We are proud to be part of the @ellis.eu community. @margretkeuper.bsky.social has been an Ellis Fellow for some time, now @janiskeuper.bsky.social also joined as a Member...

2nd paper accepted at #ICLR 26: "RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo" openreview.net/forum?id=Reb...

New paper out (accepted at #ICLR 26) "GeoDiv: Framework for Measuring Geographical Diversity in Text-to-Image Models" openreview.net/forum?id=Wli...

We are proud to announce the first CV4Edu workshop at #CVPR2026 in Denver. We are bringing together researchers in AI in education, computer vision, and human-centered AI, and invite you to submit a full, short, or position paper to our workshop.

Open PostDoc position: Hardware aware NAS / Model Distillation / Model Compression of Vision and Language Models for Humanoid Robots... www.keuper-labs.org/team/#open-p...

New paper out. (Accepted at TMLR with J2C Certification!): mSOP-765k: A Benchmark For Multi-Modal Structured Output Predictions. www.msop-765k.org

A small step for science, quite a big one for us: reaching 10k citations. Thanks to all co-authors! scholar.google.de/citations?hl...

Say hello to @margretkeuper.bsky.social, Prof at Uni Mannheim 🇩🇪 and ELLIS Fellow at ELLIS Unit Saarbrücken. Her area of research is machine learning for computer vision. Her advice: When your research goals are much harder than anticipated, take a step back to see the big picture. #WomenInELLIS

ICCV 2025 🌺 Aloha from Hawaii! MPI-INF (D2) is presenting 4 papers this year (one Highlight). Thread 👇

Excited to have DCBMs at #ICCV2025 - come by ballroom A tomorrow to meet @shashank-agnihotri.bsky.social presenting our joint work with @patrickknab.bsky.social @smarton.bsky.social Christian Bartelt @margretkeuper.bsky.social @keuper-labs.bsky.social #UniMa

Our new paper (accepted at #NeurIPS UrbanAI Workshop): "Real-time Prediction of Urban Sound Propagation with Conditioned Normalizing Flows" arxiv.org/pdf/2510.04510 is part of our work using generative model to predict complex physics www.physics-gen.org

Our GCPR @gcpr-by-dagm.bsky.social paper (Oral) "Assessing Foundation Models for Mold Colony Detection with Limited Training Data" is now on Arxiv: arxiv.org/pdf/2510.00561

Our #NeurIPS ORAL "MaxSup: Overcoming Representation Collapse in Label Smoothing", joint work with @cispa.de, is now on Arxiv: arxiv.org/pdf/2502.15798

Happy to discuss the past, present, and future of DCBMs at #GCPR2025. @patrickknab.bsky.social @smarton.bsky.social Christian Bartelt @margretkeuper.bsky.social @keuper-labs.bsky.social @maopenscience.bsky.social

Following up on the discussions about prompt injections which were found in Arxiv paper sources - indicating that some authors try to manipulate LLM generate reviews: beyond the ethical implications, I was wondering if this actually works and did some experiments... arxiv.org/abs/2509.10248

🎉Our TMLR paper FlowBench is out! Optical flow keeps getting better on benchmarks, but reliability and generalization remain a challenge for safety-critical tasks. FlowBench provides the most comprehensive robustness benchmark to date. 📄 openreview.net/forum?id=Kh4... 💻 github.com/shashankskag...

🚨 10 days left! Submit to L2S: Learning to Sense @ NeurIPS 2025 📡🤖 📅 Dec 6/7, San Diego, USA 🎤 Invited speakers from academia & industry 🌐 Details & CFP: sites.google.com/view/l2s-wor... Let’s shape the future of how machines sense! #L2S #NeurIPS2025 #NeurIPSWorkshop

🚀 Calling all ML, CV and Sensor Enthusiasts! Join us at the L2S: Learning to Sense Workshop at #NeurIPS2025 ! 🗓 Date: December 6/7, 2025 📍 Location: San Diego, USA sites.google.com/view/l2s-wor...

Congratulations to @juliagrabinski.bsky.social for successfully defending her PhD thesis on "Multifaceted Analysis of Deep Convolutional Neural Networks and Novel Fourier Modules" 🥳🎓

Poster is up and we are looking forward to the #ICML2025 poster session. Come join @patrickknab.bsky.social and me at Poster #W-214 presenting our work with @smarton.bsky.social, Christian Bartelt, and @margretkeuper.bsky.social @margretkeuper.bsky.social #UniMa

Join us on Thursday 11-13 in poster hall West #214 to discuss image segments as concepts. #ICML2025 @patrickknab.bsky.social @smarton.bsky.social Christian bartelt @margretkeuper.bsky.social @keuper-labs.bsky.social

Attending #ICML2025? Watch out for our paper "DCBM: Data-Efficient Visual Concept Bottleneck Models" presented by @katharinaprasse.bsky.social -> github.com/KathPra/DCBM

Congratulations to @paulgavrikov.bsky.social for an excellent PhD defense today!

Two papers with @keuper-labs.bsky.social participation accepted at #ICCV2025: 1) Scientific figure generation with TikZero, it generates scientific figures from text as high-level, human-interpretable, and editable graphics programs -> arxiv.org/pdf/2503.11509

Presenting our poster #45 today at #CVPR in poster session 3: "PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?" cvpr.thecvf.com/virtual/2025...

