Baseline evaluation today. It is not going very well...

This is what you do when you set allow_sliding=true in your Habitat simulator. If you want to run test with sim2real transfer, you might want to consider wearing a helmet !

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

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

I'd like to highlight PICT, our new differentiable Fluid Solver built for AI & learning: github.com/tum-pbs/PICT

Simulating fluids is hard, and learning 3D closure models even harder: This is where PICT comes in — a GPU-accelerated, fully differentiable fluid solver for PyTorch 🥳

We have an open internship position on socially aware navigation, human aware world models etc.

At @naverlabseurope.bsky.social in Grenoble (Meylan), France.

careers.werecruit.io/en/naver-lab...

We have made some post-conference improvements of our CVPR'25 paper on end-to-end trained navigation. The agent has similar success rate but is more efficient, faster, less hesitant. Will be presented at CVPR in June.

arxiv.org/abs/2503.08306

Work by @steevenj7.bsky.social et al.

Interactive website:

europe.naverlabs.com/research/pub...

Large-scale study w. 262 real episodes finds: evidence for presence of realistic dynamics used for open-loop forecasting and interplay with sensing; usage of latent memory (emerging maps); value relates to long-term planning.
#CVPR2025

Our end-to-end trained navigation agent has been accepted to #CVPR2025: fast-moving, efficient: correct modelling of motion during training in simulation.

arxiv.org/abs/2503.08306

By @steevenj7.bsky.social, H Poirier, L Antsfeld, G Bono, G Monaci, B Chidlovskii, F Giuliari, A Del Bue and myself

Ad on research positions and internships at NAVER LABS Europe, Grenoble, France in February 2025

Welcome to NAVER LABS Europe on Bluesky! We chose 'LABS blue' to kickoff our posts & we'd appreciate it if you could share this one widely tinyurl.com/2nt9jdnv 😊 #hiring #jobs #internships

The view from my new office at NaverLabs (Grenoble, France). It could also be yours, we are looking for PhD interns!

PhD Internship at NaverLabs Europe!

Our Spatial AI team is looking for a PhD intern to work on robot navigation! If you have experience in end-to-end training & RL, and want to work with real robots, DM me!

Bonus: great team, good coffee, amazing landscapes and french castle!

Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation.

Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map.

With @ericdexheimer.bsky.social* @ajdavison.bsky.social (*Equal Contribution)

I have owned the R2 for 2 years now (no colour, no backlight) and I'm very happy with it ! Some friends tested other android-based models but it's not as fast and responsive. The biggest flaw is indeed the lack of Zotero plugin: proprietary OS makes it impossible for the community to build plugins

Check out this BEAUTIFUL interactive blog about cameras and lenses

ciechanow.ski/cameras-and-...

An unexpected behavior emerged from a variant of our navigation policy at NaverLabs. It's not great for SPL, but does a wonderful job as an exhibition mode !

This bot will from today on cross-post on two different platforms.