iiinova — where your digital self keeps evolving

Reposted by Daniel Dauner

KE:SAI - Kyutai ELLIS Scalable Autonomous Intelligence @kesai.eu · 17/07/2026

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...

0216

Reposted by Daniel Dauner

KE:SAI - Kyutai ELLIS Scalable Autonomous Intelligence @kesai.eu · 28/06/2026

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...

062

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 27/06/2026

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.

282

Reposted by Daniel Dauner

Bernhard Jaeger @bernhard-jaeger.bsky.social · 09/06/2026

🔬 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.

184

Reposted by Daniel Dauner

Bernhard Jaeger @bernhard-jaeger.bsky.social · 03/06/2026

(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

132

Reposted by Daniel Dauner

Andrei Bursuc @abursuc.bsky.social · 01/06/2026

Over the years models got bigger, tasks more diverse and harder, datasets larger, etc. However, the message between the lines in AZ’s talks remained the same: everyone, look really carefully at your data, so many questions and solutions come from there. #CVPRinParis

1164

Reposted by Daniel Dauner

Bernhard Jaeger @bernhard-jaeger.bsky.social · 29/05/2026

🧵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

152

Reposted by Daniel Dauner

KE:SAI - Kyutai ELLIS Scalable Autonomous Intelligence @kesai.eu · 24/05/2026

KE:SAI has been (briefly) featured in ZDF Länderspiegel! Watch here (starting at 17:00, in German): www.zdf.de/video/magazi...

094

Reposted by Daniel Dauner

Bernhard Jaeger @bernhard-jaeger.bsky.social · 20/05/2026

Today, we are launching KE:SAI, a new non-profit open-science research organization dedicated to physical AI research, particularly autonomous driving. Our goal is to build the first competitive, fully open autonomous driving stack. kesai.eu/blog/2026-05...

1224

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 20/05/2026

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.

kesai.eu

KE:SAI — Open Science Autonomy Lab

KE:SAI is a Franco-German non-profit open science lab for scalable autonomous intelligence.

1316

Reposted by Daniel Dauner

Andrei Bursuc @abursuc.bsky.social · 19/05/2026

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!

0154

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 18/05/2026

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.

0258

Reposted by Daniel Dauner

Christian Wolf @chriswolfvision.bsky.social · 25/03/2026

Jensen's inequality

4609

Reposted by Daniel Dauner

Tzu-Mao Li @tzumaoli.bsky.social · 09/01/2026

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.

cseweb.ucsd.edu

27625

Reposted by Daniel Dauner

Bernhard Jaeger @bernhard-jaeger.bsky.social · 27/12/2025

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/

0316

Reposted by Daniel Dauner

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 21/12/2025

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...

open.substack.com

Why study self-driving?

Isn't it "solved"?

1638

Reposted by Daniel Dauner

Andreas Geiger @andreasgeiger.bsky.social · 02/12/2025

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...

03612

Reposted by Daniel Dauner

Bernhard Jaeger @bernhard-jaeger.bsky.social · 01/12/2025

Scholar Inbox for NeurIPS is live now.

0145

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 28/10/2025

Launching the Physical AI AV Dataset! 🚀 huggingface.co/datasets/nvi... One of the largest, most diverse & commercially usable open-source datasets for AVs. - 1727 hours of driving data - Camera, LiDAR, & radar - 25 countries, 2500+ cities This is just the beginning, more features to come!

0287

Reposted by Daniel Dauner

Andreas Geiger @andreasgeiger.bsky.social · 24/10/2025

Congratulations to our PhD student @takerumiyato.bsky.social for winning the Google PhD Fellowship in the category "Machine Learning and ML Foundations". Takeru is pioneering new neural architectures that improve generalization and efficiency. Check out his research: takerum.github.io

takerum.github.io

Takeru Miyato - AI Research Scientist

PhD student at University of Tübingen working on artificial intelligence, machine learning, and deep learning research.

