Understandable Machine Intelligence Lab
@UMI_Lab_AI
Followers
651
Following
231
Media
56
Statuses
168
Understandable Machine Intelligence Lab: We bring #explainable #AI to the next level. Part of @LeibnizATB, Ex @TUBerlin, funded by @BMBF_Bund #XAI
Berlin, Germany
Joined November 2020
Our latest paper is out! 🚀.
🔍 When do neurons encode multiple concepts?. We introduce PRISM, a framework for extracting multi-concept feature descriptions to better understand polysemanticity. 📄 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework.🧵
0
0
3
RT @anna_hedstroem: If you're at #AAAI2025 don't miss our poster today (alignment track)! . Paper 📘: Code 👩💻: htt….
0
2
0
Huge thanks again to our co-authors!. @anna_hedstroem @BommerPhiline @tfburns @SLapuschkin @WojciechSamek @Marina_MCV. @TUBerlin.@FraunhoferHHI.@bifoldberlin.@BrownUniversity.@Cornell.@OISTedu.@LeibnizATB.@unipotsdam.
0
2
4
Our recently accepted TMLR paper has been awarded:. 🔥 Survey certification 🔥. "For an exceptionally thorough or insightful survey of interpretability evaluation.". 📖 Read: 💻 Code:
1
0
4
Huge thanks to our co-authors!. @anna_hedstroem @BommerPhiline @tfburns @SLapuschkin @WojciechSamek @Marina_MCV. @TUBerlin.@FraunhoferHHI.@bifoldberlin.@BrownUniversity.@Cornell.@OISTedu.@LeibnizATB.@unipotsdam.
0
0
3
🚨 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:
1
5
5
RT @anna_hedstroem: If you’re still @NeurIPSConf and are curious about how evaluation outcomes of interpretability methods can be adversari….
0
1
0
RT @anna_hedstroem: Interested in eval, vision and mechanistic interpretability?. Come chat at our @NeurIPSConf poster! #3107 . 👉 Thu, 12 D….
0
1
0
RT @anna_hedstroem: First day #NeurIPS2024 jetlagged but happy to be reunited with @UMI_Lab_AI . @Marina_MCV @lkopf_ml .
0
2
0
RT @lkopf_ml: I’ll be presenting our work at @NeurIPSConf in Vancouver! 🎉.Join me this Thursday, December 12th, in East Exhibit Hall A-C, P….
0
4
0
RT @kirill_bykov: I am not attending #NeurIPS2024, but I encourage everyone interested in #XAI and #MechInterp to check out our paper on ev….
0
3
0
RT @di_lya: ✨Introducing quanda: an open-source library for benchmarking training data attribution (TDA) methods in PyTorch!. Quanda offers….
0
8
0
RT @anna_hedstroem: We (@di_lya, Galip Ümit Yolcu, Niklas Schmolenski, @wiegand_t, @WojciechSamek, @SLapuschkin + me) just launched QUANDA….
0
2
0
Congratulations to all authors: @di_lya , Galip Ümit Yolcu, @anna_hedstroem , Niklas Schmolenski, @wiegand_t, @WojciechSamek , @SLapuschkin.
0
0
1
🚨 New paper alert! 🚨. Excited to share Quanda—a toolkit for evaluating data attribution methods, accepted at #NeurIPS ATTRIB workshop!🎉. A collaboration between @FraunhoferHHI & @bifoldberlin. 🔗 Paper: 🔗 Code:
1
4
12
RT @Marina_MCV: You want to contribute to cutting-edge microbiome & AI research tackling climate change, biodiversity loss, and pollution.….
0
2
0
RT @kirill_bykov: Thank you Stefan Lindow @SlineL for the amazing opportunity to give a talk on Explainable AI at the Potsdam Graduate Scho….
0
1
0
RT @lkopf_ml: 🎉 Excited to announce that our paper has been accepted to #NeurIPS2024! This is my first first-author publication 🥳 I'm incre….
0
3
0