Sophia Sirko-Galouchenko 🇺🇦
@ssirko.bsky.social
📤 210
📥 324
📝 12
PhD student in visual representation learning at Valeo.ai and Sorbonne Université (MLIA)
pinned post!
1/n 🚀New paper out - accepted at
#ICCV2025
! Introducing DIP: unsupervised post-training that enhances dense features in pretrained ViTs for dense in-context scene understanding Below: Low-shot in-context semantic segmentation examples. DIP features outperform DINOv2!
5 months ago
1
20
10
reposted by
Sophia Sirko-Galouchenko 🇺🇦
valeo.ai
7 days ago
Need pixel-level features from your backbone (DINOv3, CLIP, RADIO, FRANCA...)? 🚀Introducing NAF: A universal, zero-shot feature upsampler. It turns low-res ViT features into pixel-perfect maps. -⚡ Model-agnostic -🥇 SoTA results -🚀 4× faster than SoTA -📈 Scales up to 2K res
loading . . .
1
15
5
reposted by
Sophia Sirko-Galouchenko 🇺🇦
Björn Michele
8 days ago
🚗🌐 Working on domain adaptation for 3D point clouds / LiDAR? We'll present MuDDoS at BMVC: a method that boosts multimodal distillation for 3D semantic segmentation under domain shift. 📍 BMVC 🕚 Monday, Poster Session 1: Multimodal Learning (11:00–12:30) 📌 Hadfield Hall
#859
1
13
7
reposted by
Sophia Sirko-Galouchenko 🇺🇦
MLIA ISIR
8 days ago
🎉 Accepted papers at NeurIPS 2025 🎉 The team is proud to announce that several paper were accepted at
#NeurIPS25
. Looking forward to meet in Paris (25th-26th Nov), Copenhagen or San Diego (1st-7th Dec)! Let's present our papers ⬇️
1
3
1
Yesterday was PhD defense day for
@paulcouairon.bsky.social
at
@mlia-isir.bsky.social
🎓 His thesis focused on structured visual representations: • VidEdit - zero-shot text-to-video editing • DiffCut - zero-shot segmentation via diffusion features • JAFAR - high-res visual representation upsampling
27 days ago
1
1
0
Thrilled to present DIP at
#ICCV2025
! Great discussions and insightful questions during the poster session. Thank you to everyone who stopped by!
about 1 month ago
1
8
0
Happy to represent Ukraine at
#ICCV2025
. Come see my poster today at 11:45 (#399)!
about 1 month ago
0
17
2
Come say hi to our poster October 21st at 11:45 poster session 1 (#399)! We introduce unsupervised post-training of ViTs that enhances dense features for in-context tasks. First conference as a PhD student, really excited to meet new people.
add a skeleton here at some point
about 1 month ago
0
6
1
reposted by
Sophia Sirko-Galouchenko 🇺🇦
valeo.ai
about 2 months ago
Our recent research will be presented at
@iccv.bsky.social
!
#ICCV2025
We’ll present 5 papers about: 💡 self-supervised & representation learning 🌍 3D occupancy & multi-sensor perception 🧩 open-vocabulary segmentation 🧠 multimodal LLMs & explainability
valeoai.github.io/posts/iccv-2...
1
8
6
reposted by
Sophia Sirko-Galouchenko 🇺🇦
Tetiana Martyniuk
about 2 months ago
Another great event for
@valeoai.bsky.social
team: a PhD defense of Corentin Sautier. His thesis «Learning Actionable LiDAR Representations w/o Annotations» covers the papers BEVContrast (learning self-sup LiDAR features), SLidR, ScaLR (distillation), UNIT and Alpine (solving tasks w/o labels).
1
9
5
reposted by
Sophia Sirko-Galouchenko 🇺🇦
Tetiana Martyniuk
about 2 months ago
So excited to attend the PhD defense of
@bjoernmichele.bsky.social
at
@valeoai.bsky.social
! He’s presenting his research results of the last 3 years in 3D domain adaptation: SALUDA (unsupervised DA), MuDDoS (multimodal UDA), TTYD (source-free UDA).
2
12
2
1/n 🚀New paper out - accepted at
#ICCV2025
! Introducing DIP: unsupervised post-training that enhances dense features in pretrained ViTs for dense in-context scene understanding Below: Low-shot in-context semantic segmentation examples. DIP features outperform DINOv2!
5 months ago
1
20
10
reposted by
Sophia Sirko-Galouchenko 🇺🇦
Paul Couairon
6 months ago
🚀Thrilled to introduce JAFAR—a lightweight, flexible, plug-and-play module that upsamples features from any Foundation Vision Encoder to any desired output resolution (1/n) Paper :
arxiv.org/abs/2506.11136
Project Page:
jafar-upsampler.github.io
Github:
github.com/PaulCouairon...
loading . . .
1
26
6
reposted by
Sophia Sirko-Galouchenko 🇺🇦
Tetiana Martyniuk
7 months ago
Our paper "LiDPM: Rethinking Point Diffusion for Lidar Scene Completion" got accepted to IEEE IV 2025! tldr: LiDPM enables high-quality LiDAR completion by applying a vanilla DDPM with tailored initialization, avoiding local diffusion approximations. Project page:
astra-vision.github.io/LiDPM/
0
12
5
reposted by
Sophia Sirko-Galouchenko 🇺🇦
David Picard
9 months ago
🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷 Registration is open (it's free) with priority given to authors of accepted papers:
cvprinparis.github.io/CVPR2025InPa...
Big 🧵👇 with details!
8
137
61
reposted by
Sophia Sirko-Galouchenko 🇺🇦
Andrei Bursuc
10 months ago
This amazing team ❤️
add a skeleton here at some point
1
19
3
reposted by
Sophia Sirko-Galouchenko 🇺🇦
Noa Garcia
about 1 year ago
As I haven't found it out there yet, I made the Women in computer vision started pack. Many more missing, please let me know how is already in bsky to add them!
go.bsky.app/BowzivT
add a skeleton here at some point
11
43
14
you reached the end!!
feeds!
log in