Zeynep Akata
@zeynepakata.bsky.social
Liesel Beckmann Distinguished Professor of Computer Science at Technical University of Munich and Director of the Institute for Explainable ML at Helmholtz Munich
We are looking for PhD students via the @ellis.eu and @munichcenterml.bsky.social PhD programs!
🎓PhD application season is back!
We’re hiring ONLY through the ELLIS @ellis.eu and the MCML
@munichcenterml.bsky.social
📌Please denote Prof. Zeynep Akata @zeynepakata.bsky.social as your preferred supervisor!
👉 Link to ELLIS (ellis.eu/news/ellis-p...) and MCML (mcml.ai/opportunitie...)
We’re hiring ONLY through the ELLIS @ellis.eu and the MCML
@munichcenterml.bsky.social
📌Please denote Prof. Zeynep Akata @zeynepakata.bsky.social as your preferred supervisor!
👉 Link to ELLIS (ellis.eu/news/ellis-p...) and MCML (mcml.ai/opportunitie...)
October 24, 2025 at 10:27 AM
We are looking for PhD students via the @ellis.eu and @munichcenterml.bsky.social PhD programs!
What if your CBM actually doesn’t look at attributes when it explains the classification decision? We suggest to use this dataset and method to generate realistic images with unusual attributes to stress-test explainability methods. @jessica-bader.bsky.social is at ICCV to talk to you about it!
1/
SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions
@jessica-bader.bsky.social , @lgirrbach.bsky.social , Stephan Alaniz, @zeynepakata.bsky.social
[Paper]: arxiv.org/pdf/2507.23784
[Code]: github.com/ExplainableM...
📍Hall I #2142
🕑Oct 23, Poster Session 5
SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions
@jessica-bader.bsky.social , @lgirrbach.bsky.social , Stephan Alaniz, @zeynepakata.bsky.social
[Paper]: arxiv.org/pdf/2507.23784
[Code]: github.com/ExplainableM...
📍Hall I #2142
🕑Oct 23, Poster Session 5
October 20, 2025 at 2:14 PM
What if your CBM actually doesn’t look at attributes when it explains the classification decision? We suggest to use this dataset and method to generate realistic images with unusual attributes to stress-test explainability methods. @jessica-bader.bsky.social is at ICCV to talk to you about it!
Reposted by Zeynep Akata
Are you at #ICCV2025? 🎉 @iccv.bsky.social
EML Munich is presenting two poster papers—come say hi to our authors!
Details in the thread 👇
EML Munich is presenting two poster papers—come say hi to our authors!
Details in the thread 👇
October 20, 2025 at 12:35 PM
Are you at #ICCV2025? 🎉 @iccv.bsky.social
EML Munich is presenting two poster papers—come say hi to our authors!
Details in the thread 👇
EML Munich is presenting two poster papers—come say hi to our authors!
Details in the thread 👇
We got two papers of two orthogonal methods for interpretability and one paper of a GenAI method at @neuripsconf.bsky.social 2025 🔥 Please checkout the details in the thread below.
🔥We celebrate 3 papers accepted to NeurIPS 2025, see you in San Diego! 🥳Topics include diffusion models, sparse autoencoders (SAEs) and neural chunking. See the thread for highlights👇
October 13, 2025 at 4:41 PM
We got two papers of two orthogonal methods for interpretability and one paper of a GenAI method at @neuripsconf.bsky.social 2025 🔥 Please checkout the details in the thread below.
Reposted by Zeynep Akata
Unfortunately, our submission to #NeurIPS didn’t go through with (5,4,4,3). But because I think it’s an excellent paper, I decided to share it anyway.
We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!
📝 arxiv.org/abs/2412.06014
We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!
📝 arxiv.org/abs/2412.06014
Post-hoc Probabilistic Vision-Language Models
Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descripti...
arxiv.org
September 18, 2025 at 8:34 PM
Unfortunately, our submission to #NeurIPS didn’t go through with (5,4,4,3). But because I think it’s an excellent paper, I decided to share it anyway.
We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!
📝 arxiv.org/abs/2412.06014
We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!
