Sign in

Computer Vision and Machine Learning at MPI Informatics

@cvml.mpi-inf.mpg.de
112 followers 39 following 51 posts

Computer Vision and Machine Department at the Max Planck Institute for Informatics | www.mpi-inf.mpg.de/departments/comp…

PostsRepliesMedia
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 07/09/2026
🎉 Our group is heading to #ECCV2026 in Malmö (September 8–12) with five papers across the main conference and workshops, including one Spotlight! Come find us at the posters, and a big thank you to all our collaborators!
063
Reposted by Computer Vision and Machine Learning at MPI Informatics
Sid @sidgairo18.bsky.social · 10/02/2026
🚀New preprint: DAVE — Distribution-aware Attribution via ViT Gradient DEcomposition. 1/11 🔍 What’s new: We fix a persistent issue in ViT explainability: unstable, artifact-heavy pixel attributions. DAVE yields fine-grained pixel-level maps without patch-grid saliency.
111
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 21/10/2025
AIM Project Page: eyad-alshami.github.io/aim-page/
eyad-alshami.github.io
AIM: Amending Inherent Interpretability via Self-Supervised Masking
AIM: Amending Inherent Interpretability via Self-Supervised Masking
000
Reposted by Computer Vision and Machine Learning at MPI Informatics
#ICCV2025 @iccv.bsky.social · 19/10/2025
ICCV 2025 kicks off tomorrow! We look forward to welcoming everyone to Hawaii 🌺
093
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 19/10/2025
cc: @janericlenssen.bsky.social al @xhxie.bsky.social
000
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 19/10/2025
MVGBench: “A Comprehensive Benchmark for Multi-view Generation Models” — measures 3D consistency & image quality for fair comparisons. By Xianghui Xie, Jan Eric Lenssen, Gerard Pons-Moll Project: virtualhumans.mpi-inf.mpg.de/MVGBench/
110
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 19/10/2025
cc: With @adagorgun.bsky.social
110
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 19/10/2025
VITAL: “More Understandable Feature Visualization via Distribution Alignment & Relevant Information Flow.” Fewer artifacts, more faithful internals, scales well. By Ada Görgün, Bernt Schiele, Jonas Fischer Project: adagorgun.github.io/VITAL-Project/
120
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 19/10/2025
cc: @eyadshami.bsky.social @shashank-agnihotri.bsky.social @margretkeuper.bsky.social
100
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 19/10/2025
AIM (Highlight 🎉): “Amending Inherent Interpretability via Self-Supervised Masking.” - Promotes genuine features over spurious ones—no extra annotations. By Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper
210
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 19/10/2025
cc: @oduenkel.bsky.social @wimmerthomas.bsky.social @adamkortylewski.bsky.social
110
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 19/10/2025
DIY-SC: “Do It Yourself—Learning Semantic Correspondence from Pseudo-Labels.” - Light-weight adapter on DINOv2 / SD+DINOv2 → SOTA on SPair-71k w/o keypoints. By O. Dünkel, T. Wimmer, C. Theobalt, C. Rupprecht, A. Kortylewski Page: genintel.github.io/DIY-SC
110
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 19/10/2025
ICCV 2025 🌺 Aloha from Hawaii! MPI-INF (D2) is presenting 4 papers this year (one Highlight). Thread 👇
1126
Reposted by Computer Vision and Machine Learning at MPI Informatics
Olaf Dünkel @oduenkel.bsky.social · 26/06/2025
Are you using DINOv2 for tasks that require semantic features? DIY-SC might be the alternative! It refines DINOv2 or SD+DINOv2 features and achieves a new SOTA on the semantic correspondence dataset SPair-71k when not relying on annotated keypoints! [1/6] genintel.github.io/DIY-SC
1153
Reposted by Computer Vision and Machine Learning at MPI Informatics
Thomas Wimmer @wimmerthomas.bsky.social · 16/10/2025
