. Höhne (née Vidovic) and Kirill Bykov has been accepted to #NeurIPS2024 🎉 Check out the preprint: arxiv.org/abs/2405.20331 #ExplainableAI BIFOLD Fraunhofer HHI

Congratulations, Laura, on our NeurIPS paper acceptance! 🥳 I hope you had a wonderful PhD start at BIFOLD today.

You want to contribute to cutting-edge microbiome & AI research tackling climate change, biodiversity loss, and pollution. Ahmed Abdelfattah and I are searching for a Postdoc in Bioinformatics! #Bioinformatics #AI #MicrobiomeResearch #Postdoc #Bioeconomy

🚨 New paper alert! 🚨 Excited to share Quanda—a toolkit for evaluating data attribution methods, accepted at #NeurIPS ATTRIB workshop!🎉 A collaboration between Fraunhofer HHI & BIFOLD. 🔗 Paper: arxiv.org/abs/2410.07158 🔗 Code: github.com/dilyabareeva/q…

Looking forward to meet everyone at our #NeurIPS2024 poster and beyond 🤗

NeurIPS has an overwhelming amount of papers, so I made myself a hacky spreadsheet of all (well, most) of the interpretability papers - sharing in case others find it useful! It's definitely got false negatives and positives, but hopefully is better than baseline.

What a great and motivated team - Looking forward to our collaboration on SPIN-FERT 😍

Wow, what an amazing day at #NeurIPS2024 🎉 Presenting CoSy: Evaluating Textual Explanations of Neurons with Laura Kopf & Anna Hedström sparked so much interest and brainstorming sessions! 🌟 Huge thanks to our brilliant co-authors Philine Bommer Sebastian Lapuschkin Kirill Bykov! 🙌

🚨 New paper alert! 🚨 We’re excited to share our latest work on interpretability evaluation: "Evaluating Interpretable Methods via Geometric Alignment of Functional Distortions" 📜 Accepted at TMLR 🎉 🔥 Survey certification 🔥 📖 Read: openreview.net/pdf?id=ukLxqA8…