SLapuschkin Profile Banner
Sebastian Lapuschkin Profile
Sebastian Lapuschkin

@SLapuschkin

Followers
134
Following
62
Media
17
Statuses
73

Head of #XAI at @FraunhoferHHI Google Scholar: https://t.co/fTd8OLgxRq

Berlin
Joined June 2022
Don't wanna be here? Send us removal request.
@SLapuschkin
Sebastian Lapuschkin
13 days
RT @egor_zverev_ai: 🚀 We’ve released the source code for 𝗔𝗦𝗜𝗗𝗘 (presented as an 𝗢𝗿𝗮𝗹 at the #ICLR2025 BuildTrust workshop)!. 🔍ASIDE boosts….
0
6
0
@SLapuschkin
Sebastian Lapuschkin
1 month
Have had enough of the fake "sources" "cited" by ChatGPT? We have the solution in the form of low-cost causal citations for LLMs: Thanks to my amazing co-authors @pkhdipraja. , Reduan Achtibat, @wiegand_t. and @WojciechSamek. from @FraunhoferHHI
Tweet media one
0
1
4
@SLapuschkin
Sebastian Lapuschkin
1 month
RT @pkhdipraja: ICL allows LLMs to adapt to new tasks and at the same time enables them to access external knowledge through RAG. How does….
0
2
0
@SLapuschkin
Sebastian Lapuschkin
4 months
0
2
0
@SLapuschkin
Sebastian Lapuschkin
5 months
RT @UMI_Lab_AI: 🚨 New paper alert! 🚨. We’re excited to share our latest work on interpretability evaluation:. "Evaluating Interpretable Met….
0
5
0
@SLapuschkin
Sebastian Lapuschkin
7 months
RT @FraunhoferHHI: Congrats to Fraunhofer HHI #XAI experts @WojciechSamek & @SLapuschkin!. @Handelsblatt has listed them among the most cit….
0
4
0
@SLapuschkin
Sebastian Lapuschkin
9 months
RT @di_lya: ✨Introducing quanda: an open-source library for benchmarking training data attribution (TDA) methods in PyTorch!. Quanda offers….
0
8
0
@SLapuschkin
Sebastian Lapuschkin
9 months
RT @anna_hedstroem: We (@di_lya, Galip Ümit Yolcu, Niklas Schmolenski, @wiegand_t, @WojciechSamek, @SLapuschkin + me) just launched QUANDA….
0
2
0
@SLapuschkin
Sebastian Lapuschkin
9 months
RT @UMI_Lab_AI: 🚨 New paper alert! 🚨. Excited to share Quanda—a toolkit for evaluating data attribution methods, accepted at #NeurIPS ATTRI….
0
4
0
@SLapuschkin
Sebastian Lapuschkin
10 months
RT @kirill_bykov: I'm very excited to share some great news: the paper I supervised has been accepted to #NeurIPS2024. Huge congratulations….
0
3
0
@SLapuschkin
Sebastian Lapuschkin
1 year
Go meet our #AttnLRP - Team at #ICML -- Reduan Achtibat, (Sayed) Erfan Hatefi and Aakriti Jain, right now!. Discuss how to best (ie, fast, cheap, faithful!) explain your transformer-based model during Poster Session 2!
Tweet media one
1
2
17
@SLapuschkin
Sebastian Lapuschkin
1 year
🚨 AttnLRP is at #ICML! Explain your transformers in a fast, efficient and best possible way! 🚨. more info: paper: code:
Tweet media one
Tweet media two
2
4
13
@SLapuschkin
Sebastian Lapuschkin
1 year
RT @anna_hedstroem: Our latest paper is out! . On Tuesday, 17 July, we will present our latest work "A Fresh Look at Sanity Checks for Sali….
0
3
0
@SLapuschkin
Sebastian Lapuschkin
1 year
New paper alert!. With EMPRT and SMPRT we fix some glaring issues with the original Model Parameter Randomization Test (MPRT). Visit our talk at the 2nd XAI World Conference in Valetta, Malta, on July 17th!. more info & paper:
Tweet media one
0
3
14
@SLapuschkin
Sebastian Lapuschkin
1 year
Much appreciation and Thanks to @FraunhoferHHI for the support of this work.
0
0
1
@SLapuschkin
Sebastian Lapuschkin
1 year
Another paper presented during CVPR from my group!.With PURE, we can purify neural representations for more crisp, precise and contextual information. More info / code / paper here: Kudos to Max Dreyer, Erblina Purellku, @jvielhaben, @WojciechSamek
Tweet media one
1
2
7
@SLapuschkin
Sebastian Lapuschkin
1 year
Thank you to co-authors Maximilian Dreyer, Reduan Achtibat and @WojciechSamek , all affiliated to @FraunhoferHHI.
0
0
1
@SLapuschkin
Sebastian Lapuschkin
1 year
RT @di_lya: Check out our paper "Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression" at….
0
3
0
@SLapuschkin
Sebastian Lapuschkin
1 year
New paper alert! Check out our paper called "Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations" (PCX) scheduled for presentation during #CVPR this year!. date&time/paper/code/project page:
Tweet media one
1
4
11
@SLapuschkin
Sebastian Lapuschkin
1 year
RT @FraunhoferHHI: How can we use AI to automate our #rail transportation, when we all know how bad mobile data service can be on the train….
0
2
0