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...

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...

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

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

🔬 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-...

@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...

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).

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.

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!

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.

Another fantastic post from @kashyap7x.bsky.social open.substack.com/pub/kashyap7...

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/...

📣 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/

🌍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

We're releasing OVIE, a novel view generation model trained entirely on single images. No multi-view datasets needed. Given a single image, it generates novel views of any scene in real time, running orders of magnitude faster than competing approaches.

MolmoBot, our open robotic manipulation suite trained entirely in simulation, now has code, training data, a data generation pipeline, & evals all available. This puts our robotics models within reach of any research lab—no extensive real-world data collection required. 🧵

Following the success of the EurIPS and NeurIPS-Mexico City pilots in 2025, we are thrilled to announce two official NeurIPS 2026 satellite events for this year! These will be held in Paris, France and Atlanta, USA, respectively, running alongside the main venue in Sydney, Australia.

Naver AI has put the word "World" into "World Models", at least on a metropolis scale: A world model for Seoul using Naver Maps (the Seoul capital area is 25.6 million people, btw.). seoul-world-model.github.io arxiv.org/abs/2603.15583 @jnhwkim.bsky.social

Today, a step forward in open robotics - our results show that sim-to-real zero shot transfer for manipulation is possible. MolmoBot is our open model suite for robotics, trained entirely in simulation on MolmoSpaces.🧵

Interested in ✨world models✨? I just open-sourced an implementation of the Dreamer 4 world model. It's in PyTorch and comes with a pretrained model + a neat little web interface that lets you interact with any of 30 DMControl tasks that I trained it on! Link: github.com/nicklashanse...

cseweb.ucsd.edu/~tzli/novelt... I gave an internal talk at UCSD last year regarding "novelty" in computer science research. In it I "debunked" some of the myth people seem to have about what is good research in computer science these days. People seemed to like it, so I thought I should share.

Simple and efficient transformer based end-to-end driving. If we could give out another innovation award for NAVSIM, it would go to this work! valeoai.github.io/driving-on-r...

While we also hype the moderation features, I'm really excited about the paper discovery tools @mariaa.bsky.social and I are starting to build. Open social means we can bootstrap onto existing discussions that are happening

Wrapping up 2025 with a review of some recent work, led by several amazing students and collaborators: Yixuan Pan, Ruoyi Qiao, @jiazhiyang.bsky.social, Shuhan Tan, Brayden Zhang, Shihao Li, @longpollehn.bsky.social, Peter Karkus, and @maxigl.bsky.social! kashyap7x.substack.com/p/2025-resea...

Wrapping up 2025 with a review of some recent work, led by several amazing students and collaborators: Yixuan Pan, Ruoyi Qiao, @jiazhiyang.bsky.social, Shuhan Tan, Brayden Zhang, Shihao Li, @longpollehn.bsky.social, Peter Karkus, and @maxigl.bsky.social! kashyap7x.substack.com/p/2025-resea...

Our new E2E driving method, TransFuser v6, is out on ArXiv. It outperforms all other methods on CARLA by a wide margin, 95 DS on Bench2Drive! We show that minimizing the asymmetry between data annotator and policy is key for strong IL results. Code, models, and paper: ln2697.github.io/lead/

🧥 Live-stream robotic teamwork that folds clothes. 6 clothes in 3 minutes straight. χ₀ = 20hrs data + 8 A100s + 3 key insights: - Mode Consistency: align your distributions - Model Arithmetic: merge, don't retrain - Stage Advantage: pivot wisely 🔗 mmlab.hk/research/kai0 checkout 3mins demo

What's left to do in self-driving given Waymo is taking off? An argument that it's still a great research problem: open.substack.com/pub/emergere...

More details at tuebingen.ai/news/ai-powe...

waymo.com/blog/2025/12... Waymo is training End-to-End driving models with RL in simulation.

Speaking of RL, Nvidia also just published a survey on the importance of closed-loop training (RL, etc.) in E2E driving. research.nvidia.com/publication/...

Attending #Neurips2025? Get your personalized Scholar Inbox conference program now to easily navigate the poster sessions and find what you are looking for: www.scholar-inbox.com/conference/n...

I'll be at #NeurIPS2025 in San Diego from Thu to Sat, and I am looking for PostDocs in Embodied AI, particularly in world modeling and simulator learning. Please reach out if you are interested.

Wondering how DeepSeek v3.2 rivals SOTA models (e.g., GPT5/Gemini 3 pro) while being ~30x cheaper? 🤔 Let's learn how the base model works! We'll focus on attention, the need for KV caching, and key ideas for improving attention (MQA/GQA/MLA/DSA). youtu.be/Y-o545eYjXM

🚀 Introducing TMLR Beyond PDF! 🎬 This is a new, HTML-based submission format for TMLR, that supports interactive figures and videos, along with the usual LaTeX and images. 🎉 Thanks to TMLR Editors in Chief: Hugo Larochelle, @gautamkamath.com, Naila Murray, Nihar B. Shah, and Laurent Charlin!

TMLR (@tmlrorg.bsky.social) is now proud to support interactive HTML-based submissions, going "Beyond PDF" -- check it out! Thanks to Paul Vicol (@paulvicol.bsky.social) for his tireless work on this new option, as well as the OpenReview team.