📝 arxiv.org/abs/2412.06014
Reposted by Zeynep Akata
I am hiring PhD students and/or Postdocs, to work on the theory of explainable machine learning. Please apply through Ellis or IMPRS, deadlines end october/mid november. In particular: Women, where are you? Our community needs you!!!
imprs.is.mpg.de/application
ellis.eu/news/ellis-p...
imprs.is.mpg.de/application
ellis.eu/news/ellis-p...
September 17, 2025 at 6:18 AM
I am hiring PhD students and/or Postdocs, to work on the theory of explainable machine learning. Please apply through Ellis or IMPRS, deadlines end october/mid november. In particular: Women, where are you? Our community needs you!!!
imprs.is.mpg.de/application
ellis.eu/news/ellis-p...
imprs.is.mpg.de/application
ellis.eu/news/ellis-p...
It is an honor to receive the ZukunftsWissen award from the German National Academy of the Sciences @leopoldina.org and Commerzbank-Stiftung 😊🙏🎉
🎉🎬 @zeynepakata.bsky.social erhält den diesjährigen „ZukunftsWissen“-Preis von Leopoldina & Commerzbank-Stiftung. Die Informatikerin @tum.de und Helmholtz_Munich spricht über ihre Forschung zur erklärbaren #KI. Zum Video auf YouTube: www.youtube.com/watch?v=ZqIH...
„ZukunftsWissen“-Preis 2025 | Die Preisträgerin Zeynep Akata im Interview
YouTube video by Nationale Akademie der Wissenschaften Leopoldina
www.youtube.com
September 18, 2025 at 10:39 AM
It is an honor to receive the ZukunftsWissen award from the German National Academy of the Sciences @leopoldina.org and Commerzbank-Stiftung 😊🙏🎉
NeurIPS has decided to do what ICLR did: As a SAC I received the message 👇 This is wrong! If the review process cannot handle so many papers, the conference needs yo split instead of arbitrarily rejecting 400 papers.
August 28, 2025 at 4:12 PM
NeurIPS has decided to do what ICLR did: As a SAC I received the message 👇 This is wrong! If the review process cannot handle so many papers, the conference needs yo split instead of arbitrarily rejecting 400 papers.
Congratulations Karsten @confusezius.bsky.social for a wonderful PhD journey that ended with a summa cum laude 🎉 It is rare that a PhD researcher creates a paradigm shift in a research group: I am grateful for everything that I learned from you 😉 Best of luck at Google DM in Zurich!
🎓PhD Spotlight: Karsten Roth
Celebrate @confusezius.bsky.social , who defended his PhD on June 24th summa cum laude!
🏁 His next stop: Google DeepMind in Zurich!
Join us in celebrating Karsten's achievements and wishing him the best for his future endeavors! 🥳
Celebrate @confusezius.bsky.social , who defended his PhD on June 24th summa cum laude!
🏁 His next stop: Google DeepMind in Zurich!
Join us in celebrating Karsten's achievements and wishing him the best for his future endeavors! 🥳
August 4, 2025 at 2:17 PM
Congratulations Karsten @confusezius.bsky.social for a wonderful PhD journey that ended with a summa cum laude 🎉 It is rare that a PhD researcher creates a paradigm shift in a research group: I am grateful for everything that I learned from you 😉 Best of luck at Google DM in Zurich!
Reposted by Zeynep Akata
I love the #eurips initiative! But to live up to its potential, it should be accepted an official #neurips conference location (similar to Mexico City) and not just an addon! Then we would save C02, rather than adding to it!!! What can we do to achieve this?
EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
July 21, 2025 at 4:30 PM
Reposted by Zeynep Akata
🚨 Poster at #ICML2025!
How can LLMs really keep up with the world?
Come by E-2405 on July 15th (4:30–7:00pm) to check out WikiBigEdit – our new benchmark to test lifelong knowledge editing in LLMs at scale.
🔗 Real-world updates
📈 500k+ QA edits
🧠 Editing vs. RAG vs. CL
How can LLMs really keep up with the world?
Come by E-2405 on July 15th (4:30–7:00pm) to check out WikiBigEdit – our new benchmark to test lifelong knowledge editing in LLMs at scale.