0293

Reposted by Daniel Dauner

Yiyi Liao @yiyiliao.bsky.social · 19/10/2025

🚗 Join us for the RealADSim Workshop @ ICCV 2025! 🗓 Oct 19 morning | 📍 Hawaii Conv. Center, 305A Featuring exciting talks and winner presentations from our challenges (70+ regs, ~30 subs). Don’t miss it! 🎉 #ICCV2025

074

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 01/09/2025

Announcing the @iccv.bsky.social NAVSIM Challenge! What's new? We're testing not only on real recordings, but also perturbed futures generated from the real ones via pseudo-simulation! $8K in prizes + several $1.5k travel grants. Submit by September 20! opendrivelab.com/challenge2025/ 🧵👇

1149

Reposted by Daniel Dauner

Christian Wolf @chriswolfvision.bsky.social · 12/08/2025

NeurIPS PCs: Borderline Reject: "Please use sparingly" NeurIPS reviewers: BR go BR BR BR BR BR BR

3222

Reposted by Daniel Dauner

Bernhard Jaeger @bernhard-jaeger.bsky.social · 31/07/2025

One concern that I have as an AI researcher when publishing code is that it can potentially be used in dual-use applications. To solve this, we propose Civil Software Licenses. They prevent dual-use while being minimal in the restrictions they impose: civil-software-licenses.github.io

civil-software-licenses.github.io

Civil Software Licenses

3163

Reposted by Daniel Dauner

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 15/07/2025

New YouTube playlist category is Relaxing self-driving agents to vibe to

0141

Reposted by Daniel Dauner

Bernhard Jaeger @bernhard-jaeger.bsky.social · 15/07/2025

We have released the code for our work, CaRL: Learning Scalable Planning Policies with Simple Rewards. The repository contains the first public code base for training RL agents with the CARLA leaderboard 2.0 and nuPlan. github.com/autonomousvi...

github.com

GitHub - autonomousvision/CaRL: [ArXiv 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards

[ArXiv 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards - autonomousvision/CaRL

0207

Daniel Dauner @danieldauner.bsky.social · 15/07/2025

Back in 2023, I worked on rule-based planning for the nuPlan challenge and was skeptical that learned methods could do well on this benchmark. Turns out, RL is the answer. The CaRL code is out now. Also check out this 2h+ demo video of our policy: youtu.be/_godUKkICec

youtu.be

CaRL: Learning Scalable Planning Policies with Simple Rewards

YouTube video by Daniel Dauner

041

Reposted by Daniel Dauner

Andreas Geiger @andreasgeiger.bsky.social · 15/07/2025

In case you find it as relaxing as we do: Here is a 2h+ video of our autonomous RL driving agent CaRL in action! @danieldauner.bsky.social @bernhard-jaeger.bsky.social @kashyap7x.bsky.social youtube.com/watch?v=_god...

youtube.com

CaRL: Learning Scalable Planning Policies with Simple Rewards

YouTube video by Daniel Dauner

0215

Reposted by Daniel Dauner

Andreas Geiger @andreasgeiger.bsky.social · 25/06/2025

Christina's new work PrITTI generates high-quality, controllable 3D semantic urban scenes in a compact primitive-based representation using a latent diffusion model. This enables applications like scene editing, inpainting, and photo-realistic street view synthesis! raniatze.github.io/pritti/

0137

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 17/06/2025

The 2025 Waymo Challenge results are out! We achieved second place in the End-to-End Driving Challenge with DiffusionLTF and third place in the Scenario Generation Challenge with SHRED. Our approaches prioritized simplicity, and we're preparing to make them publicly available soon.

1155

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 05/06/2025

🚗 Pseudo-simulation combines the efficiency of open-loop and robustness of closed-loop evaluation. It uses real data + 3D Gaussian Splatting synthetic views to assess error recovery, achieving strong correlation with closed-loop simulations while requiring 6x less compute. arxiv.org/abs/2506.04218

02210

Reposted by Daniel Dauner

Andreas Geiger @andreasgeiger.bsky.social · 16/05/2025

EMPERROR is a new generative perception error model for probing self-driving planners. It imitates modern 3D detectors, maintains temporal consistency, and reveals brittleness in IL-based planning - raising collision rates by up to 85%! #RA_L #robotics #AI - lasnik.github.io/emperror/

194

Reposted by Daniel Dauner

Katrin Renz @katrinrenz.bsky.social · 08/05/2025

📣 Excited to share our #CVPR2025 Spotlight paper and my internship project @wayve: SimLingo. A Vision-Language-Action (VLA) model that achieves state-of-the-art driving performance with language capabilities. Code: github.com/RenzKa/simli... Paper: arxiv.org/abs/2503.09594

1259

Daniel Dauner @danieldauner.bsky.social · 08/05/2025

I've always found the default Alt+Tab behavior in Ubuntu frustrating. Recently, I discovered this plugin for GNOME distros. Personally, it’s a game changer and enables switching windows specific to the application, monitor, and workspaces. Highly recommend! github.com/G-dH/advance...

github.com

GitHub - G-dH/advanced-alttab-window-switcher: A highly customizable replacement for Gnome Shell's Alt-Tab window and app switchers.

