Andrei Bursuc

The #WorldEngine tech report is now up! It's our post-training framework to deal w/ scarcity of long-tail safety-critical scenarios. Post-training strategies for autonomous driving are rarely tackled and discussed in the open. We hope that this will open more this area. arxiv.…

World Engine: Towards the Era of Post-Training for Autonomous Driving arxiv.org

Announcing the LAIA dataset: 15 hours of driving in CARLA with labelled human gaze arxiv.org/abs/2607.25570 #ssad2026

The LAIA Dataset: Labelled Attention for Intelligent Automobiles arxiv.org

Though a bit bummed for having some of our contributions on self-distillation in 2019-2021 missing from there 🥲 - BoWNet: SSL distillation using BoW representations (pre-BYOL) arxiv.org/abs/2002.12247 - OBoW: self-distillation with EMA and dynamic BoW representations arxiv.org…

Learning Representations by Predicting Bags of Visual Words arxiv.org

Though a bit bummed for having some of our contributions on self-distillation in 2019-2021 missing from there 🥲 - BoWNet: SSL distillation using BoW representations (pre-BYOL) arxiv.org/abs/2002.12247 - OBoW: self-distillation with EMA and dynamic BoW representations arxiv.org…

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning arxiv.org

💻 Link: uncertainty-cv.github.io/2026/ 💪 Supported by: @elliot-eu.bsky.social

UNCV Workshop @ ECCV 2026 uncertainty-cv.github.io

Maximilian Igl on stage talking about Reinforcement Learning for Autonomous Driving #ssad2026 His slides are available online www.maximilianigl.com/blog/rl-for-...

Reinforcement Learning for Autonomous Driving: Lecture Slides maximilianigl.com

🛟 Reliable & reliability folks @eccv.bsky.social! Join our workshop on Uncertainty Quantification for Computer Vision #eccv2026 We have a super lineup of speakers (from computer vision to MLLMs & LLMs) and cool posters. 🗓️ Date: Tue Sep 8 📌Room: Quality View Hotel - Helsingborg