Super excited to introduce ✨ AnyUp: Universal Feature Upsampling 🔎 Upsample any feature - really any feature - with the same upsampler, no need for cumbersome retraining. SOTA feature upsampling results while being feature-agnostic at inference time. 🌐 wimmerth.github.io/anyup/
2285
Reposted by Computer Vision and Machine Learning at MPI Informatics
Sweta Mahajan @swetamahajan.bsky.social · 08/09/2025
🚨 Call for Questions! 🚨 We are inviting the community and the stakeholders to submit questions, which will be discussed with our experts at the workshop! 🎤💡 👉 Submit your questions: forms.gle/8cYb4Ce3dGHi... Workshop: excv-workshop.github.io @iccv.bsky.social #ICCV2025 #eXCV
165
Reposted by Computer Vision and Machine Learning at MPI Informatics
Max Planck Institute for Informatics @mpi-inf.mpg.de · 21/08/2025
Kurt Mehlhorn, Founding Director of MPI for Informatics, was awarded the Saarland Order of Merit yesterday by Minister President Anke Rehlinger. The award recognizes his life’s work, from advancing algorithmic research to mentoring researchers and helping build key institutions. More: sic.link/merit
sic.link
Kurt Mehlhorn awarded the Saarland Order of Merit
Minister President Rehlinger presented the order during a ceremonial event at the Saarland State Chancellery.
021
Reposted by Computer Vision and Machine Learning at MPI Informatics
Sukrut Rao @sukrutrao.bsky.social · 14/08/2025
Are you an XAI researcher attending #ICCV2025? Submit your recently published work — at CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI etc. — to the eXCV Workshop for the opportunity to further showcase your work! Published papers can be submitted as is, no rewriting necessary. @iccv.bsky.social
eXCV Workshop at ICCV 2025, Submission deadline August 15.
144
Reposted by Computer Vision and Machine Learning at MPI Informatics
Nina Shvetsova @ninashv.bsky.social · 08/08/2025
🚀 UTD is now fully released! Code ✅ Models ✅ 2M video descriptions ✅ Debiased splits for 12 datasets ✅ Everything you need to benchmark video models more fairly is now public: 🔗 github.com/ninatu/utd-p... 🎥 Let’s make video understanding actually about video understanding.
092
Reposted by Computer Vision and Machine Learning at MPI Informatics
Shashank Agnihotri @shashank-agnihotri.bsky.social · 24/07/2025
People often use synthetic corruptions to test model robustness, but do these reflect real-world challenges? We explore this in detail in our CVPR 2025 Workshop paper: Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions? arxiv.org/abs/2505.04835 by: @margretkeuper.bsky.social
011
Reposted by Computer Vision and Machine Learning at MPI Informatics
Sweta Mahajan @swetamahajan.bsky.social · 18/07/2025
🚨Deadline Extension Alert! Our Non-proceedings track is open till August 15th for the eXCV workshop at ICCV. Our nectar track accepts published papers, as is. More info at: excv-workshop.github.io @iccv.bsky.social #ICCV2025
155
Reposted by Computer Vision and Machine Learning at MPI Informatics
Sid @sidgairo18.bsky.social · 24/07/2025
⏳Still need to wait for your last experiment results? 📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025 Looking forward to your submissions! cv4dc.github.io/2025/
022
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 13/07/2025
📄 spatialreasoners.github.io 🔗 github.com/spatialreaso...
spatialreasoners.github.io
🌀Spatial Reasoners
000
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 13/07/2025
4/ "🌀Spatial Reasoners for Continuous Variables in Any Domains" by @bartpog.bsky.social, @chriswewer.bsky.social, Bernt Schiele, and @janericlenssen.bsky.social (CODEML Workshop) 🔍 Software framework for training Spatial Reasoning Models in any domain
Image for "🌀Spatial Reasoners for Continuous Variables in Any Domains"
100
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 13/07/2025
🔍 Can you really trust the explanations your classifier gives you? We show which pixels in the input are provably important to the classifier’s prediction within a radius around the input. 📄 openreview.net/pdf?id=NngoE... 🔗 github.com/AlaaAnani/ce...
