Yannis Kalantidis
@skamalas.bsky.social
📤 873
📥 459
📝 27
he/him; Researcher at NAVER LABS Europe. Greek, resident a Barcelona.
https://www.skamalas.com/
reposted by
Yannis Kalantidis
Diane Larlus
about 2 months ago
Research described in these 2 papers: UNIC -
europe.naverlabs.com/unic
#ECCV2024
DUNE -
europe.naverlabs.com/dune
#CVPR2025
1
4
2
reposted by
Yannis Kalantidis
Diane Larlus
about 2 months ago
🎬 Nice video illustrating our recent line of work on multi-teacher distillation for learning visual representations
add a skeleton here at some point
1
14
4
reposted by
Yannis Kalantidis
Dmytro Mishkin
23 days ago
ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
@psuma.bsky.social
@gkordo.bsky.social
@skamalas.bsky.social
@gtolias.bsky.social
tl;dr: SuperGlue, but single score on light-weight top descriptors. Most important thing is dustbin.
arxiv.org/abs/2603.28603
0
12
2
reposted by
Yannis Kalantidis
Bill Psomas
6 months ago
🤞🏾A few days left for
#CVPR
submissions. 🪩 If submitting a paper on composed image retrieval, test your method on i-CIR, the real-world, truly compositional dataset.
#cvpr2026
#composed_image_retrieval
#image_retrieval
add a skeleton here at some point
0
3
2
reposted by
Yannis Kalantidis
NAVER LABS Europe
7 months ago
We’re
#HiringNow
a Senior Research Scientist in ML for Robotics in Grenoble, France Don't miss us at
#iros2025
this week to chat about the role, research & team with Darko Drakulic & @rbregier.bsky.social on Tue 21 & Thur 23 Oct! More info on where to find them & job ad ⬇️⬇️
1
4
3
reposted by
Yannis Kalantidis
Zeynep Akata
7 months ago
What if your CBM actually doesn’t look at attributes when it explains the classification decision? We suggest to use this dataset and method to generate realistic images with unusual attributes to stress-test explainability methods.
@jessica-bader.bsky.social
is at ICCV to talk to you about it!
add a skeleton here at some point
0
6
2
reposted by
Yannis Kalantidis
Giorgos Kordopatis-Zilos
7 months ago
🌺 Just 4 days to go! Join us in Honolulu for the Instance-Level Recognition and Generation Workshop at
#ICCV2025
🏝 🗓️ Oct 19, 8:30am–12:30pm 📍 Room 306 A We’ll have amazing keynotes, plus oral and poster sessions featuring accepted and invited papers. Don’t miss it!
ilr-workshop.github.io/ICCVW2025/
1
9
6
reposted by
Yannis Kalantidis
Evangelos Kazakos
7 months ago
👋 I created a feed for ICCV 2025! Use it to share, discuss, and discover everything ICCV 2025 — from workshops, orals, and posters to announcements, social events, and adventures 🌺. 🗣️ Posts appear if you include
#iccv2025
or tag
@iccv.bsky.social
Looking forward to meeting you all! Remember to📌
add a skeleton here at some point
0
14
7
reposted by
Yannis Kalantidis
Yoshitomo Matsubara
7 months ago
Did you open-source your
#ICCV2025
works? As a PyTorch Ambassador, I would like to write an article to introduce open-sourced ICCV 2025 works (including workshops and demos) for promoting open-source/science + PyTorch If interested, share your work via the form in my reply 👇
3
9
8
reposted by
Yannis Kalantidis
Kara Swisher
8 months ago
No notes
591
37349
10483
reposted by
Yannis Kalantidis
Diane Larlus
9 months ago
Next
#PAISS2025
lecture by Ahmet Iscen on 'web scale fine grained visual recognition'
1
9
2
reposted by
Yannis Kalantidis
Christian Wolf
9 months ago
Dima Damen opens the afternoon session of
#PAISS2025
with a presentation on egocentric vision. At which point does an egg become an egg-shell and how do we deal with the fact that the egg-shell looks more like the "old egg" than the "new egg" in the pan now does?
@dimadamen.bsky.social
1
20
2
reposted by
Yannis Kalantidis
Christian Wolf
9 months ago
The 4th day of the
#PAISS2025
summer school is opened by Jérôme Revaud presenting 'Data-driven 3d vision' and the DUSt3R and MASt3R family of models.
