Thanks to Daniil Zverev*, @thwiedemer.bsky.social*, @bayesiankitten.bsky.social, Matthias Bethge (@bethgelab.bsky.social), and @wielandbrendel.bsky.social for making VGGSound sounder! π π π
21.10.2025 18:08 β π 2 π 0 π¬ 0 π 0
VGGSounder: Audio-Visual Evaluations for Foundation Models
VGGSounder, a multi-label audio-visual classification dataset with modality annotations.
π With VGGSounder, we show that existing models donβt always benefit from multimodal input and sometimes performance even degrades.
Code and data: vggsounder.github.io
21.10.2025 18:07 β π 2 π 0 π¬ 1 π 0
VGGSounder is a new video classification benchmark for audio-visual foundation models:
We provide:
π’ Re-annotated VGGSound test set
π’ Modality-specific manual labels
π’ A modality confusion metric to diagnose when models misuse modalities
Paper: arxiv.org/pdf/2508.08237
21.10.2025 18:06 β π 1 π 0 π¬ 1 π 0
π Excited to present our paper VGGSounder: AudioβVisual Evaluations for Foundation Models today at #ICCV2025!
π¦ Poster Session 1 | 11:30β13:30
π Poster #88
Come by if you're into audio-visual learning and want to know whether multiple modalities actually help or hurt.
21.10.2025 18:06 β π 6 π 1 π¬ 1 π 0
Thanks to @munichcenterml.bsky.social for supporting the workshop with a best paper award (announced at 2.50pm CDT)!
11.06.2025 17:59 β π 1 π 0 π¬ 0 π 0
We have fantastic speakers, including @saining.bsky.social, @aidanematzadeh.bsky.social, @ranjaykrishna.bsky.social, Ludwig Schmidt, @lisadunlap.bsky.social, and Ishan Misra.
11.06.2025 17:57 β π 0 π 0 π¬ 0 π 0
EVAL-FoMo 2 - Schedule
Date: June 11 (1:00pm - 6:00pm)
Our #CVPR2025 workshop on Emergent Visual Abilities and Limits of Foundation Models (EVAL-FoMo) is taking place this afternoon (1-6pm) in room 210.
Workshop schedule: sites.google.com/view/eval-fo...
11.06.2025 17:55 β π 7 π 3 π¬ 3 π 0
Screenshot of the workshop website "Emergent Visual Abilities and Limits of Foundation Models" at CVPR 2025
Our paper submission deadline for the EVAL-FoMo workshop @cvprconference.bsky.social has been extended to March 19th!
sites.google.com/view/eval-fo...
We welcome submissions (incl. published papers) on the analysis of emerging capabilities / limits in visual foundation models. #CVPR2025
12.03.2025 11:41 β π 12 π 5 π¬ 0 π 1
Our 2nd Workshop on Emergent Visual Abilities and Limits of Foundation Models (EVAL-FoMo) is accepting submissions. We are looking forward to talks by our amazing speakers that include @saining.bsky.social, @aidanematzadeh.bsky.social, @lisadunlap.bsky.social, and @yukimasano.bsky.social. #CVPR2025
13.02.2025 16:02 β π 7 π 3 π¬ 0 π 1
Upcoming π ππ»πΆπ°π΅ ππ ππ²π°πππΏπ² featuring Prof. Franca Hoffmann from California Institute of Technology and Prof. Holger Hoos from RWTH Aachen University: munichlectures.ai
ποΈ December 17, 2024
π 16:00 CET
π« Senatssaal, #LMU Munich
09.12.2024 15:03 β π 4 π 1 π¬ 2 π 1
Kicking off our TUM AI - Lecture Series tomorrow with none other than Jiaming Song, CSO @LumaLabsAI.
He'll be talking about "Dream Machine: Emergent Capabilities from Video Foundation Models".
Live stream: youtu.be/oilWwsXZamA
7pm GMT+1 / 10am PST (Mon Dec 2nd)
01.12.2024 12:55 β π 42 π 6 π¬ 1 π 0
neuroscientist @berkeley_ai. NIH K00 + UC Presidential Postdoctoral Fellow. he/him
PhD @Berkeley prev CS/Math @MIT
Human-Centered AI Researcher
PhD student @ UC Berkeley | Previous: CS + Music @ MIT | underfit to the demands of reality
https://stephanie-fu.github.io/
Professor, Santa Fe Institute. Research on AI, cognitive science, and complex systems.
Website: https://melaniemitchell.me
Substack: https://aiguide.substack.com/
Tea drinking assistant professor of cognitive psychology at Stanford.
https://cicl.stanford.edu
An EU-funded project bringing AI to the CCIs. Through HAMLET's Hub, artists, creative directors, writers, game developers, and AI experts co-create with tools for adaptive storytelling, dance analysis, 3D assets and more. https://hamlet-project.eu/
Professor Oxford in Machine Learning
Involved in many start ups including FiveAI, Onfido, Oxsight, AIStetic. Eigent, etc
I occasionally look here but am mostly on linkedin, find me there, www.linkedin.com/in/philip-torr-1085702
Cognitive scientist, philosopher, and psychologist at Berkeley, author of The Scientist in the Crib, The Philosophical Baby and The Gardener and the Carpenter and grandmother of six.
Assistant Professor @tticconnect.bsky.social
Understanding intelligence, one pixel at a time.
shiry.ttic.edu
Thinking about multimodal representations | Postdoc at UCPH/Pioneer Centre for AI (DK).
πͺπΊ ELLIOT is a Horizon Europe project developing the next generation of open and trustworthy Multimodal Generalist Foundation Models β advancing open, general-purpose AI rooted in European values. π€π
Official account for IEEE/CVF Conference on Computer Vision & Pattern Recognition. Hosted by @CSProfKGD with more to come.
ππ π cvpr.thecvf.com π June 19, 1983
Ph.D. student at the computer vision group TUM @tumuenchen.bsky.social
Supervised by Prof.Cremers @dcremers.bsky.social
https://sangluisme.github.io
Principal research scientist at Naver Labs Europe, I am interested in most aspects of computer vision, including 3D scene reconstruction and understanding, visual localization, image-text joint representation, embodied AI, ...
Professor for Machine Learning, University of TΓΌbingen, Germany
The German Conference on Pattern Recognition (GCPR) is the annual symposium of the German Association for Pattern Recognition (DAGM). It is the national venue for recent advances in image processing, pattern recognition, and computer vision.