openreview.net
100
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 13/07/2025
3/ "Pixel-level Certified Explanations via Randomized Smoothing" by @aanani.bsky.social, Tobias Lorenz, Mario Fritz, and Bernt Schiele
Image for "Pixel-level Certified Explanations via Randomized Smoothing"
110
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 13/07/2025
📄 arxiv.org/abs/2502.21075 🔗 geometric-rl.mpi-inf.mpg.de/srm/ 🔗 github.com/Chrixtar/SRM
arxiv.org
Spatial Reasoning with Denoising Models
We introduce Spatial Reasoning Models (SRMs), a framework to perform reasoning over sets of continuous variables via denoising generative models. SRMs infer continuous representations on a set of unob...
100
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 13/07/2025
2/ "Spatial Reasoning with Denoising Models" by @chriswewer.bsky.social, @bartpog.bsky.social, Bernt Schiele, and @janericlenssen.bsky.social 🔍 Can image generators solve visual Sudoku? Naively, no, with sequentialization and the correct order, they can!
Image for "Spatial Reasoning with Denoising Models"
100
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 13/07/2025
📄 arxiv.org/abs/2412.11576 🔗 github.com/KathPra/DCBM
arxiv.org
DCBM: Data-Efficient Visual Concept Bottleneck Models
Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted ...
100
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 13/07/2025
1/ "DCBM: Data-Efficient Visual Concept Bottleneck Models" by @katharinaprasse.bsky.social*, @patrickknab.bsky.social*, Sascha Marton, Christian Bartelt, and @margretkeuper.bsky.social 🔍 Data-efficient CBMs (DCBMs) generate concepts from image regions detected by segmentation or detection models
Image for "DCBM: Data-Efficient Visual Concept Bottleneck Models"
110
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 13/07/2025
Papers being presented from our group at #ICML2025! Congratulations to all the authors! To know more, visit us in the poster sessions! A 🧵with more details: @icmlconf.bsky.social @mpi-inf.mpg.de
Papers accepted at ICML 2025 from the Computer Vision and Machine Learning Department at the Max Planck Institute for Informatics.
1215
Reposted by Computer Vision and Machine Learning at MPI Informatics
Sid @sidgairo18.bsky.social · 12/07/2025
📣 Proceeding track's results are out. 🎉 Congratulations to all the authors whose papers were accepted. We can't wait to meet you at @iccv.bsky.social in Hawaii on Oct 19th. ⏰ Our non-proceeding track is still accepting submissions until July 20th! Details in the comments
172
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 05/07/2025
🎉 Congrats to Yue Fan on defending his PhD: "Improving Representation Learning from Data and Model Perspectives: Semi-Supervised Learning and Foundation Models" 🧑‍🎓 He is now at Genmo.ai as a Research Engineer working on video generation! 🚀 More: yue-fan.github.io All the best!
180
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 01/07/2025
Congratulations to our PhD alumna @annakukleva.bsky.social for being awarded the prestigious Otto Hahn Medal by @maxplanck.de! 🎉
081
Reposted by Computer Vision and Machine Learning at MPI Informatics
Thomas Wimmer @wimmerthomas.bsky.social · 26/06/2025
🚀 Just accepted to ICCV 2025! In DIY-SC, we improve foundational features using a light-weight adapter trained with carefully filtered and refined pseudo-labels. 🔧 Drop-in alternative to plain DINOv2 features! 📦 Code + pre-trained weights available now. 🔥 Try it in your next vision project!
1102
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 26/06/2025
Submission deadline is today!
