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.

Excellent speaker lineup for the @naverlabseurope.bsky.social AI for Robotics Workshop. For those at home, the event is live-streamed on the landing page: europe.naverlabs.com/updates/ai4r...

We’re live! 🚀 Streaming: tinyurl.com/bdtk2nzs The International Workshop on AI4Robotics by @naverlabseurope 2dys of Spatial AI, SLAM, robot learning, HRI, autonomy This AM CET: @martinhumenberger.bsky.social @marcpollefeys.bsky.social Andrea Vedaldi Cordelia Schmid & @andrewdavidson.bsky.social ⬇️

A fascinating and historic panel discussion with six of the recipients of the 2025 Queen Elizabeth Prize for Engineering, honoring the critical interplay between Algorithms, Data, and Compute that gave rise to today’s remarkable advances in AI and Machine Learning

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!

X-mas came earlier this year! Nvidia has just released the huge Physical AI AV Dataset - 1727 hrs of driving data: 310K clips of 20s - sensor rig: 7 cameras, lidar, radar - 25 countries, 2.5K cities from US + Europe Kudos to @kashyap7x.bsky.social et al.! huggingface.co/datasets/nvi...

Hundreds of hours of European driving data from NVIDIA! 1700 hours total

Big day for autonomous driving research. Nvidia just dropped 1700 hours of public driving data on HuggingFace from over 2500 cities: huggingface.co/datasets/nvi...

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!

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

🚀 The new call for Principal Investigators as Hector Endowed Fellows at the ELLIS Institute Tübingen is now open! These positions offer the exciting possibility of co-appointments with the @mpi-is.bsky.social and the @tuebingen-ai.bsky.social . 📌 Apply here: institute-tue.ellis.eu/en/jobs/PI-c...

Today is the day for our @iccv.bsky.social workshop that we've been cooking with excitement in the past months. Learning to See: Advancing Spatial Understanding for Embodied Intelligence #ICCV2025 Join us! opendrivelab.com/iccv2025/wor...

🚗 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

Over the past year, my lab has been working on fleshing out theory + applications of the Platonic Representation Hypothesis. Today I want to share two new works on this topic: Eliciting higher alignment: arxiv.org/abs/2510.02425 Unpaired learning of unified reps: arxiv.org/abs/2510.08492 1/9

CVPR 2026 Workshop Call is officially open! 🎉 📅 Deadline: Nov 3, 2025 cvpr.thecvf.com/Conferences/... We expect to host over 100 workshops this year — and this is where the next breakthroughs begin. 🚀 With Mei Chen,Erik Blasch,Brian Clipp,Sharon Huang,Andreas Savakis @cvprconference.bsky.social

Personal programs for ICCV 2025 are now available at: www.scholar-inbox.com/conference/i...

We're finally out of stealth: percepta.ai We're a research / engineering team working together in industries like health and logistics to ship ML tools that drastically improve productivity. If you're interested in ML and RL work that matters, come join us 😀

We've hired some *fantastic* researchers but our startup is still looking for 2-3 more people with skills in ML/RL/LLMs. If you'd like to work on some transformative applied problems, hit me up. We'll be launching publicly soon too...

We're recruiting our next batch of interns. Come join the team! nvidia.wd5.myworkdayjobs.com/en-US/NVIDIA...

How AI Taught Itself to See Self-supervised learning is fascinating! How can AI learn from images only without labels? In this video, we’ll build the method from first principles and uncover the key ideas behind CLIP, MAE, SimCLR, and DINO (v1–v3). Video link: youtu.be/oGTasd3cliM

Putting the final touches on your submission? Just a few days left to enter the @iccv.bsky.social NAVSIM Challenge! Deadline: September 20. $8K in prizes and several travel grants are on the line!

Found this marvelous little course full of readings to trace the evolution of computer science and its canonical ideas graphics.stanford.edu/courses/cs20...

Our Principal Investigators Antonio Orvieto, Celestine Mendler-Dünner, Maximilian Dax, Rediet Abebe, @shiweiliu.bsky.social, T. Konstantin Rusch, and @wielandbrendel.bsky.social are looking for motivated students interested in internships. Apply here: docs.google.com/forms/d/e/1F...

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/ 🧵👇

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/ 🧵👇

🎓 Interested in a #PhD in machine learning or #AI? The ELLIS PhD Program connects top students with leading researchers across Europe. The application portal opens on Oct 1st. Curious? Join our info session on the same day. Get all the info 👉

Let's push for the obvious solution: Dear @neuripsconf.bsky.social ! Allow authors to present accepted papers at EurIPS instead of NeurIPS rather than just additionally. Likely, at least 500 papers would move to Copenhagen, problem solved.

🚀 Introducing our new paper, MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models. 📄 Paper: www.scholar-inbox.com/papers/He202... arxiv.org/pdf/2508.13148 💻 Code: github.com/autonomousvi... 🌐 Project Page: cli212.github.io/MDPO/

Introducing DINOv3 🦕🦕🦕 A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale. High quality dense features, combining unprecedented semantic and geometric scene understanding. Three reasons why this matters👇

Our paper "CaRL: Learning Scalable Planning Policies with Simple Rewards" has been accepted to the Conference on Robot Learning (CoRL 2025). See you in Seoul at the end of September. Code & Paper: github.com/autonomousvi...

At TRI’s newest division: Automated Driving Advanced Development, we’re building a clean-slate, end-to-end autonomy stack. We're hiring, with open roles in learning, infra, and validation: www.tri.global/careers#open...

1/ Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research.

Adding a nice way to visualize the PPO objective to the rlhf book. Core for policy-gradient is L is proportional to R*A (R=policy ratio, A = advantage). PPO makes good actions more likely, up to a point. PPO makes bad actions less likely, up to a point.