🔗 Real-world updates
📈 500k+ QA edits
🧠 Editing vs. RAG vs. CL
July 14, 2025 at 4:58 PM
🚨 Poster at #ICML2025!
How can LLMs really keep up with the world?
Come by E-2405 on July 15th (4:30–7:00pm) to check out WikiBigEdit – our new benchmark to test lifelong knowledge editing in LLMs at scale.
🔗 Real-world updates
📈 500k+ QA edits
🧠 Editing vs. RAG vs. CL
How can LLMs really keep up with the world?
Come by E-2405 on July 15th (4:30–7:00pm) to check out WikiBigEdit – our new benchmark to test lifelong knowledge editing in LLMs at scale.
🔗 Real-world updates
📈 500k+ QA edits
🧠 Editing vs. RAG vs. CL
Reposted by Zeynep Akata
How can we circumvent data scarcity in the time series domain?
We propose to leverage pretrained ViTs (e.g., CLIP, DINOv2) for time series classification and outperform time series foundation models (TSFMs).
📄 Preprint: arxiv.org/abs/2506.08641
💻 Code: github.com/ExplainableM...
We propose to leverage pretrained ViTs (e.g., CLIP, DINOv2) for time series classification and outperform time series foundation models (TSFMs).
📄 Preprint: arxiv.org/abs/2506.08641
💻 Code: github.com/ExplainableM...
July 3, 2025 at 7:59 AM
How can we circumvent data scarcity in the time series domain?
We propose to leverage pretrained ViTs (e.g., CLIP, DINOv2) for time series classification and outperform time series foundation models (TSFMs).
📄 Preprint: arxiv.org/abs/2506.08641
💻 Code: github.com/ExplainableM...
We propose to leverage pretrained ViTs (e.g., CLIP, DINOv2) for time series classification and outperform time series foundation models (TSFMs).
📄 Preprint: arxiv.org/abs/2506.08641
💻 Code: github.com/ExplainableM...
It is a great honor to receive the ZukunftsWissen Prize 2025 from the German Academy of the Sciences @leopoldina.org with generous support of the commerzbank foundation 🎉 This achievement wouldn’t have been possible without my wonderful group @eml-munich.bsky.social @tum.de @helmholtz.de
🎉Der „ZukunftsWissen“-Preis 2025 von Leopoldina und Commerzbank-Stiftung geht an Zeynep Akata (@zeynepakata.bsky.social) @tum.de / @helmholtz.de. Die Informatikerin erhält die mit 50.000 € dotierte Auszeichnung für ihre Forschung zur erklärbaren #KI.
www.leopoldina.org/presse-1/nac...
www.leopoldina.org/presse-1/nac...
June 25, 2025 at 1:59 PM
It is a great honor to receive the ZukunftsWissen Prize 2025 from the German Academy of the Sciences @leopoldina.org with generous support of the commerzbank foundation 🎉 This achievement wouldn’t have been possible without my wonderful group @eml-munich.bsky.social @tum.de @helmholtz.de
From classification to retrieval to generative models compositionality has been central to @shyamgopal.bsky.social‘s PhD. Congratulations to Shyam’s very successful journey 🎉 We are looking forward to his upcoming PhD defense next week in Tübingen!
🎓PhD Spotlight: Shyamgopal Karthik
Celebrate @shyamgopal.bsky.social , who will defend his PhD on 23rd June! Shyam has been a PhD student @unituebingen.bsky.social since October 2021, supervised by @zeynepakata.bsky.social.
Celebrate @shyamgopal.bsky.social , who will defend his PhD on 23rd June! Shyam has been a PhD student @unituebingen.bsky.social since October 2021, supervised by @zeynepakata.bsky.social.
June 18, 2025 at 11:57 AM
From classification to retrieval to generative models compositionality has been central to @shyamgopal.bsky.social‘s PhD. Congratulations to Shyam’s very successful journey 🎉 We are looking forward to his upcoming PhD defense next week in Tübingen!