Excited to share our work at the WiCV Workshop, CVPR 2025! Catch our presentation today from 3:00–4:30 PM (Nashville time)!

We are presenting 7 papers (main conference+ workshops) at #CVPR2025 www.keuper-labs.org/research/?se...

Announcing our amazing Keynote Speakers for #GCPR2025: Venkatesh Babu Radhakrishnan, IISc Dima Damen, University of Bristol @dimadamen.bsky.social Efstratios Gavves, University of Amsterdam @egavves.bsky.social Stefanie Jegelka, MIT EECS and TU Munich ‪@tum.de Alex Kolesnikov, OpenAI @kolesnikov.ch

Looking forward to visiting this beautiful city for #GCPR2025, but the deadline for submission is too close? Worry no more, we have now extended the deadline for regular and special track submissions to 11th June! www.dagm-gcpr.de/year/2025/su... All the best!👍 Photo: @paulgavrikov.bsky.social

Announcing the Amazing Chairs for #GCPR2025! General Chairs: Thomas Brox and Abhinav Valada Program Chairs: Margret Keuper and Francesco Locatello More announcements coming soon! Stay tuned....

Happy to announce that we have an #ICML paper! Our DCBMs use cropped image segmentats for model interpretability. It was great collaborating with @patrickknab.bsky.social, @smarton.bsky.social , Christian Bartelt, and @margretkeuper.bsky.social @keuper-labs.bsky.social

Visit our poster presentations at #ICLR2025 iclr.cc/virtual/2025...

On Thursday, I'll be presenting our paper "Can We Talk Models Into Seeing the World Differently?" (#328) at ICLR 2025 in Singapore! If you're attending or just around Singapore, l'd love to connect—feel free to reach out! Also, I’m exploring postdoc or industry opportunities–happy to chat!

Ever wondered how big convolutional filters should really be? 🤔 We push things to the limit literally. Infinite-size convs, but efficient. “As Large as It Gets – Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters” at #ICLR2025, Singapore! #ML #DeepLearning #ComputerVision

Hello world, we are now on Bluesky 🦋! Follow us to receive updates on exciting research and projects from our group! #computervision #machinelearning #research

Team #GirlsDay 2025 with Julie missing. It was great exploring pixels and their power with 19 bright, young minds. Feeling inspired while hoping to inspire. It was a delight @margretkeuper.bsky.social @tejaswinimedi.bsky.social @keuper-labs.bsky.social #UniMannheim

New pre-print: "FOUNDATION MODELS FOR SEISMIC DATA PROCESSING: AN EXTENSIVE REVIEW". Interesting findings for #Seismic / #Geophysic Applications: I) hierarchical models outperform basic approaches, II) pre-training on natural images actually helps in low-data settings. arxiv.org/pdf/2503.02113

@hf.co featured our latest CVPR paper on the physical correctness of generative model in daily papers: huggingface.co/papers/2503.... and is hosting the benchmark data: huggingface.co/datasets/msp... Project page: www.physics-gen.org

Our latest paper accepted at #CVPR2025 is now arxiv: "PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?" arxiv.org/abs/2503.05333

Hi everyone 😀 ! I'm excited to present our work FAIR-TAT, an adversarial training framework to address fairness issues in DNN classifiers. Catch our poster at WACV 2025 on March 3rd, from 11:15 AM. Happy to connect and discuss! 📄 arxiv.org/pdf/2410.23142 @margretkeuper.bsky.social & #Steffen Jung

Inspired and grateful after discussing our work on minimum cost multicuts for visual frame detection. Thanks to everyone at #wacv25! @margretkeuper.bsky.social @isaacbravo.bsky.social @stefaniewalter.bsky.social @keuper-labs.bsky.social

Happy and sad to see @yumengli.bsky.social defend the PhD thesis supervised by @margretkeuper.bsky.social, Dan Zhang, and Anna Khoreva. We will miss you @keuper-labs.bsky.social

If you are at wacv and interested in visual frame detection, don't miss our poster, which will be presented by first author @katharinaprasse.bsky.social

Proud to announce that our paper "Can We Talk Models Into Seeing the World Differently?" was accepted at #ICLR2025 🇸🇬. This marks my last PhD paper, and we are honored that all 4 reviewers recommended acceptance, placing us in the top 6% of all submissions.

We will be presenting 3 papers at @iclr-conf.bsky.social : 1. Can we talk models into seeing the world differently? 2. VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis 3. "As large as it gets – Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters"

Today at #NeurIPS2024 Interpretable AI Workshop! Poster sessions are at 10am and 4pm. "How Do Training Methods Influence the Utilization of Vision Models?" arxiv.org/abs/2410.14470 We won’t be there, but Ruta Binkyte is presenting for us!

Congratulations to Mario Fernandez for his successful defense in Paris at ENS - "Towards deep learning for seismic processing". Joint supervision with Matthias Delescluse (ENS) FraunhoferITWM and @keuper-labs.bsky.social

New IJCV paper out: Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach. Joint work with Fraunhofer ITWM and @keuper-labs.bsky.social link.springer.com/content/pdf/...

www.keuper-labs.org is going blue ... we will post our latest research and other #ComputerVision and #MachineLearning news in our new #BlueSky channel ...