Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale

New paper: Back into Plato’s Cave

Are vision and language models converging to the same representation of reality? The Platonic Representation Hypothesis says yes. BUT we find the evidence for this is more fragile than it looks.

Project page: akoepke.github.io/cave_umwelten/

1/9

Happy Tuesday ! 🚲💻

Work with @mbsariyildiz.bsky.social @weinzaepfelp.bsky.social @skamalas.bsky.social @pdejorge.bsky.social and other @naverlabseurope.bsky.social colleagues

Research described in these 2 papers:
UNIC - europe.naverlabs.com/unic #ECCV2024
DUNE - europe.naverlabs.com/dune #CVPR2025

🎬 Nice video illustrating our recent line of work on multi-teacher distillation for learning visual representations

The DUNE encoder is a ViT distilled from multiple heterogenous teachers and is incredibly powerful, even outperforming the MASt3R on localization. We use it for navigation and manipulation.

@mbsariyildiz.bsky.social
@weinzaepfelp.bsky.social
@skamalas.bsky.social
@dlarlus.bsky.social
et al.

🚨 Happy to announce CVPR@Paris'26 which will take place on June 1st in Paris. The goal of the event is to share a little bit of the conference before it happens. We will have poster sessions as well as several plenary talks by world-class speakers.

info: cvprinparis.github.io/CVPR2026InPa...

The keynotes and award talks at 3DV 2026 have been made available, with talks by Christian Rupprecht ("3D computer vision done and Dusted?", Angela Dai, Alec Jacobson, Jitendra Malik, Songyou Peng and Michael Niemeyer.

www.youtube.com/playlist?lis...

Today NeurIPS is announcing our official satellite event in Paris.

After responding to the call from Ellis following the success of EurIPS in December, we are pleased to reach a new milestone by joining forces with the NeurIPS organizing committee for the 2026 edition.

Spring flowers on top of a castle

A bike behind a bench, mountains at a distance

Spring commute 🌱🌸🚲

Amazing slides! And good cat-to-slide ratio 😻

The 🔥🔥Anny roll continues this week with the release of Multi-HMR trained with the Anny body model. Multi-person, single shot Human Mesh Recovery predictions are now made in the open, interpretable parameter space of Anny!
🧑‍🤝‍🧑Multi-HMR code: github.com/naver/multi-...
👉Anny: tinyurl.com/5fsekm9z

We're pleased to share that the much awaited Anny-One dataset is now available!
Download ➡️ tinyurl.com/anny-one
*⃣ 800K images
🚀Multi-view & multi-person
🏠Indoor 3D scenes
📷Wild cameras
🔥Anny format! github.com/naver/anny

S-MUSt3R: Sliding Multi-view 3D Reconstruction

Leonid Antsfeld, Boris Chidlovskii, Yohann Cabon, @vincentleroy.bsky.social Jerome Revaud
tl;dr: sliding MUSt3R for cheap long seq
The most interesting is alignment: point-based+camera-based. KDTree local desc for loop closure
arxiv.org/abs/2602.04517

It's time, dear #CVPR2026 reviewers. Time to decide.

We kick off our 2026 Open Seminar series with Dimitris Samaras @stonybrooku.bsky.social on 'Controllable and Efficient Diffusion Models'. Learn how they can be steered & optimized for efficient, controllable generation!
📅 Tuesday Jan 20th: 10am CET
More info & registration ➡️ tinyurl.com/y3m23j2x

𝗠𝗲𝘀𝗵𝟰𝗗: 𝟰𝗗 𝗠𝗲𝘀𝗵 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗧𝗿𝗮𝗰𝗸𝗶𝗻𝗴 𝗳𝗿𝗼𝗺 𝗠𝗼𝗻𝗼𝗰𝘂𝗹𝗮𝗿 𝗩𝗶𝗱𝗲𝗼
Zeren Jiang, Chuanxia Zheng, Iro Laina ... Andrea Vedaldi
arxiv.org/abs/2601.05251
Trending on www.scholar-inbox.com

Sunset on the Alps, above the clouds

Read about the 5 common themes that emerged from the talks and discussions at the 4th edition of this international workshop. Common themes that emerged from the talks and discussions at the 4th edition of this international workshop.

The 4th AI for Robotics workshop surfaced converging themes around embodied perception, task learning & evaluation methodologies - emphasising a shift to integrated, context-aware systems. Dive into our key takeaways #AI #Robotics #spatialAI
🥽 ➡️ tinyurl.com/bvxxcn5e

Check out our 2025 highlights in computer vision!
🚀Five new *St3R models (MASt3R-SfM, MUSt3R, PanSt3R, HAMSt3R, HOSt3R)
🤩Anny parametric 3D human model (Apache 2.0)
🤟Universal encoder for all-in-one vision FM
Watch the highlights 👇
More info ▶️ tinyurl.com/muvs5vnu

Congratulations Andreas !

Can vision transformers learn without images?🤔👀
Our latest work shows that pretraining ViTs on procedural symbolic data (eg sequences of balanced parentheses) makes subsequent standard training (eg on ImageNet) more data efficient! How is this possible?! ⬇️🧵

The 5th edition of the Conference on Lifelong Learning Agents is going to Romania in 2026 & I'm happy to serve as program chair

We've just put the CfP online ⬇️ & we're particularly excited to broaden the scope to all facets of adaptation of ML models.

Please check out these exciting additions!

New startup Gradium spawned out of @kyutai-labs.bsky.social

Congrats Nicolas ! On the PhD and on those beautifully crafted slides 🤩

This fourth edition of the AI4Robotics workshop was such a nice event 🤩 If you couldn't attend, recordings for all the talks are now available online 🎬🍿
europe.naverlabs.com/updates/ai4r...

🔊 @bjornih.bsky.social will present his #BMVC2025 paper in half an hour !

The 4th #AI4RoboticsWorkshop is over! A big THANK YOU to all our fab speakers & participants for great presentations & conversations. Snapshot souvenir ⬇️ For those who missed out -recordings available soon! tinyurl.com/bdtk2nzs

Recordings will soon be available, stay tuned !