Reposted by Zeynep Akata
📢 Landed in Nashville🎺 for #CVPR2025! The EML group is presenting 4 exciting papers — come say hi at our poster sessions! More details in the thread — see you there! 🏁🌟
June 11, 2025 at 1:13 PM
📢 Landed in Nashville🎺 for #CVPR2025! The EML group is presenting 4 exciting papers — come say hi at our poster sessions! More details in the thread — see you there! 🏁🌟
We are looking forward to Leonard Salewski’s PhD defense soon! 🎉 Leonard has done some interesting research on explainable AI as well as impersonation in (multimodal) LLMs, details below 👇
🎓PhD Spotlight: Leonard Salewski
Celebrate @l-salewski.bsky.social, who will defend his PhD on 24th June! 📸🎉
Celebrate @l-salewski.bsky.social, who will defend his PhD on 24th June! 📸🎉
May 27, 2025 at 4:31 AM
We are looking forward to Leonard Salewski’s PhD defense soon! 🎉 Leonard has done some interesting research on explainable AI as well as impersonation in (multimodal) LLMs, details below 👇
We are looking forward to Thomas Hummel‘s @hummelth.bsky.social PhD defense soon. If you are looking for experts in video action recognition or retrieval, he is to be contacted 😉
🎓PhD Spotlight: Thomas Hummel
A spotlight on our one and only @hummelth.bsky.social , who will defend his PhD on 23rd June! 🎉
Thomas started his PhD in 2020 at @unituebingen.bsky.social as part of the IMPRS-IS program under the supervision of @zeynepakata.bsky.social . 👇 His full story:
A spotlight on our one and only @hummelth.bsky.social , who will defend his PhD on 23rd June! 🎉
Thomas started his PhD in 2020 at @unituebingen.bsky.social as part of the IMPRS-IS program under the supervision of @zeynepakata.bsky.social . 👇 His full story:
May 19, 2025 at 7:22 PM
We are looking forward to Thomas Hummel‘s @hummelth.bsky.social PhD defense soon. If you are looking for experts in video action recognition or retrieval, he is to be contacted 😉
Reposted by Zeynep Akata
🚨 Happy to announce that one paper, "Understanding the Limits of Lifelong Knowledge Editing in LLMs", is accepted at #icml2025 ! Congrats to @lukasthede.bsky.social , @confusezius.bsky.social , Matthias Bethge, @zeynepakata.bsky.social , and @tomhartvigsen.bsky.social . 👇 Highlights in the thread
May 14, 2025 at 10:55 AM
🚨 Happy to announce that one paper, "Understanding the Limits of Lifelong Knowledge Editing in LLMs", is accepted at #icml2025 ! Congrats to @lukasthede.bsky.social , @confusezius.bsky.social , Matthias Bethge, @zeynepakata.bsky.social , and @tomhartvigsen.bsky.social . 👇 Highlights in the thread
Reposted by Zeynep Akata
Our paper is now out in Nature Human Behaviour! 🎉 We use games from behavioural economics to explore how LLMs behave in repeated social interactions, revealing both self-interested strengths and coordination blind spots, and propose strategies to improve AI-human collaboration.
What happens when Large Language models play repeated economic games? This new study from @elifakata.bsky.social et al investigates across a range of models and games.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Playing repeated games with large language models - Nature Human Behaviour
Large language models perform well in self-interested games such as the iterated Prisoner’s Dilemma but struggle in games that require coordination. Social reasoning strategies can improve cooperative...
www.nature.com
May 12, 2025 at 12:14 PM
Our paper is now out in Nature Human Behaviour! 🎉 We use games from behavioural economics to explore how LLMs behave in repeated social interactions, revealing both self-interested strengths and coordination blind spots, and propose strategies to improve AI-human collaboration.
Our second PhD spotlight, Jae Myung Kim is about to complete his PhD within the @ellis.eu and IMPRS-IS PhD programs, big congratulations to Jae Myung 🎈🎊🎉
🎓PhD Spotlight: Jae Myung Kim
We’re thrilled to celebrate Jae Myung Kim, who will defend his PhD on 25th June! 🎉
Jae Myung began his PhD at @unituebingen.bsky.social as part of the ELLIS & IMPRS-IS programs, advised by @zeynepakata.bsky.social and collaborating closely with Cordelia Schmid.