1
21
2
reposted by
Yannis Kalantidis
NeurIPS Europe Conference
9 months ago
Is your company interested in reaching Europe's leading AI researchers? If so, don't worry! There are still plenty of opportunity to support
#EurIPS
as a sponsor. Sponsorship packages are available and can be further customized if necessary. More info at:
eurips.cc/become-sponsor/
0
8
7
reposted by
Yannis Kalantidis
Christian Wolf
9 months ago
#ICLR2026
PCs consider prompt injection as an ethics problem, in particular an attempt to collude with a potential malicious reviewer (using an LLM). I can't agree more.
blog.iclr.cc/2025/08/26/p...
2
24
4
reposted by
Yannis Kalantidis
NeurIPS Europe Conference
9 months ago
So, what is
#EurIPS
anyway? 🤔 EurIPS is a community-driven conference taking place in Copenhagen Denmark endorsed by
@neuripsconf.bsky.social
and
@nordicair.bsky.social
and co-developed with
@ellis.eu
, where you can additionally present your NeurIPS papers.
1
17
5
reposted by
Yannis Kalantidis
Vision and Graphics Trends
9 months ago
𝗛𝗢𝗦𝘁𝟯𝗥: 𝗞𝗲𝘆𝗽𝗼𝗶𝗻𝘁-𝗳𝗿𝗲𝗲 𝗛𝗮𝗻𝗱-𝗢𝗯𝗷𝗲𝗰𝘁 𝟯𝗗 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗥𝗚𝗕 𝗶𝗺𝗮𝗴𝗲𝘀 Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel ... Grégory Rogez
arxiv.org/abs/2508.16465
Trending on
www.scholar-inbox.com
0
6
3
reposted by
Yannis Kalantidis
Vision and Graphics Trends
9 months ago
𝗛𝗔𝗠𝗦𝘁𝟯𝗥: 𝗛𝘂𝗺𝗮𝗻-𝗔𝘄𝗮𝗿𝗲 𝗠𝘂𝗹𝘁𝗶-𝘃𝗶𝗲𝘄 𝗦𝘁𝗲𝗿𝗲𝗼 𝟯𝗗 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 Sara Rojas, Matthieu Armando, Bernard Ghamen ... Gregory Rogez
arxiv.org/abs/2508.16433
Trending on
www.scholar-inbox.com
0
11
3
Check out HAMSt3R 🐹 A human-aware multi-view 3D reconstruction method from NLE, accepted at ICCV 2025!
add a skeleton here at some point
9 months ago
0
15
1
reposted by
Yannis Kalantidis
Dmytro Mishkin
9 months ago
Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
@ryan-ramos.bsky.social
@stojnicv.xyz
@gkordo.bsky.social
Yuta Nakashima
@gtolias.bsky.social
@noagarciad.bsky.social
tl;dr: CLIP sees difference DSLR vs iphone, DINO doesn't.
arxiv.org/abs/2508.10637
1/
1
15
4
reposted by
Yannis Kalantidis
Dmytro Mishkin
9 months ago
HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images Anilkumar Swamy,
@vincentleroy.bsky.social
@weinzaepfelp.bsky.social
Jean-Sébastien Franco, Grégory Rogez tl;dr: DUSt3R tuned on hands-pose dataset + handcrafted 3D reconstruction system
arxiv.org/abs/2508.16465
0
14
5
reposted by
Yannis Kalantidis
Christian Wolf
9 months ago
From:
www.argmin.net/p/the-negron...
add a skeleton here at some point
0
27
15
reposted by
Yannis Kalantidis
Dr Abeba Birhane
10 months ago
"Asked to generate intervention plans for struggling students, AI teacher assistants recommended more-punitive measures for hypothetical students with Black-coded names and more supportive approaches for students the platforms perceived as white"
www.chalkbeat.org/2025/08/06/a...
loading . . .
Annie and Lakeesha struggle in school. AI teacher assistants treated them very differently.
A Common Sense Media study found that prominent teacher assistants that use AI generated recommendations that appeared to be rooted in racial stereotypes based on students’ names. About a third of tea...
https://www.chalkbeat.org/2025/08/06/ai-teacher-assistants-promote-racial-bias-study-finds/
9
542
379
reposted by
Yannis Kalantidis
Dr Abeba Birhane
over 1 year ago
most people want a quick and simple answer to why AI systems encode/exacerbate societal and historical bias/injustice and due to the reductive but common thinking of "bias in, bias out," the obvious culprit often is training data but this is not entirely true 1/
26
597
258
reposted by
Yannis Kalantidis
Dmytro Mishkin
10 months ago
The biggest update in 3D reconstruction world - VGGT (new weights) has been released for commercial usage as well. Kudos to
@jianyuanwang.bsky.social
to make this happen!
github.com/facebookrese...
