Lightnews — Scholar-powered news

Reposted by NAVER LABS Europe

Laurent Besacier @lbesacier.bsky.social · 2d

The UTTER EU project is wrapping up!
At NAVER LABS Europe, we’re proud to have contributed with models like mHuBERT & SPIRE as well as datasets such as ELITR-Bench for long-context LLM evaluation.
Discover more in our latest post 👇
europe.naverlabs.com/blog/multimo...

Multimodal, multilingual and trustworthy AI models and resources for XR

Models, data, resources and publications as part of the EU project UTTER (2022-2025).

europe.naverlabs.com

2 3

NAVER LABS Europe @naverlabseurope.bsky.social · 12d

Only a few days left to submit your poster
🗓️DEADLINE SEPT 30th 🗓️
Remember - accepted posters qualify for travel grant!
Place: Grenoble, France #AI4Robotics
Submission info ➡️ t.co/Xi7aCDpXVd

3 4

NAVER LABS Europe @naverlabseurope.bsky.social · 26d

If you're working on or care about AI Safety don't miss next week's open seminar with Tomek Korbak of UK AI Security Institute
on 'Chain of thought monitorability'.
🗓️Tuesday Sept 16th: 3pm CEST
Registration & more info: tinyurl.com/2bbkby3c

3

Reposted by NAVER LABS Europe

Nadia Chirkova @nadiinchi.bsky.social · Sep 5

Applications for #ALPS2026 are now open!

lig-alps.imag.fr/index.php/ap...

👉What? Advanced Language Processing School
👉When? 29.03.26-03.04.26
👉Where? French Alps
👉For whom? Phd & advanced MS students, practitioners in academia and industry

Photos from the last run below!

#NLProc

1 5

Reposted by NAVER LABS Europe

Diane Larlus @dlarlus.bsky.social · Sep 4

#PAISS2025 continues with @yann-lecun.bsky.social talking about 'Word Models'

2 2 11

NAVER LABS Europe @naverlabseurope.bsky.social · Sep 4

Adding the fab view of Grenoble by night!

1 4

NAVER LABS Europe @naverlabseurope.bsky.social · Aug 25

HOSt3R (Keypoint-free Hand-Object 3D Reconstruction from RGB images) builds upon DUSt3R for unconstrained hand-object 3D reconstruction - example 3D shape output below.
Paper: arxiv.org/abs/2508.16465
More info on @naverlabseurope.bsky.social
@iccv.bsky.social ➡️ tinyurl.com/2p9kcb86
2/2🧵

2 9

NAVER LABS Europe @naverlabseurope.bsky.social · Aug 25

Announcing 2 new members of the *St3R family for human-centric 3D vision tasks!
Meet HAMst3R & HOSt3R
@iccv.bsky.social
- HAMSt3R (Human-Aware Multi-view Stereo 3D Reconstruction) extends MASt3R to handle scenes involving people.
Paper: arxiv.org/abs/2508.16433
1/2 🧵

1 4 15

NAVER LABS Europe @naverlabseurope.bsky.social · Jul 29

Accepted posters qualify for travel grant. Submit your poster now!
This event is free of charge (inc meals) but you need to register for a seat: bit.ly/3I8olT2

International Workshop on AI FOR ROBOTICS

The 4th edition of a workshop series on how AI can help solve the biggest challenges of real-world robotics applications.

bit.ly

2

NAVER LABS Europe @naverlabseurope.bsky.social · Jul 29

All confirmed speakers: Andrew Davison - Nicolas Mansard - Cordelia Schmid - Marc Pollefeys - Michael Gienger - David Novotny - Andrea Vedaldi - Xavier Alameda-Pineda - Eric Brachmann - Fatma Güney - Aniruddha Kembhavi - Daniel Cremers - Adrien Gaidon - Dongwhan Lee

1 1 4

NAVER LABS Europe @naverlabseurope.bsky.social · Jul 29

Major announcement ✨registration is OPEN✨
AI for Robotics workshop (4th edition): Spatial AI
🗓️Nov 21-22 Grenoble, France!
Details: tinyurl.com/bdtk2nzs
⭐⭐ 14 confirmed speakers ⭐⭐: 🧵2/3
Poster submissions (travel grant possible): 🧵 3/3
Spread the word!