A highly customizable replacement for Gnome Shell's Alt-Tab window and app switchers. - G-dH/advanced-alttab-window-switcher

020

Reposted by Daniel Dauner

Stefano Esposito @s-esposito.bsky.social · 05/05/2025

📢 New paper CVPR 25! Can meshes capture fuzzy geometry? Volumetric Surfaces uses adaptive textured shells to model hair, fur without the splatting / volume overhead. It’s fast, looks great, and runs in real time even on budget phones. 🔗 autonomousvision.github.io/volsurfs/ 📄 arxiv.org/pdf/2409.02482

13221

Reposted by Daniel Dauner

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 28/04/2025

Waited to finish reading it but I wanted to highlight the nice reward design here, which alleviates many of the failures of reward shaping

1225

Reposted by Daniel Dauner

Bernhard Jaeger @bernhard-jaeger.bsky.social · 28/04/2025

Introducing CaRL: Learning Scalable Planning Policies with Simple Rewards We show how simple rewards enable scaling up PPO for planning. CaRL outperforms all prior learning-based approaches on nuPlan Val14 and CARLA longest6 v2, using less inference compute. arxiv.org/abs/2504.17838

02414

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 28/04/2025

⏰ Heads up! The deadline for two #CVPR2025 Autonomous Grand Challenge tracks is May 10th, 2025: 1️⃣ NAVSIM v2 Challenge: huggingface.co/spaces/AGC20... 2️⃣ World Model Challenge by 1X: huggingface.co/spaces/1x-te...

196

Reposted by Daniel Dauner

Andreas Geiger @andreasgeiger.bsky.social · 14/04/2025

🚀 Never miss a beat in science again! 📬 Scholar Inbox is your personal assistant for staying up to date with your literature. It includes: visual summaries, collections, search and a conference planner. Check out our white paper: arxiv.org/abs/2504.08385 #OpenScience #AI #RecommenderSystems

19420

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 13/04/2025

Announcing the 2025 NAVSIM Challenge! What's new? We're testing not only on real recordings—but also imaginary futures generated from the real ones! 🤯 Two rounds: #CVPR2025 and #ICCV2025. $18K in prizes + several $1.5k travel grants. Submit in May for Round 1! opendrivelab.com/challenge2025/ 🧵👇

11810

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 17/03/2025

🐎 Centaur, our first foray into test-time training for end-to-end driving. No retraining needed, just plug-and-play at deployment given a trained model. Also, theoretically nearly no overhead in latency with some clever use of buffers. Surprising how effective this is! arxiv.org/abs/2503.11650

1127

Reposted by Daniel Dauner

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 12/03/2025

Building a "human-level" simulated driver that zero-shot generalizes to many benchmarks: a fun interview with @natolambert.bsky.social www.youtube.com/watch?v=2Q66...

youtube.com

Self-play for Self-driving and where Scaling Reinforcement Learning is Heading with Eugene Vinitsky

YouTube video by Interconnects AI

0183

Reposted by Daniel Dauner

OpenDriveLab @opendrivelab.bsky.social · 03/03/2025

🚀 This year, we’re bringing you three thrilling tracks in Embodied AI and Autonomous Driving, with a total prize pool of $100,000! Now get ready and join the competition! Visit the challenge website: opendrivelab.com/challenge2025 And more on #CVPR2025: opendrivelab.com/cvpr2025

054

Reposted by Daniel Dauner

Andreas Geiger @andreasgeiger.bsky.social · 12/02/2025

Synchronization is ubiquitous in nature and a key mechanism for information processing in the brain. We introduce AKOrN as a dynamical alternative to threshold units, which can be combined with MLPs, CNNs or Transformers. ICLR'25 Oral. Project page: takerum.github.io/akorn_projec...

24611

Reposted by Daniel Dauner

Kashyap Chitta @kashyap7x.bsky.social · 23/01/2025

The NAVSIM challenge will be back in 2025! Stay tuned 🚗 github.com/autonomousvi...

074

Reposted by Daniel Dauner

Andreas Geiger @andreasgeiger.bsky.social · 16/01/2025

This week we had our winter retreat jointly with Daniel Cremer's group in Montafon, Austria. 46 talks, 100 Km of slopes and night sledding with some occasionally lost and found. It has been fun!

07211