Testing the robot handing out swag before Christmas break🎄

宇田君がIROSで発表したクローラロボットをyoutubeにアップしました。体の任意の点を曲げることで、狭路や段差を器用に踏破することができます。 https://t.co/mtfERj2CoA 実は大幅にパワーアップしたver.も既に開発しており、近いうちに公開出来ると思います。

Robotic Olaf の肩をかみしめる なるほどなぁ ボールベアリングとボールジョイントの組合せで楽しめそうだ

Demo showing our system doing autonomous assembly of a part! What else should we have it do? And if you want a hand, wait list is open here! https://t.co/bh9Xv05eje

Disney olaf robot. Classic mimic RL with nice modelling. Surprisingly small legs and big necks.

It turns out that VLAs learn to align human and robot behavior as we scale up pre-training with more robot data. In our new study at Physical Intelligence, we explored this "emergent" human-robot alignment and found that we could add human videos without any transfer learning!

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can

(1/6) X-Humanoid 🤖: Scaling up data for Humanoid Robots. We convert human daily activity videos (from Ego-Exo4D) into humanoid videos (i.e., Tesla Optimus) performing tasks like cooking or fixing a bike. This data can be potentially used to train robot policies and world

Generalist robots need a generalist evaluator. But how do you test safety without breaking things? 💥 🌎 Introducing our new work from @GoogleDeepMind: Evaluating Gemini Robotics Policies in a Veo World Simulator https://t.co/ZjvpYXFddZ 🧵👇

Safety in mobile robotics! 👷🏼‍♂️ Robots navigating through crowds is one of the hardest problems in mobile robotics, uncertainty, human motion, and real-time constraints don’t mix well. A team at @tudelft has introduced DRA-MPPI, a new motion-planning method that lets robots move

1.7× faster inverse kinematics in pure Python, GPU-accelerated! Fully open-source and built for scale [📍Bookmark for later] PyRoki, a modular toolkit for robot kinematic optimization, supporting - inverse kinematics - trajectory optimization, and - motion retargeting. Built

Robotic oil painting powered by a learning-based pixel dynamics model (world-model style). 🤖🎨 The key part? Once you have a reasonably good model (even an approximate one) you unlock a ton of possibilities through inverse optimization, from motion planning and corrective

GPU parallelized envs have accelerated RL, but most implementations exhibit critical instability when running on-policy RL with short rollouts. We present Staggered Environment Resets. A few lines of code are all you need! Presenting today, 4:30PM poster 310 #NeurIPS2025 🧵(1/8)

Always important to remember that a lot of these robots are "faking" the humanlike motions -- its a property of how they're trained not an inherent property of the hardware. They're actually capable of way weirder stuff and way faster motions.

🚀 Introducing X-VLA ; LeRobot’s new soft-prompted Vision-Language-Action model. X-VLA is built to scale across many embodiments: different robots, cameras, action spaces, and environments, all handled by one unified transformer backbone. - Generalist across robots (Franka,

📢#NeurIPS2025 Welcome to check out our work @NeurIPSConf📢 * 3D Gen - PhysX: https://t.co/JQQbV8PWgI * VLM - GUI-Reflection: https://t.co/mRpl6CaOAc - ShotBench: https://t.co/ftsZqQxqI4 * World Model - Spatial Mem: https://t.co/aiyloarmsH - Imagine360: https://t.co/VKrwbc0mXc

Can we quickly improve a pre-trained robot policy by learning from real world human corrections? Introducing Compliant Residual DAgger (CR-DAgger), a system that improves policies performance to close to 100% on challenging contact-rich manipulation problems, using as few as

🤖 New paper: MobileVLA-R1 A unified VLA system that brings real reasoning + continuous control to quadruped robots. CoT dataset, 2-stage training, real-world deployment. 📄paper & code & demo: https://t.co/w1FqDRS5K4

@faraz_r_khan @spectral_hq Plugin is internal. We are working with a select group of partners to make it and an API available. Please let us know if you are interested (dm). We also have a hugging face space where you can play with a preview of the model today.