1 7 19

NAVER LABS Europe @naverlabseurope.bsky.social · Jul 7

We're thrilled to have Ahmet Iscen of Google DeepMind with us tomorrow to talk about his work on #VLMs. Join us online! 'VLM-driven data & context curation for visual understanding'
🗓️Tuesday July 8th: 11am CEST
Registration & more info: tinyurl.com/yz3rvz3z

1 9

NAVER LABS Europe @naverlabseurope.bsky.social · Jul 3

Introducing the latest model in our *St3R family! In a single step PanSt3R performs fast & scalable 3D reconstruction & scene understanding with object instances.
Paper: arxiv.org/abs/2506.21348
More info on our 3D FMs: tinyurl.com/vxw4mn9x
Accepted at #ICCV25 🎉

4 16

NAVER LABS Europe @naverlabseurope.bsky.social · Jun 19

Introducing 2 ***ONLINE*** compression models for #RAG
▶️PROVENCE: hard-PnP-streamlined-fast-accurate
▶️OSCAR: soft-fine-tuned LLMs-highest existing compression-fast -accurate
👉Blog &🤗models: tinyurl.com/5n7zb4vf
@nadiinchi.bsky.social S. Clinchant V. Nikoulina M. Louis
T.Formal & H.Dejean

2

Reposted by NAVER LABS Europe

Philippe Weinzaepfel @weinzaepfelp.bsky.social · Jun 15

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

6 18

NAVER LABS Europe @naverlabseurope.bsky.social · Jun 13

MUSt3R and Pow3R code the same day 😮!
All @naverlabseurope.bsky.social code & data can be accessed here europe.naverlabs.com/research/code/

1 10

NAVER LABS Europe @naverlabseurope.bsky.social · Jun 12

Come on @vincentleroy.bsky.social - it must be MUSt3R the most amazing right 😉 !

Vincent Leroy @vincentleroy.bsky.social · Jun 12

I don't know whether I'm more amazed by the drone hitting tree branches and recovering instead of crashing or MUSt3R following it as if nothing special happened...

1 4

NAVER LABS Europe @naverlabseurope.bsky.social · Jun 11

A teaser of the latest 3D DUSt3R based models we’re presenting at ‪@cvprconference.bsky.social‬
Discover MUSt3R & Pow3R, universal encoder DUNE + research in navigation, vizloc, segmentation & human motion understanding!
All our #CVPR2025 papers are here
➡️ tinyurl.com/4z79ujce

3 19

Reposted by NAVER LABS Europe

Diane Larlus @dlarlus.bsky.social · Jun 8

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 🔽

David Picard @davidpicard.bsky.social · Jun 6

I'm so happy to have (finally) the opportunity of having Diane Larlus present her amazing work. This is our second keynote of the day.

1 3 28

NAVER LABS Europe @naverlabseurope.bsky.social · Jun 3

Incorporating physics into embodied AI has massive impact on out-of-the-box robot navigation! @steevenj7.bsky.social & @chriswolfvision.bsky.social share what was learned in moving from simulation to the real world with #spatialAI ➡️ tinyurl.com/k83svt8a

5 12

NAVER LABS Europe @naverlabseurope.bsky.social · May 23

Many congratulations indeed and, Ginger, we will miss you!

1

NAVER LABS Europe @naverlabseurope.bsky.social · May 20

We're delighted to have Kristiina Jokinen for this week's 📣Open Seminar (🖥️ online)! ‪@helsinki.fi‬ & ‪@naist-nlp.bsky.social‬ Tokyo 'From words to real-world interactions: grounding & shared knowledge in human robot cooperation'
🗓️ Thur May 23, 11am CEST
Register now ➡️ tinyurl.com/2kcycj93

Image announcing the seminar of Kristiiina Jokinen at NAVER LABS Europe on May 23rd 2025

2 4

NAVER LABS Europe @naverlabseurope.bsky.social · Apr 11

Applications are 📣OPEN📣 for #PAISS2025 THE AI summer school in #Grenoble 1-5 Sept! Speakers so far @yann-lecun.bsky.social @dimadamen.bsky.social @arthurgretton.bsky.social @gabrielpeyre.bsky.social @science4all.org A. Cristia J. Revaud M. Caron J. Carpentier M. Vladimirova ➡️ paiss.inria.fr

9 30

NAVER LABS Europe @naverlabseurope.bsky.social · Mar 31

Join us for our next Open Seminar w/ Derek Hoiem, Siebel School of Computing & DS at UIUC on AI to get the whole job done. Event onsite & virtual!
🗓️ Tues April 8th, 11am CEST
Register 2 attend onsite @naverlabseurope.bsky.social
➡️ tinyurl.com/ypy444tw
Register 4 virtual ➡️ tinyurl.com/3424kpjh

Derek Hoiem: Three elements to AI that get the job done

On site registration. Speaker: Derek Hoiem, professor, Computer Science at the University of Illinois at Urbana-Champaign

tinyurl.com

1 2 6

Reposted by NAVER LABS Europe

Laurent Besacier @lbesacier.bsky.social · Mar 31

#ALPS2025 first talk: Kyunghyun Cho himself! “Causality gets help from deep learning “

1 6