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.
Kashyap Chitta
@kashyap7x.bsky.social
kashyap7x.github.io Principal Investigator at ELLIS Institute Tübingen; Co-Founder and CTO at kesai.eu; Physical AI, Robot Learning, Autonomous Driving.
🚀 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
🏹 Job Alert: Research Scientist in World Models and Autonomy at KE:SAI 📍 Tübingen 🇩🇪 🔗 https://kesai.eu/join/
KE:SAI — Open Positions at Our AI Research Lab
Join KE:SAI, a Franco-German non-profit AI research lab co-located in Tübingen and Paris. Open positions for researchers in physical AI and autonomous systems.
kesai.eu
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...
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 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
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.
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.
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
You really should be using scholar inbox. Don't want to gate keep how useful this is: www.scholar-inbox.com
Scholar Inbox - Free Academic Paper Recommendations
Scholar Inbox is a free personal paper recommender enabling researchers to stay up-to-date with the most relevant progress in their field. Daily indexes arXiv, bioRxiv, medRxiv, ChemRxiv and open acce...
scholar-inbox.com
Interested in the ELLIS Summer School on Autonomous Driving? 🚗 Let's meet our speakers! Today we introduce @kashyap7x.bsky.social (Co-Founder & Chief Technology Officer at @kesai.eu) 📝 (New) Application deadline: June 12, 2026 pages.cvc.uab.es/ssadriving/
Missed the deadline? You’re in luck! 🚨 👉 Deadline Extended: Friday, 12 June! Last call to dive into robust, multimodal AI for autonomous driving! 🏎️✨ 👇 Apply before Friday! pages.cvc.uab.es/ssadriving/ @ellis.eu @valeoai.bsky.social @uab.cat
ELLIS Summer School on Autonomous Driving — Barcelona 2026
An official ELLIS Summer School — four intensive days in Barcelona where world-class researchers and the next generation of scientists converge to push the boundaries of perception, world models, end-to-end driving, and beyond.
pages.cvc.uab.es
ELLIOT Project@elliot-eu.bsky.social · 3mo agoThe future of Autonomous Driving is heading to Barcelona! 🏎️🏙️ Supported by ELLIOT, this ELLIS Summer School allows researchers to learn from experts and build new collaborations over four intensive days. 🚀 Apply by 8 June! ⏳ pages.cvc.uab.es/ssadriving/ @ellis.eu @valeoai.bsky.social @uab.cat
🔬 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.
KE:SAI has been (briefly) featured in ZDF Länderspiegel! Watch here (starting at 17:00, in German): www.zdf.de/video/magazi...
Bill Gurley made a fantastic post on the case for open-science labs like KE:SAI. A strongly encouraged read on open source in general and for autonomous vehicles in particular! p3institute.substack.com/p/from-open-...
From Open Source Software to Open Source Strategy
How the Smartest Executives Are Using Open Source Techniques to Optimize Corporate Strategy
p3institute.substack.com
@kesai.eu is a joint venture of @kyutai-labs.bsky.social and @ellisinsttue.bsky.social. We are a focused team building fully open stacks together with the community. We have locations in Tübingen and Paris. If you want to build the future of open physical AI with us, we’re hiring! kesai.eu/join
Today @kyutai-labs.bsky.social and @ellisinsttue.bsky.social launch @kesai.eu! Robot learning is bottlenecked by the cost of physical interaction. Our mission is to advance the efficiency frontier of robust & safe physical AI through fully open and reproducible research. kesai.eu/blog/2026-05...
Kyutai and ELLIS Tübingen launch KE:SAI: A Premier Franco-German Partnership for Open Science in Physical AI
Kyutai and ELLIS Tübingen announce the official launch of KE:SAI – Kyutai ELLIS Scalable Autonomous Intelligence, a non-profit open science lab for physical AI.
kesai.eu
Hello world from @kesai.eu! Here is a new non-profit open-science AI lab based in Tübingen and Paris pushing the frontiers of Physical AI and self-driving in particular. They have a top-notch founding team, an ambitious agenda and incredible supporters (the team behind @kyutai-labs.bsky.social).
Kashyap Chitta@kashyap7x.bsky.social · 3mo agoOpen-source fueled the LLM revolution, but Physical AI hasn't fully benefited from this flywheel yet. Today, we're launching kesai.eu, our mission to democratize robotics research! First milestone: training a frontier-level self-driving policy using significantly less data than typically required.
Open-source fueled the LLM revolution, but Physical AI hasn't fully benefited from this flywheel yet. Today, we're launching kesai.eu, our mission to democratize robotics research! First milestone: training a frontier-level self-driving policy using significantly less data than typically required.
KE:SAI — Open Science Autonomy Lab
KE:SAI is a Franco-German non-profit open science lab for scalable autonomous intelligence.
kesai.eu
pip install py123d 3,300 hours of multimodal driving data at your fingertips (Physical AI AV + nuPlan + … + can add custom datasets)! 📄 Paper: arxiv.org/abs/2605.08084 ⭐️ GitHub: github.com/kesai-labs/py123d Monumental effort led by @danieldauner.bsky.social to accelerate open-source AV research.
py123d: @danieldauner.bsky.social et al. did all the crazy and dirty work to unify the highly heterogeneous autonomous driving datasets into a single efficient data format. nuscenes + nuplan + Waymo + Physical AI AV, etc., are all there. This is how you accelerate open-source AD research!
Kashyap Chitta@kashyap7x.bsky.social · 3mo agopip install py123d 3,300 hours of multimodal driving data at your fingertips (Physical AI AV + nuPlan + … + can add custom datasets)! 📄 Paper: arxiv.org/abs/2605.08084 ⭐️ GitHub: github.com/kesai-labs/py123d Monumental effort led by @danieldauner.bsky.social to accelerate open-source AV research.
pip install py123d 3,300 hours of multimodal driving data at your fingertips (Physical AI AV + nuPlan + … + can add custom datasets)! 📄 Paper: arxiv.org/abs/2605.08084 ⭐️ GitHub: github.com/kesai-labs/py123d Monumental effort led by @danieldauner.bsky.social to accelerate open-source AV research.
MolmoAct 2 is a foundation built for others to study, deploy, & customize. 📝 Learn more in our blog: allenai.org/blog/molmoact2 🤖 Models: huggingface.co/collections/... 📊 Training dataset: huggingface.co/collections/...
MolmoAct 2: An open foundation for robots that work in the real world | Ai2
MolmoAct 2 is a fully open robotics foundation model that brings faster, stronger 3D action reasoning to real-world robot tasks, alongside a major new bimanual manipulation dataset for researchers to ...
allenai.org
📣 ELLIS | ELLIOT Summer School on Autonomous Driving 🚗 Super happy to announce the hottest event this summer. Apply now! 📅 September 15-18, 2026 📍Barcelona, Spain 🌐 pages.cvc.uab.es/ssadriving/ @ellis.eu, ELLIS-Barcelona, CVC-Barcelona, @valeoai.bsky.social ai.bsky.social, @elliot-eu.bsky.social
🌍 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
🌍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
OpenDriveLab@opendrivelab.bsky.social · 4mo ago🌍 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/