2
12
3
reposted by
Yannis Kalantidis
Dr Abeba Birhane
10 months ago
so I am one of the 12 people (including the “god-fathers of AI”) that will be at the Vatican this September for a two full-day working group on the Future of AI here is my Vatican approved short provocation on 'AI and Fraternity' for the working group
29
533
172
reposted by
Yannis Kalantidis
Christian Wolf
11 months ago
Deadlines for ICLR 2026 have been communicated on the official site: Abstract: Sep 19 '25 (Anywhere on Earth) Paper: Sep 24 '25 (Anywhere on Earth)
iclr.cc/Conferences/...
ICLR 2026 will happen in Brazil! ❤️ (Don't fall for the predatory conferences with the same name)
add a skeleton here at some point
0
23
8
reposted by
Yannis Kalantidis
Bradley Busch
11 months ago
New research from MIT found that those who used ChatGPT can’t remember any of the content of their essays. Key takeaway: the product doesn’t suffer, but the process does. And when it comes to essays, the process *is* how they learn.
arxiv.org/pdf/2506.088...
192
3701
1879
reposted by
Yannis Kalantidis
Philippe Weinzaepfel
11 months ago
When were
#CVPR2025
papers available on arXiv? 👇
2
39
10
reposted by
Yannis Kalantidis
Christian Wolf
11 months ago
#CVPR2025
attendance per country, comparing 2025 and 2024, sorted by diff. Numbers were extracted from these two slides presented by the respective program chairs. (Totals on the slide seem to include virtual registrations, but not the per country numbers) Diff between western and eastern Europe?
2
19
3
reposted by
Yannis Kalantidis
Christian Wolf
11 months ago
I have created a starter pack with researchers from Naver Labs Europe
@naverlabseurope.bsky.social
: we are in Grenoble, France, and we do research in AI for robotics, computer vision, NLP, machine learning, HRI.
go.bsky.app/JdTFu4Q
add a skeleton here at some point
1
33
8
reposted by
Yannis Kalantidis
Christian Wolf
11 months ago
Our work on "Reasoning in visual navigation..." presented as a "Highlight" by Boris Chidlovskii and Francesco Giuliari at
#cvpr2025
! Interactive site, play around with dynamical models:
europe.naverlabs.com/research/pub...
Thanks
@weinzaepfelp.bsky.social
for the photo.
@steevenj7.bsky.social
0
10
4
reposted by
Yannis Kalantidis
Philippe Weinzaepfel
11 months ago
During today's
#CVPR2025
workshops, I will present: - What matters in ImageNav: architecture, pre-training, sim settings, pose (poster & highlight at the Embodied AI workshop) - CondiMen: Conditional Multi-person Human Mesh Recovery (Poster at the Rhobin workshop and at the 3D Humans workshop)
0
10
4
reposted by
Yannis Kalantidis
Vladan Stojnić
11 months ago
Paper:
arxiv.org/abs/2503.19777
Code:
github.com/vladan-stojn...
Demo:
huggingface.co/spaces/stojn...
Work with
@skamalas.bsky.social
, Jiri Matas, and
@gtolias.bsky.social
.
