To build a self-driving car, you need lots of GPUs. KE:SAI is renting a dedicated H100 cluster from @scaleway.com to perform our research and train foundation models. The pictures show one of our many racks.

Another fantastic paper from Valeo folks, 35M mid-simulator kilometers to develop safe behavior under partial observability valeoai.github.io/Pictura/

Pictura: Perspective-View Self-Play at Scale for Driving

Self-play driving policies trained directly from rendered perspective images, without privileged vectorized observation of the surroundings.

valeoai.github.io

🚀 We are thrilled to welcome Dr. Kashyap Chitta to the ELLIS Institute Tübingen as our newest Principal Investigator and Hector-Endowed Fellow! Alongside this academic role, he will continue his work with @kesai.eu, a non-profit open-science AI lab he co-founded in May 2026.

Dr. Kashyap Chitta Joins ELLIS Institute Tübingen as Principal Investigator and Hector-Endowed Fellow

institute-tue.ellis.eu

I am mildly jealous of whoever winds up with this position. Amazing team, amazing goal

KE:SAI - Kyutai ELLIS Scalable Autonomous Intelligence@kesai.eu · 2w ago

KE:SAI is hiring! You are super excited about world models and autonomy? Come and join our team! Let's have impact together! kesai.eu/join/

KE:SAI is hiring! You are super excited about world models and autonomy? Come and join our team! Let's have impact together! kesai.eu/join/

Startup news from Tübingen! SOO happy for 🎉 Ontic Labs and Feyer, who have been selected for @SPRIND's Next Frontier AI Challenge. As two of just ten teams across Europe, they'll each receive €3 million to develop their companies. Congratulations to everyone involved! 🚀 tuebingen.ai/news/breakth...

Breakthrough for two University of Tübingen AI startups

Ontic Labs and Feyer each to receive three million euros as they reach second round of Europe-wide competition

tuebingen.ai

🚗 KE:SAI got their own car for data collection and, once we have a permit, policy testing! Read more at: kesai.eu/blog/2026-07...

It's getting real! We have been working on self-driving for more than 15 years, and most of that work has happened in simulation. Today that changes: our research vehicle arrived, and we can start testing our ideas in the physical world. kesai.eu/blog/2026-07...

I resigned from Google DeepMind bc it broke its founding promise by selling AI to the military without restrictions against killer robots or mass spying. For months, I worked to stop this but watched powerful ethicists and institutions choose silence. Here's what happened. 🧵

I work at Google DeepMind. This won't make me popular. But it's all public reporting: 2014: DeepMind reportedly sold to Google on conditions: no military use, independent oversight 2026: a Pentagon contract for "any lawful government purpose" Not one safeguard survived intact

🗣️ I will give a talk at the Emerging Behaviors for Achieving Robust Autonomy workshop at ECCV 2026 this year in Malmö. emerging-ad.github.io 📜 The workshop is also accepting paper submissions. The deadline is next week: 20.07.2026

In this talk from the GenAV Workshop at ICRA 2026, our CTO Kashyap Chitta highlights how open tools, shared benchmarks, and collaborative research can help accelerate progress in autonomous driving. Watch here: www.youtube.com/watch?v=_CYp...

Keshyap Chitta - KE:SAI - Workshop on Generalization in Autonomous Driving at ICRA 2026

What does it take to make autonomous driving research more open, accessible, and scalable? In this talk from the 1st GenAV Workshop at ICRA 2026, Kashyap Chitta explores Democratizing Autonomous…

youtube.com

The AlpaSim E2E Closed Loop Challenge 2026 is open for registration and leaderboard access in a soft-open period. Build AV policies for realistic closed-loop simulation, where each policy's own decisions shape future scenes, observations, and interactions.

Our team placed 3rd in the KITScenes LongTail Challenge at the CVPR 2026 Workshop on Autonomous Driving! We used zero-shot evaluation with the NVIDIA Alpamayo 1.5 vision-language-action model, with zero fine-tuning or task-specific training.

Our CTO Kashyap gave a very nice talk at ICRA 2026 on "World Models: The Next Frontier of Motion Prediction". The talk sketches the history and also lays out what we plan to do at KE:SAI. Watch here: www.youtube.com/watch?v=sxlh...

