Zeynep Akata
@zeynepakata.bsky.social
1.8K followers 60 following 27 posts
Liesel Beckmann Distinguished Professor of Computer Science at Technical University of Munich and Director of the Institute for Explainable ML at Helmholtz Munich
Posts Media Videos Starter Packs
Reposted by Zeynep Akata
trappmartin.bsky.social
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
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
Reposted by Zeynep Akata
ulrikeluxburg.bsky.social
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...
zeynepakata.bsky.social
I am very sorry to hear this 😓
zeynepakata.bsky.social
It is an honor to receive the ZukunftsWissen award from the German National Academy of the Sciences @leopoldina.org and Commerzbank-Stiftung 😊🙏🎉
leopoldina.org
🎉🎬 @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
zeynepakata.bsky.social
Yes, you are right, we don’t know the official numbers yet. I was assuming that it is already 25%, but perhaps it is higher still.
zeynepakata.bsky.social
Yes, I think so too. But I don’t think this is a good idea. 25-30% is already a rather low acceptance rate.
zeynepakata.bsky.social
I am not sure. With the increasing number of submissions, to keep the number of accepted papers the same (due to space constraints), the acceptance rate needs to drop. This is how I read the email.
zeynepakata.bsky.social
There are so many alternative solutions: half a poster space, an alternative official location, remote presentation with physical presentation in an alternative location, just a remote presentation etc.
zeynepakata.bsky.social
Due to physical resource constraints, we currently estimate that around 300–400 of the candidate papers recommended for acceptance by the ACs will need to be rejected. We seek the support of our 41 SACs in addressing this distributed optimization problem in a fair and professional manner.
zeynepakata.bsky.social
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.
zeynepakata.bsky.social
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!
eml-munich.bsky.social
🎓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! 🥳
Reposted by Zeynep Akata
ulrikeluxburg.bsky.social
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?
euripsconf.bsky.social
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
Reposted by Zeynep Akata
lukasthede.bsky.social
🚨 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
Reposted by Zeynep Akata
simonroschmann.bsky.social
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...
zeynepakata.bsky.social
Thank you Julia! 👏
zeynepakata.bsky.social
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
leopoldina.org
🎉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...
Porträt einer jungen Frau mit schulterlangen, lockigen, rötlich-blonden Haaren, hellem Teint und hellen Augen. Sie steht draußen in einem Park und lächelt leicht in die Kamera. Logo des „ZukunftsWissen“-Preises. Links ein stilisiertes Kreisdiagramm mit vier farbigen Segmenten: grün, gelb, rot und blau. Das blaue Segment zeigt ein abstrahiertes menschliches Profil mit einem Netzwerk aus verbundenen Punkten. Rechts davon der Schriftzug: „ZukunftsWissen – Der Early Career Award von Leopoldina und Commerzbank-Stiftung“.
zeynepakata.bsky.social
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!
eml-munich.bsky.social
🎓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.
Reposted by Zeynep Akata
eml-munich.bsky.social
📢 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! 🏁🌟
zeynepakata.bsky.social
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 👇
eml-munich.bsky.social
🎓PhD Spotlight: Leonard Salewski

Celebrate @l-salewski.bsky.social, who will defend his PhD on 24th June! 📸🎉
zeynepakata.bsky.social
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 😉
eml-munich.bsky.social
🎓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:
Reposted by Zeynep Akata
eml-munich.bsky.social
🚨 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