Julia Grabinski

📢Excited to share our IROS 2025 paper “Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model”!

Work by Jannik Endres, @olvrhhn.bsky.social, Charles Cobière, @simoneschaub.bsky.social, @stefanroth.bsky.social and Alexandre Alahi.

[1/8] We are presenting four main conference papers, two workshop papers, and a workshop at @iccv.bsky.social 2025 in Hawaii! 🎉🏝

ELLIS PhD Program: Call for Applications 2025 The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...

🎓 Looking for a PhD position in computer vision? Apply to the European Laboratory for Learning & Intelligent Systems (ELLIS) and work with @stefanroth.bsky.social & @simoneschaub.bsky.social! Join the info session on Oct 1.

@ellis.eu @tuda.bsky.social

ellis.eu/news/ellis-p...

Some impressions from our VISINF summer retreat at Lizumer Hütte in the Tirol Alps — including a hike up Geier Mountain and new research ideas at 2,857 m! 🇦🇹🏔️

🚨 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

PhD: DONE! ✅ If you are wondering how I feel, just check out these smiling pics. Incredibly thankful and happy! 😊 #PhDLife #PhDConpleted

a cartoon of a girl using a laptop with the word revising written above her ALT: a cartoon of a girl using a laptop with the word revising written above her

✍️Submitting to the Fast Review Track at GCPR 2025?

Remember, the deadline is just 5 days away: July 1st, 2025, 11:59 CEST!

Perfect for revised versions of your hard work.

We are excited to see your research shine! 🚀
#GCPR2025

👉 www.dagm-gcpr.de/year/2025/su...

🌐📖 Published a great paper recently? Share it with an even wider audience at GCPR 2025’s Nectar Track! Present your published research, gain recognition, and expand your network! Submission Deadline: July 28, 2025 🚀 #ResearchImpact #ComputerVision #MachineLearning
👉 www.dagm-gcpr.de/year/2025/su...

🌟📚 DAGM Young Researchers’ Forum: Submission deadline - June 04, 2025! Showcase your thesis, meet experts, and compete for the Best Master’s Thesis Award! 🚀 #YoungResearchers #MasterThesis 👉 www.dagm-gcpr.de/year/2025/su...

It's a wrap! 🎉 Thank you @iclr-conf.bsky.social for supporting so many inspiring ideas and thanks Singapore for having me again! 🇸🇬 #ICLR2025 #MachineLearning #PhDlife

Update: thanks @iclr-conf.bsky.social for finding this creative and well working solution ☺️

The modern way to present a fabric poster @iclr-conf.bsky.social 😎😂

come drop by #74

Abstract of the paper

Our paper "Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?" will be presented at #ICLR2025!
It's also the first paper of my first PhD student, congrats @maximemeloux.bsky.social ! 🎉

blog: melouxm.github.io/MI-identifia...

An explanatory thread 🧵:

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!

GitHub - GeJulia/NIFF Contribute to GeJulia/NIFF development by creating an account on GitHub.

🗓️ Thu, Apr 24, 10:00–12:30
📍 Hall 3 + 2B, Poster #74
🧠 Paper: openreview.net/pdf?id=xRy1Y...
💻 Code: github.com/GeJulia/NIFF

Are you around? Come say hi! 😊

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

Amid all the super-duper research advances, I am excited to share my video on a super-duper basic topic:

How to sample your signals?

Here we discuss sampling, why aliasing occurs, and how to prevent it. It's fascinating to view this through the lens of frequency analysis. youtu.be/fTJjPGaPsq4

FrequencyLowCut Pooling - Plug and Play Against Catastrophic Overfitting Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing point of view, this...

Really cool video! Maybe our work on aliasing artifacts and robustness link.springer.com/article/10.1... within vision models and how to fix them to link.springer.com/chapter/10.1... might be interesting for you 😊

🏔️⛷️ Looking back on a fantastic week full of talks, research discussions, and skiing in the Austrian mountains!

3. our TMLR Featured Certification "As large as it gets – Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters" - openreview.net/forum?id=xRy... joint work with @juliagrabinski.bsky.social @janiskeuper.bsky.social and @margretkeuper.bsky.social

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"