Postdoc at Visual Inference Lab, TU Darmstadt
Mannheim
Joined September 2022
- Tweets100
- Following184
- Followers256
- Likes685
Pinned Tweet
PhD: DONE! ✅ If you are wondering how I feel, just check out these smiling pics. Incredibly thankful and happy! 😊 #PhDLife #DoneAndDusted
Julia Grabinski retweeted
📢 LucidLyra: Feed-Forward Generative 3D Scene Reconstruction and Joint Understanding via Multi-Task Distillation!
Generate a queryable 3D Gaussian scene from a single image! Our feed-forward decoder jointly predicts geometry, appearance, open-vocabulary semantics, and object instances. We train on generated videos, combining video-model self-distillation with supervision from frozen 2D vision foundation models. LucidLyra enables applications such as physical AI simulation, 3D scene editing, and 3D asset mining.
🌍 research.nvidia.com/labs/sil…
Julia Grabinski retweeted
if you want to come post-docing with me at the Technion, here's your chance: azrielifoundation.org/fellow…
Always wanted to come work with me and my students but lacked funding? You’re out of excuses 🙂
The Azrieli Foundation (@azrielifdn) is sponsoring visiting PhD positions (up to 4 months) and postdocs (up to 3 years).
azrielifoundation.org/fellow…
Julia Grabinski retweeted
Excited to share our NeurIPS 2026 paper (+code): Learnable Spectral Activations 📢
Prior INR work tunes which frequencies are available. LSA learns how to compose them. Gains on audio, images, NeRFs & more.
📄 arxiv.org/abs/2610.07419
Kudos to Tamir Shor who led it like a champ
Two reviewer awards in one week? Apparently peer review is my cardio now. 😄 Honored to be an Outstanding Reviewer at @CVPR ! No free registration, but a nice certificate 📜 #PeerReview
Top Reviewer at #NeurIPS2026, two years in a row! 🎉 Good reviewing often goes unnoticed, so I love that @NeurIPSConf makes a point of rewarding it. Thanks to the organizers and ACs!
1/2
What works well for me:
- Read the paper and note strengths & weaknesses as you go
- Sleep on it 😴
- Next day, reread the paper and your notes, then write the summary
Julia Grabinski retweeted
🔥🏆Heat Kernel Textures (HKTex) received the Best Paper Award at #ECCV2026. 🏆🔥
UV-mapping anchors 3D texturing to the past. Inspired by 3DGS, we rethink textures using heat kernels and NO splatting!
circle-group.github.io/resea…
Julia Grabinski retweeted
Sometimes you just need to think that a hard math problem has been solved by others in order to actually solve it. I am referring of course to Dantzig’s 1939 solution of two open problems that he thought were instead routine assigned homework problems. :)
Julia Grabinski retweeted
ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views
@GpStracquadanio, Kevin Raj, @JuliaGrabinski, @stefanroth
tl;dr: learn a diffusion prior guided by multi-view-consistent variational latents
arxiv.org/abs/2608.28895
Come and visit us on Thursday morning 10:30 Poster #196 @eccvconf
[3/6] ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views
@GpStracquadanio, K. Raj, @JuliaGrabinski, @stefanroth
📚 Paper: arxiv.org/abs/2608.28895
🌍 Project Page: visinf.github.io/reconsplat
Julia Grabinski retweeted
📢 [CVPR’26] Can we learn to detect, segment, and track every object in a video without human supervision?
Yes, we introduce VideoCUPS, the first unsupervised video panoptic segmentation (VPS) method: 1. Get pseudo-labels from monocular videos. 2. Train a VPS model on them. – at Denver, CO
Honored to be recognized as an outstanding reviewer for @CVPR this year! 🙏 Grateful to keep contributing to the community!
We are grateful to all of the 17,491 reviewers who helped make #CVPR2026 possible. We are especially pleased to recognize the following Outstanding Reviewers, whose high-quality reviews (as judged by their Area Chairs) placed them among the top 5% of reviewers.
Julia Grabinski retweeted
@LogmlSchool is ready for an exciting program for this summer! The applications will close soon. Apply to participate:
logml.ai/
Julia Grabinski retweeted
Modern deep networks are often trained at the #EdgeOfStability, a regime where dynamics are locally unstable, nearing chaos. Yet generalization improves, defying the wisdom of classical optimization. We now theoretically explain this central puzzle: arxiv.org/abs/2604.19740. 👇
Julia Grabinski retweeted
🔥 Can in-context segmentation emerge directly from frozen DINOv3 features?
At #CVPR2026, we present INSID3: Training-Free In-Context Segmentation with DINQv3 — a collaboration between PoliTo, TU Darmstadt and TU Munich.
A training free approach that generalizes from object-level to part-level and personalized segmentation, across natural, medical, underwater, and aerial domains
Check it out: github.com/visinf/INSID3
Julia Grabinski retweeted
📢🎓 We have open PostDoc positions in Computer Vision & Machine Learning at @TUDarmstadt and hessian.AI within the Reasonable AI Cluster of Excellence — supervised by @stefanroth, @schaub_simone and many others!
Apply here: career.tu-darmstadt.de/tu-da…
Julia Grabinski retweeted
📢🎓 We have open PhD positions in Computer Vision & Machine Learning at @TUDarmstadt and hessian.AI within the Reasonable AI Cluster of Excellence — supervised by @stefanroth, @schaub_simone and many others!
Apply here: career.tu-darmstadt.de/tu-da…