We’re thrilled to celebrate Jae Myung Kim, who will defend his PhD on 25th June! 🎉
Jae Myung began his PhD at @unituebingen.bsky.social as part of the ELLIS & IMPRS-IS programs, advised by @zeynepakata.bsky.social and collaborating closely with Cordelia Schmid.
May 12, 2025 at 7:48 PM
Our second PhD spotlight, Jae Myung Kim is about to complete his PhD within the @ellis.eu and IMPRS-IS PhD programs, big congratulations to Jae Myung 🎈🎊🎉
Reposted by Zeynep Akata
One week left to apply, so please do... 😀
🚨 We're hiring! If you're excited about 🤖 ML/LLMs, 🧠 cognitive science, or 💭 computational psychiatry, come join us in Munich. Two fully funded PhDs @www.helmholtz-munich.de: tailored mentorship, international vibe, lots of room to grow.
📅 May 16th
🔗 hcai-munich.com/PhDHCAI.pdf
📅 May 16th
🔗 hcai-munich.com/PhDHCAI.pdf
May 9, 2025 at 1:07 PM
One week left to apply, so please do... 😀
@eml-munich.bsky.social is going to @cvprconference.bsky.social🎉 Checkout our papers below 👇
#CVPR2025 is heading to the 'Music City' — Nashville! 🎺 Join us from June 11–15. We're thrilled to announce that we'll be presenting four papers at @cvprconference.bsky.social! Check out the thread below for highlights, and feel free to stop by and chat with our authors! 📷👇
April 28, 2025 at 11:57 AM
@eml-munich.bsky.social is going to @cvprconference.bsky.social🎉 Checkout our papers below 👇
Reposted by Zeynep Akata
At #ICLR2025, #HelmholtzMunich researchers are sharing advancements in #MachineLearning.
👉 t1p.de/8jfgn
@fabiantheis.bsky.social @carstenmarr.bsky.social @stes.io @zeynepakata.bsky.social @ericschulz.bsky.social @vincefort.bsky.social @iclr-conf.bsky.social
👉 t1p.de/8jfgn
@fabiantheis.bsky.social @carstenmarr.bsky.social @stes.io @zeynepakata.bsky.social @ericschulz.bsky.social @vincefort.bsky.social @iclr-conf.bsky.social
April 24, 2025 at 11:14 AM
At #ICLR2025, #HelmholtzMunich researchers are sharing advancements in #MachineLearning.
👉 t1p.de/8jfgn
@fabiantheis.bsky.social @carstenmarr.bsky.social @stes.io @zeynepakata.bsky.social @ericschulz.bsky.social @vincefort.bsky.social @iclr-conf.bsky.social
👉 t1p.de/8jfgn
@fabiantheis.bsky.social @carstenmarr.bsky.social @stes.io @zeynepakata.bsky.social @ericschulz.bsky.social @vincefort.bsky.social @iclr-conf.bsky.social
Reposted by Zeynep Akata
We’ve landed in Singapore for #ICLR2025!
The EML group is presenting 4 exciting papers — come say hi at our poster sessions! 👇Let's chat!
More details in the thread — see you there! 🌟
The EML group is presenting 4 exciting papers — come say hi at our poster sessions! 👇Let's chat!
More details in the thread — see you there! 🌟
April 22, 2025 at 1:44 PM
We’ve landed in Singapore for #ICLR2025!
The EML group is presenting 4 exciting papers — come say hi at our poster sessions! 👇Let's chat!
More details in the thread — see you there! 🌟
The EML group is presenting 4 exciting papers — come say hi at our poster sessions! 👇Let's chat!
More details in the thread — see you there! 🌟
Check out our first profile spotlight featuring @merceaotniel.bsky.social who will be defending his thesis this Wednesday 👏
🎓 PhD Spotlight: Otniel-Bogdan Mercea
We’re excited to celebrate @merceaotniel.bsky.social , who will defend his PhD on April 16th! See the thread to feature his research highlights👇
We’re excited to celebrate @merceaotniel.bsky.social , who will defend his PhD on April 16th! See the thread to feature his research highlights👇
April 14, 2025 at 11:28 AM
Check out our first profile spotlight featuring @merceaotniel.bsky.social who will be defending his thesis this Wednesday 👏