0
2
1
reposted by
Yannis Kalantidis
Philippe Weinzaepfel
11 months ago
Wanna the outstanding performance of MASt3R while using a ViT-B or ViT-S encoder instead of its ViT-L one? Don't miss how we build DUNE, a single encoder for diverse 2D & 3D tasks, at this afternoon
#CVPR2025
poster session (poster #376). paper:
arxiv.org/abs/2503.14405
code:
github.com/naver/dune
add a skeleton here at some point
0
17
6
reposted by
Yannis Kalantidis
Giorgos Kordopatis-Zilos
11 months ago
Are you at
@cvprconference.bsky.social
? Come by our poster! 📅 Sat 14/6, 10:30-12:30 📍 Poster #395, ExHall D
add a skeleton here at some point
0
16
9
reposted by
Yannis Kalantidis
Women in Computer Vision at CVPR 2026
11 months ago
💜 Huge thanks to our amazing organizers for making
#WiCV
@cvprconference.bsky.social
2025 possible! 🙌 After 6+ months of near-daily work by 9 dedicated organizers, it’s exciting to see everything come together. So proud of this amazing team! 💪✨
0
15
3
reposted by
Yannis Kalantidis
Andrei Bursuc
11 months ago
You woke up early in the morning jet-lagged and having a hard time deciding for a workshop today
@cvprconference.bsky.social
? Here's a reliable choice for you: our workshop on 🛟 Uncertainty Quantification for Computer Vision! 🗓️ Day: Wed, Jun 11 📍Room: 102 B
#CVPR2025
#UNCV2025
add a skeleton here at some point
0
9
3
reposted by
Yannis Kalantidis
Dima Damen
11 months ago
Have you heard about HD-EPIC? Attending
#CVPR2025
Multiple opportunities to know about the most highly-detailed video dataset with a digital twin, long-term object tracks, VQA,…
hd-epic.github.io
1. Find any of the 10 authors attending
@cvprconference.bsky.social
– identified by this badge. 🧵
1
5
3
reposted by
Yannis Kalantidis
Pau de Jorge
12 months ago
Check out our new paper in
#CVPR2025
! We test the limits of multi-teacher distillation to get one of the most versatile encoders yet. Mixing DINOv2 semantics 🦕, MASt3R multi-view reconstruction 📸📸...📸 and Human Mesh Recovery 🕺💃...🏌️♂️ Check our project page:
europe.naverlabs.com/research/pub...
add a skeleton here at some point
0
3
1
🧵 Two new papers at
#CVPR2025
on generalization in visual representations — covering both universal encoders for 2D and 3D tasks, and open-vocabulary semantic segmentation Let's dive in! 👇
12 months ago
1
23
3
reposted by
Yannis Kalantidis
RTÉ News
12 months ago
Famine is so close in Gaza that when it does hit it will be too late for aid to arrive and there will be mass death, UNICEF's Global spokesperson James Elder has warned.
loading . . .
Aid will be too late when famine hits Gaza, warns UNICEF
Famine is so close in Gaza that when it does hit it will be too late for aid to arrive and there will be mass death, UNICEF's Global spokesperson James Elder has warned.
https://www.rte.ie/news/world/2025/0609/1517441-israel-gaza/
3
96
104
reposted by
Yannis Kalantidis
Diane Larlus
12 months ago
DUNE 🏜️ - multi-teacher distillation extended to heterogeneous teachers: DiNOv2, Multi-HMR and MASt3R -
#CVPR2025
Paper:
arxiv.org/abs/2503.14405
Project page:
europe.naverlabs.com/dune
1
9
3
reposted by
Yannis Kalantidis
Diane Larlus
12 months ago
UNIC 🃏 - multi-teacher distillation to create a UNIC model for classification -
#ECCV2024
Paper:
eccv.ecva.net/virtual/2024...
Project page:
europe.naverlabs.com/unic
1
3
1
reposted by
Yannis Kalantidis
Diane Larlus
12 months ago
Fake it till you make it 🦄 - training visual representations from a synthetic clone of ImageNet -
#CVPR2023
Paper:
arxiv.org/abs/2212.08420
Project page:
europe.naverlabs.com/imagenet-sd/
1
3
1
reposted by
Yannis Kalantidis
Diane Larlus
12 months ago
CoG ⚙️ - a benchmark to study the generalization of pretrained models to unseen concepts -
#ICCV2021
Paper:
arxiv.org/abs/2012.05649
Project page:
europe.naverlabs.com/cog-benchmark
1
3
1
reposted by
Yannis Kalantidis
Diane Larlus
12 months ago
Many thanks again for the invitation and thanks everyone who came chatting and asking questions after the talk 😍 If you couldn't make it and are interested, the talk title was: *Breaking the mold:Teaching Visual Models to Generalize* and it covered the following papers 🔽
add a skeleton here at some point
1
27
3
reposted by
Yannis Kalantidis
David Picard
12 months ago
Last poster session ! (With that gorgeous Dune poster 🤩)
1
10
1
reposted by
Yannis Kalantidis
Mark Riedl
12 months ago
Oh. My. Fucking. God. This is part of the prompt used to identify Veterans Affairs contracts that should be canceled, or, using the very-much non-technical term "munched".
www.propublica.org/article/insi...
10
237
104
reposted by
Yannis Kalantidis
Christian Wolf
12 months ago
The second Keynote of CVPR@Paris is given by
@dlarlus.bsky.social
of
@naverlabseurope.bsky.social
on "Breaking the mold", generalization in computer vision.
2
22
3
Load more
feeds!
log in