Christian Wolf

chriswolfvision.bsky.social

19 October 2026 12:37

Claude: "This implementation will require roughly 2 days". Does it in 10min. As long as this phenomenon persists, we know that human data dominates in training. Or am I missing something here?

Juliette Marrie

jlt-m.bsky.social

17 October 2026 13:31

Introducing REKI, a 2.4B vision-language-action model pretrained on public data only. With a simple design, it rivals larger models trained on in-house data with complex multi-stage pipelines, setting a new Pareto frontier between performance and size. kyutai.org/reki

Christian Wolf

chriswolfvision.bsky.social

15 October 2026 10:48

Naver Labs Europe's chateau has been renovated and some of our teams are moving back there 😍 (It's one of our 4 buildings).

Dominik Schnaus

schnaus.bsky.social

09 October 2026 16:27

DINOv2 has never seen a caption, and Qwen3 has never seen an image. We still aligned their embedding spaces without a single image-caption pair. It even works when the images and the captions come from different datasets. Project page: dominik-schnaus.github.io/unpaired-rosetta ⬇️

ELLIOT Project

elliot-eu.bsky.social

09 October 2026 11:04

AI models can learn hidden visual biases from data. 🧠⚖️ In this ELLIOT Research Spotlight 🔬, we highlight MAVias from CERTH-ITI — an approach using foundation models to discover and mitigate unknown visual biases, supporting more trustworthy computer vision systems. 📄 Paper in comments 👇