Sophia Sirko-Galouchenko ๐บ๐ฆ
@ssirko.bsky.social
๐ค 224
๐ฅ 327
๐ 22
PhD student in visual representation learning at Valeo.ai and Sorbonne Universitรฉ (MLIA)
pinned post!
1/n New paper - V-GIFT ๐ Self-supervised tasks like rotation prediction or colorization were big in 2018. Do they still matter? Yes. We turn them into visual instruction tuning data for MLLMs. Result: models rely more on the image and perform better on vision tasks ๐
about 1 month ago
1
23
9
1/n New paper - V-GIFT ๐ Self-supervised tasks like rotation prediction or colorization were big in 2018. Do they still matter? Yes. We turn them into visual instruction tuning data for MLLMs. Result: models rely more on the image and perform better on vision tasks ๐
about 1 month ago
1
23
9
reposted by
Sophia Sirko-Galouchenko ๐บ๐ฆ
valeo.ai
2 months ago
Congratulations to our researchers Renaud Marlet and
@abursuc.bsky.social
on their repeated recognition as outstanding reviewers at
#CVPR
,
#ICCV
, and
#ECCV๐๐๐
Thank you for your sharp insights, kindness, and dedication. It's key for the field to count on reviewers like you!
1
15
4
reposted by
Sophia Sirko-Galouchenko ๐บ๐ฆ
valeo.ai
6 months ago
Need pixel-level features from your backbone (DINOv3, CLIP, RADIO, FRANCA...)? ๐Introducing NAF: A universal, zero-shot feature upsampler. It turns low-res ViT features into pixel-perfect maps. -โก Model-agnostic -๐ฅ SoTA results -๐ 4ร faster than SoTA -๐ Scales up to 2K res
loading . . .
1
16
5
reposted by
Sophia Sirko-Galouchenko ๐บ๐ฆ
Bjรถrn Michele
6 months ago
๐๐ 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. ๐ BMVC ๐ Monday, Poster Session 1: Multimodal Learning (11:00โ12:30) ๐ Hadfield Hall
#859
1
13
7
reposted by
Sophia Sirko-Galouchenko ๐บ๐ฆ
MLIA ISIR
6 months ago
๐ Accepted papers at NeurIPS 2025 ๐ 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 โฌ๏ธ
1
3
1
Yesterday was PhD defense day for
@paulcouairon.bsky.social
at
@mlia-isir.bsky.social
๐ His thesis focused on structured visual representations: โข VidEdit - zero-shot text-to-video editing โข DiffCut - zero-shot segmentation via diffusion features โข JAFAR - high-res visual representation upsampling
7 months 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!
7 months ago
1
8
0
Happy to represent Ukraine at
#ICCV2025
. Come see my poster today at 11:45 (#399)!
7 months 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
7 months ago
0
6
1
reposted by
Sophia Sirko-Galouchenko ๐บ๐ฆ
valeo.ai
7 months ago
Our recent research will be presented at
@iccv.bsky.social
!
#ICCV2025
Weโll present 5 papers about: ๐ก self-supervised & representation learning ๐ 3D occupancy & multi-sensor perception ๐งฉ open-vocabulary segmentation ๐ง multimodal LLMs & explainability
valeoai.github.io/posts/iccv-2...
1
8
6
reposted by
Sophia Sirko-Galouchenko ๐บ๐ฆ
Tetiana Martyniuk
8 months ago
Another great event for
@valeoai.bsky.social
team: a PhD defense of Corentin Sautier. His thesis ยซLearning Actionable LiDAR Representations w/o Annotationsยป 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 ๐บ๐ฆ
Tetiana Martyniuk
8 months ago
So excited to attend the PhD defense of
@bjoernmichele.bsky.social
at
@valeoai.bsky.social
! Heโs 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 ๐New 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!
11 months ago
1
21
10
reposted by
Sophia Sirko-Galouchenko ๐บ๐ฆ
Paul Couairon
12 months ago
๐Thrilled to introduce JAFARโa 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 ๐บ๐ฆ
Tetiana Martyniuk
about 1 year 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 ๐บ๐ฆ
David Picard
about 1 year ago
๐ฅ๐ฅ๐ฅ 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) ๐ฅ๐พ๐ฅ๐ท Registration is open (it's free) with priority given to authors of accepted papers:
cvprinparis.github.io/CVPR2025InPa...
Big ๐งต๐ with details!
7
136
63
reposted by
Sophia Sirko-Galouchenko ๐บ๐ฆ
Andrei Bursuc
over 1 year ago
This amazing team โค๏ธ
add a skeleton here at some point
1
19
3
reposted by
Sophia Sirko-Galouchenko ๐บ๐ฆ
Noa Garcia
over 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
44
14
you reached the end!!
feeds!
log in