041
Reposted by Computer Vision and Machine Learning at MPI Informatics
Sweta Mahajan @swetamahajan.bsky.social · 23/06/2025
Submission Deadline is extended by 6 days. #ICCV2025 @iccv.bsky.social
085
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 26/06/2025
@mattiasegu.bsky.social
000
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 26/06/2025
A heart congratulations to the freshly minted Dr. Mattia Segù on successfully defending his PhD, Congratulazioni!!! 🎉 🎓. His thesis is titled: Learning to Track: From Limited Supervision to Long-range Sequence Modeling Checkout his web-page to learn more about his work: mattiasegu.github.io
250
Reposted by Computer Vision and Machine Learning at MPI Informatics
Sukrut Rao @sukrutrao.bsky.social · 14/06/2025
Join us in taking stock of the state of the field of explainability in computer vision, at our Workshop on Explainable Computer Vision: Quo Vadis? at #ICCV2025! @iccv.bsky.social
Call for papers at the eXCV workshop at ICCV 2025.
1135
Reposted by Computer Vision and Machine Learning at MPI Informatics
Jan Eric Lenssen @janericlenssen.bsky.social · 12/06/2025
At #CVPR2025 and working on consistency in video and multi-view generative models? Come and visit our poster on Friday afternoon, where I present 𝗠𝗘𝘁𝟯𝗥: 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗶𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗜𝗺𝗮𝗴𝗲𝘀 @mohammadasim98.bsky.social @wimmerthomas.bsky.social @mpi-inf.mpg.de @cvml.mpi-inf.mpg.de
2171
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 11/06/2025
7 / 🧵 ... Workshop: Women in Computer Vision (WiCV) 📱 @sukrutrao.bsky.social @SwetaMahajan @MoritzBoehle
010
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 11/06/2025
7/ 🧵 Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery Authors: S. Rao, S. Mahajan, M. Böhle, B. Schiele 🔍 Explore sparse autoencoders to automatically extract and name concepts, enabling performance improvements on downstream tasks. 📚 arxiv.org/abs/2407.14499
121
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 11/06/2025
6 / 🧵 ... Workshop: Women in Computer Vision (WiCV) 📱 @tejaswinimedi.bsky.social @margretkeuper.bsky.social
131
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 11/06/2025
6/ 🧵 3D-WAG: Wavelet-Guided Autoregressive Generation for 3D Shapes Authors: T. Medi*, A. Rampini, P. Reddy, P. K. Jayaraman, M. Keuper 🔍 3D-WAG introduces wavelet-guided autoregressive generation for 3D shapes, aiming for better geometry modeling. 📚 arxiv.org/abs/2411.19037
131
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 11/06/2025
5/ 🧵 ... Workshop: Explainable AI for Computer Vision (XAI4CV) 📱 @katharinaprasse.bsky.social @smarton.bsky.social @margretkeuper.bsky.social
120
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 11/06/2025
5/ 🧵 Data-Efficient Visual Concept Bottleneck Models Authors: K. Prasse, P. Knab, S. Marton, C. Bartelt, M. Keuper 🔍 Introducing data-efficient visual concept bottleneck models for improved explainability in CV. 📚 arxiv.org/abs/2412.11576
120
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 11/06/2025
4/ 🧵 ... Workshops: What is Next in Multimodal Foundation Models? | Women in Computer Vision 📱 @maheensaleh.bsky.social @ninashv.bsky.social @annakukleva.bsky.social @hildekuehne.bsky.social
131
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 11/06/2025
4/ 🧵 HD-VILA-Caption: A Diverse Video-Text Dataset Derived from ASR Narrations By: M. Saleh, N. Shvetsova, A. Kukleva, H. Kuehne, B. Schiele 🔍 HD-VILA-Caption is a large-scale, diverse video-text dataset with 10M high-quality captions, built from ASR subtitles for video-language pretraining.
120
Computer Vision and Machine Learning at MPI Informatics @cvml.mpi-inf.mpg.de · 11/06/2025
3 / 🧵 ... Workshop: Synthetic Data for Computer Vision @ CVPR 2025 📱 @margretkeuper.bsky.social
130