Kashyap Chitta: World Models: The Next Frontier of Motion Prediction

Talk given on the 8th Workshop on Long-term Human Motion Prediction (LHMP) at ICRA 2026. Link to the Workshop website: https://motionpredictionicra2026.github.io Talk Abstract: Predicting how the…

youtube.com

Target points (from a system like Google maps) are how autonomous vehicles navigate long routes. However, make them too precise, and the policy exploits shortcuts. To deploy these systems in real-world conditions with low-res maps and noisy GPS, @kesai.eu is studying how to mitigate this bias.

World Engine is a RL post-training simulator for end-to-end driving. In collaboration with industry (and industry-scale data), we present an end-to-end policy post-trained within World Engine that achieves 200 km real driving without intervention. github.com/OpenDriveLab...

Super excited to share the last paper of my PhD: "Hallucination in World Models is Predictable and Preventable" ✨ We train a 350M-parameter generative world model on a large dataset spanning 210 tasks and show that we can predict *when* hallucination will happen and use that info to fix it! 🧵1/n

🔬 This week's KE:SAI research highlight is World Engine, a RL post-training simulator and pipeline for end-to-end driving. 📜 arxiv.org/abs/2606.19836

New Paper: arxiv.org/abs/2606.19370 Self-play yields capabilities but requires frustrating cost-function tuning. Surprisingly, just 30 minutes of demonstration data produces much more human-like driving policies! Led by @daphne-cornelisse.bsky.social Website: spiced-self-play.com

🌍 WorldEngine: Towards the Era of Post-Training for Physical AI 🎯 A post-training framework for Physical AI that systematically addresses the long-tail safety-critical data scarcity problem in autonomous driving. Github: github.com/OpenDriveLab... Project Page: opendrivelab.com/WorldEngine/

GitHub - OpenDriveLab/WorldEngine: WorldEngine: Towards the Era of Post-Training for Physical AI

WorldEngine: Towards the Era of Post-Training for Physical AI - OpenDriveLab/WorldEngine

github.com

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.org/abs/2606.19836

Andrei Bursuc@abursuc.bsky.social · 4mo ago

🌍WorldEngine is one of the most exciting projects in AD in the past years! It's a post-training framework tackling the scarcity of long-tail safety-critical scenarios by: mining -> 3DGS reconstruction and dynamic agents control w/ behavior world models -> RL post-training. Blog, code and data are up

🎰 Welcome to the FID Lottery. We pulled the lever 25 times on the same machine. Identical diffusion model, identical ImageNet class-cond recipe, only the seed changed. The house paid out anywhere from 33.59 to 35.69 FID. A 2.1-point spread, pure luck. Step onto the floor 👇🧵

If you were asked to paint this picture, how would you do it? (1/n) Most humans would not paint every pixel at once. This simple intuition inspired our ECCV 2026 paper: Trajectory Forcing. Project page: mervekocabas.github.io/TrajectoryFo... #ECCV2026

AI-accelerated warfare must stop! Together with @amnesty.org and +200 experts and civil society organizations, we are calling on governments and tech companies to ensure AI does not become a tool for accelerating death and destruction. Read our statement: www.accessnow.org/press-releas...

We're hiring a postdoc to push a moonshot that mixes world-modeling, unsupervised RL, and autonomy. More details here, and please help us get the word out! docs.google.com/document/d/1...

EMERGE Lab World Models / Unsupervised RL Postdoc

POSTDOCTORAL RESEARCHER WORLD MODELING / UNSUPERVISED RL EMERGE Lab The EMERGE lab at NYU is looking to hire a postdoc for an exciting moonshot project aimed at exploring the limits of learning in ...

docs.google.com

🔬 This week's research highlight is 123D, KE:SAI's effort to unify all open driving data, creating the largest and most diverse pool of autonomous driving data out there.

(1/9)🧵 This week's KE:SAI research highlight is our recent CVPR paper PrITTI: "PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes" arxiv.org/abs/2506.19117

(1/9)🧵 This week's KE:SAI research highlight is our recent CVPR paper PrITTI: "PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes" arxiv.org/abs/2506.19117

🧵Last week, I introduced KE:SAI, our new non-profit AI research organisation. Over the coming weeks, I’ll be sharing more about KE:SAI’s research. Today, we begin with our recent CVPR paper: **LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving** arxiv.org/abs/2512.20563