This project was a collaboration between @eml-munich.bsky.social and Huawei Paris Noahβs Ark Lab. Thank you to my collaborators @qbouniot.bsky.social, Vasilii Feofanov, Ievgen Redko, and particularly to my advisor @zeynepakata.bsky.social for guiding me through my first PhD project!
03.07.2025 07:59 β π 3 π 2 π¬ 1 π 0
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).
π Preprint: arxiv.org/abs/2506.08641
π» Code: github.com/ExplainableM...
03.07.2025 07:59 β π 6 π 2 π¬ 1 π 0
The submission deadline for the proceedings track is today !
#ICCV2025 @iccv.bsky.social
26.06.2025 11:19 β π 4 π 1 π¬ 0 π 0
Submission Deadline is extended by 6 days.
#ICCV2025 @iccv.bsky.social
23.06.2025 12:14 β π 8 π 5 π¬ 0 π 0
This is a joint work with great collaborators Ievgen Redko, Anton Mallasto, Charlotte Laclau, Karol Arndt, Oliver Struckmeier, Markus Heinonen, Ville Kyrki, Samuel Kaski.
tldr;
We propose a way to compare deep neural architectures covering everything from Alexnet to ViTs and beyond.
15.06.2025 05:14 β π 1 π 0 π¬ 0 π 0
I will be presenting our paper on measuring non-linearity of deep neural networks @cvprconference.bsky.social
!
π Project page: qbouniot.github.io/affscore_web...
Come join me on Sunday 15th June from 10:30 to 12:30, ExHall D Poster #402 #CVPR2025
15.06.2025 05:14 β π 6 π 1 π¬ 1 π 0
Call for papers at the eXCV workshop at ICCV 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
14.06.2025 15:47 β π 13 π 5 π¬ 1 π 1
πPhD Spotlight: Thomas Hummel
A spotlight on our one and only @hummelth.bsky.social , who will defend his PhD on 23rd June! π
Thomas started his PhD in 2020 at βͺβͺ@unituebingen.bsky.social as part of the IMPRS-IS program under the supervision of @zeynepakata.bsky.social . π His full story:
19.05.2025 12:36 β π 9 π 1 π¬ 1 π 1
πPhD Spotlight: Jae Myung Kim
Weβre thrilled to celebrate Jae Myung Kim, who will defend his PhD on 25th June! π
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.
12.05.2025 11:16 β π 12 π 2 π¬ 1 π 1
#CVPR2025 is heading to the 'Music City' β Nashville! πΊ Join us from June 11β15. 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! π·π
28.04.2025 11:51 β π 9 π 1 π¬ 1 π 1
Happy to share that we have 4 papers to be presented in the coming #ICLR2025 in the beautiful city of #Singapore . Check out our website for more details: eml-munich.de/publications. We will introduce the talented authors with their papers very soon, stay tunedπ
19.03.2025 11:54 β π 7 π 4 π¬ 0 π 0
Thrilled to announce that four papers from our group have been accepted to #CVPR2025 in Nashville! π Congrats to all authors & collaborators.
Our work spans multimodal pre-training, model merging, and more.
π Papers & codes: eml-munich.de#publications
See threads for highlights in each paper.
#CVPR
02.04.2025 11:36 β π 11 π 4 π¬ 1 π 0
Can we enhance the performance of T2I models without any fine-tuning?
We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec!
#NeurIPS2024
11.12.2024 23:05 β π 27 π 7 π¬ 1 π 1
π΅βπ« Continually pretraining large multimodal models to keep them up-to-date all-the-time is tough, covering everything from adapters, merging, meta-scheduling to data design and more!
So I'm really happy to present our large-scale study at #NeurIPS2024!
Come drop by to talk about all that and more!
10.12.2024 16:42 β π 40 π 6 π¬ 1 π 2
PhD Student @eml-munich.bsky.social @tum.de @www.helmholtz-munich.deβ¬.
Passionate about ML research.
"Uncultured researcher in computer science, completely banal and mainstream."
affiliΓ© Γ France Points Fixes et Γ Theorems As A Service
he/him/whatever
https://social.sciences.re/@MonniauxD
https://cv.hal.science/david-monniaux
PhD student at Stanford. Self-proclaimed computational neuroscientist and humanist. Incomplete bio at https://ynshah3.github.io/.
Getting Embodied Agents to β€οΈ Geometry | Graduate Researcher @RRCLab_IIITH, @iiit_hyderabad
Groundbreaking foundational research in Big Data Management, Machine Learning, and their intersection. #AI #Research
www.bifold.berlin
π°News: www.bifold.berlin/news-events/news
πData Privacy: www.bifold.berlin/data-privacy
PhD Student in Computational Psychiatry with @ericschulz.bsky.social at Helmholtz Munich exploring how anxious and depressed people explore. Also doing some work with LLMs these days (she/her) kristinwitte.github.io
Assistant Professor of Computer Science at TU Darmstadt, Member of @ellis.eu, DFG #EmmyNoether Fellow, PhD @ETH
Computer Vision & Deep Learning
PhD student in explainable AI for computer vision @visinf.bsky.social @tuda.bsky.social - Prev. intern AWS and @maxplanck.de
PhD Student at the Max Planck Institute for Informatics @cvml.mpi-inf.mpg.de @maxplanck.de | Explainable AI, Computer Vision, Neuroexplicit Models
Web: sukrutrao.github.io
https://unireps.org
Discover why, when and how distinct learning processes yield similar representations, and the degree to which these can be unified.
Researcher at Inria Montpellier, France. I work on computer vision / machine learning models for biodiversity and environmental issues.
Trending papers in Vision and Graphics on www.scholar-inbox.com.
Scholar Inbox is a personal paper recommender which keeps you up-to-date with the most relevant progress in your field. Follow us and never miss a beat again!
Senior Lecturer #USydCompSci at the University of Sydney. Postdocs IBM Research and Stanford; PhD at Columbia. Converts β into puns: sometimes theorems. He/him.
Assistant Prof of CS at the University of Waterloo, Faculty and Canada CIFAR AI Chair at the Vector Institute. Joining NYU Courant in September 2026. Co-EiC of TMLR. My group is The Salon. Privacy, robustness, machine learning.
http://www.gautamkamath.com
Professor at Michigan | Voxel51 Co-Founder and Chief Scientist | Creator, Builder, Writer, Coder, Human
Incoming Assistant Professor at Johns Hopkins University | RAP at Toyota Technological Institute at Chicago | web: https://anandbhattad.github.io/ | Knowledge in Generative Image Models, Intrinsic Images, Image-based Relighting, Inverse Graphics
PhD in 3D Vision @Stanford | MSc CS @ETH | Ex @Qualcomm, @MercedesBenz
W: sayands.github.io
Computer Vision PhD Student @UIUC, Undergrad @iitbombay
πUrbana, IL π http://shubhangb97.github.io
Chief Scientist @ AIST | Academic Visitor @ Oxford VGG | PI @ cvpaper.challenge | 3D ResNet (Top 0.5% in 5-yr CVPR) | FDSL (ACCV20 Award/BMVC23 Award Finalist)
