Lightnews — Scholar-powered news

Yannis Kalantidis @skamalas.bsky.social · 2d

Congrats @bjoernmichele.bsky.social for all your great work during your PhD!

1 3

Yannis Kalantidis @skamalas.bsky.social · 21d

Congrats Zeynep!!

1 2

Reposted by Yannis Kalantidis

Kara Swisher @karaswisher.bsky.social · 22d

No notes

600 10K 38K

Reposted by Yannis Kalantidis

Diane Larlus @dlarlus.bsky.social · Sep 1

Next #PAISS2025 lecture by Ahmet Iscen on 'web scale fine grained visual recognition'

1 2 9

Reposted by Yannis Kalantidis

Christian Wolf @chriswolfvision.bsky.social · Sep 4

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 2 20

Reposted by Yannis Kalantidis

Christian Wolf @chriswolfvision.bsky.social · Sep 4

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 2 21

Reposted by Yannis Kalantidis

EurIPS Conference @euripsconf.bsky.social · Sep 1

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/

6 8

Reposted by Yannis Kalantidis

Christian Wolf @chriswolfvision.bsky.social · Aug 27

#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 4 25

Reposted by Yannis Kalantidis

EurIPS Conference @euripsconf.bsky.social · Aug 27

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 5 17

Reposted by Yannis Kalantidis

Vision and Graphics Trends @si-cv-graphics.bsky.social · Aug 27

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

3 6

Reposted by Yannis Kalantidis

Vision and Graphics Trends @si-cv-graphics.bsky.social · Aug 26

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

3 11

Yannis Kalantidis @skamalas.bsky.social · Aug 25

Check out HAMSt3R 🐹 A human-aware multi-view 3D reconstruction method from NLE, accepted at ICCV 2025!

Zhenjun Zhao @ericzzj.bsky.social · Aug 25

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction

Sara Rojas, Matthieu Armando, Bernard Ghamen, @weinzaepfelp.bsky.social, @vincentleroy.bsky.social, Gregory Rogez

arxiv.org/abs/2508.16433

1 14

Reposted by Yannis Kalantidis

Dmytro Mishkin @ducha-aiki.bsky.social · Aug 25

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 4 15

Reposted by Yannis Kalantidis

Dmytro Mishkin @ducha-aiki.bsky.social · Aug 25

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

5 14

Reposted by Yannis Kalantidis

Christian Wolf @chriswolfvision.bsky.social · Aug 12

From: www.argmin.net/p/the-negron...

17 28

Reposted by Yannis Kalantidis

Dr Abeba Birhane @abeba.bsky.social · Aug 6

"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...

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...

www.chalkbeat.org

9 320 550

Reposted by Yannis Kalantidis

Dr Abeba Birhane @abeba.bsky.social · Nov 24

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/

26 220 610

Reposted by Yannis Kalantidis

Dmytro Mishkin @ducha-aiki.bsky.social · Aug 4

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 3 12

Reposted by Yannis Kalantidis

Dr Abeba Birhane @abeba.bsky.social · Aug 4

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

AI and Fraternity, Abeba Birhane, AI Accountability Lab

I envision a future where human dignity, justice, peace, kindness, care, respect, accountability, and rights and freedoms serve as the north stars that guide AI development and use. Realising these ideals can’t happen without intentional tireless work, dialogues, and confrontations of ugly realities – even if they are uncomfortable to deal with. This starts with deciphering hype from reality. Pervasive narratives portray AI as a magical, fully autonomous entity approaching a God-like omnipotence and omniscience. In reality, audits of AI systems reveal a consistent failure to deliver on grandiose promises and suffer from all kinds of shortcomings, issues often swept under the rug. AI in general, and GenAI in particular, encodes and exacerbates historical stereotypes, entrenches harmful societal norms, and amplifies injustice. A robust body of evidence demonstrates that — from hiring, welfare allocation, medical care allocation to anything in between — deployment of AI is widening inequity, disproportionately impacting people at the margins of society and concentrating power and influence in the hands of few. Major actors—including Google, Microsoft, Amazon, Meta, and OpenAI—have willingly aligned with authoritarian regimes and proactively abandoned their pledges to fact-check, prevent misinformation, respect diversity and equity, refrain from using AI for weapons development, while retaliating against critique. The aforementioned vision can’t and won’t happen without confrontation of these uncomfortable facts. This is precisely why we need active resistance and refusal of unreliable and harmful AI systems; clearly laid out regulation and enforcement; and shepherding of the AI industry towards transparency and accountability of responsible bodies. "Machine agency" must be in service of human agency and empowerment, a coexistence that isn't a continuation of modern tech corporations’ inequality-widening,

29 160 530

Reposted by Yannis Kalantidis

Christian Wolf @chriswolfvision.bsky.social · Jun 25

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)

AI Conference DL Countdown @dlcountdown.bsky.social · Jun 25

AAAI'26 (abs): 31 days.
WACV'26 (R1,reg): 17 days.
WACV'26 (R1,paper): 24 days.
AAAI'26 (paper): 38 days.
3DV'26: 54 days.
WACV'26 (R2,reg): 80 days.
WACV'26 (R2,paper): 87 days.
ICLR'26 (abs): 87 days.
ICLR'26 (paper): 92 days.

8 23

Reposted by Yannis Kalantidis

Bradley Busch @bradleybusch.bsky.social · Jun 18

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...

200 1.5K 3.7K

Reposted by Yannis Kalantidis

Philippe Weinzaepfel @weinzaepfelp.bsky.social · Jun 17

When were #CVPR2025 papers available on arXiv? 👇

2 9 39

Reposted by Yannis Kalantidis

Christian Wolf @chriswolfvision.bsky.social · Jun 14

#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 3 19

Reposted by Yannis Kalantidis

Christian Wolf @chriswolfvision.bsky.social · Jun 14

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

1 6 33

Reposted by Yannis Kalantidis

Christian Wolf @chriswolfvision.bsky.social · Jun 14

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

4 10