Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Flat cartoon illustration of a friendly coral-red lobster mascot character centered on dark charcoal background, one claw replaced with small silver mechanical robotic arm with visible joints, holding large white speech bubble containing ‘ROBOTS’ text in black Helvetica font, minimal geometric circuit board patterns in faint cyan in background, clean outlines, kawaii mascot style, high contrast, web interface aesthetic.
Introducing DreamZero 🤖🌎 from @nvidia > A 14B “World Action Model” that achieves zero-shot generalization to unseen tasks & few-shot adaptation to new robots > The key? Jointly predicting video & actions in the same diffusion forward pass Project Page: https://x.com/jang_yoel/status/2019083437265867057
New milestone: we trained a robot foundation model on a world model backbone, and enabled zero-shot, open-world prompting capability for new verbs, nouns, and environments. If the world model can “”dream”” the right future in pixels, then the robot can execute well in motors. We”” https://x.com/DrJimFan/status/2019112603637920237
📢 New paper from GEAR team @NVIDIARobotics We released DreamZero, a World Action Model that turns video world models into zero-shot robot policies. Built on a pretrained video diffusion backbone, it jointly predicts future video frames and actions. 🌐”” https://x.com/yukez/status/2019096072690553112
Introducing NVIDIA Cosmos Policy for Advanced Robot Control https://huggingface.co/blog/nvidia/cosmos-policy-for-robot-control
DreamZero: World Action Models are Zero-shot Policies
https://dreamzero0.github.io/
Jim Fan on X: “The Second Pre-training Paradigm” / X
https://x.com/DrJimFan/status/2018754323141054786
Website: https://t.co/2YwjQs3JMC Robot execution demos across various verbs, nouns, and environments: https://t.co/loUZXZODcR The model is open-source! https://x.com/DrJimFan/status/2019112605315637451
Planning is one of the most exciting uses of world models, but existing planners struggle on long horizons. Introducing GRASP: a fast gradient-based planner for world models that outperforms prior methods on long-horizon tasks. Two key ideas: 1.jointly optimize actions and”” https://x.com/_amirbar/status/2019903658792497482
tl;dr New planner for world models! GRASP: gradient-based, stochastic, parallelized. Long range planning for world models has always been an issue. 0th order methods like CEM/MPPI dominate, but have degrading performance at longer contexts or higher-dimensional actions. We”” https://x.com/michaelpsenka/status/2019870377032503595
Robbyant has announced LingBot-VLA: an open-source Vision-Language-Action model – Pretrained on ~20k hours of real-world dual-arm robot data – Strong generalization across 9 embodiments – Improves consistently with more data – Claims outperformance over π₀.₅, GR00T N1.6 &”” https://x.com/TheHumanoidHub/status/2017337216054575513
World Model meets robot policy! Robbyant’s LingBot-VA: unifies video world modeling and robotic policy learning. – A single model generates both future video and the actions to make it real. – Long-term memory enables long-horizon tasks. – Claims significant outperformance over”” https://x.com/TheHumanoidHub/status/2017638555741552672
self-driving <as a 2D robot with a low-dim action space that focused mostly on avoidance rather than interaction> will reach real-world impact faster than anything else. the really cool part is that the world model isn’t just about videos; it’s about modeling continuous,”” https://x.com/sainingxie/status/2019841784990351381
Humanoid whole-body control ASI benchmark”” https://x.com/TheHumanoidHub/status/2017293983115092168
Next Time You Come In, You Come Heavy Or Not At All”” https://x.com/adcock_brett/status/2016723547360809011
Similar to a human, Helix can use its hips to close a drawer and kick up the dishwasher door”” https://x.com/adcock_brett/status/2017654710778663399
Solve this in under 5 minutes and I’ll offer you $500k/year in cash plus several million in equity I’m building a Computer-Use team, goal is to use computers better than humans No experience or PhD needed Instructions: 1. Solve all 30 challenges on this website in under 5″” https://x.com/adcock_brett/status/2018417226895028414
This week we shared a detailed report on Helix 02 It explains how we’re working toward general robotics, for those who want to go deeper At the highest level of abstraction, our goal is to give AI a body”” https://x.com/adcock_brett/status/2016919225643008313
UPDATE: zero people have solved this”” https://x.com/adcock_brett/status/2018919553963880613
The Helix team at Figure spent the last 12 months hitting wall after wall on what seemed like a simple problem: How do we give our AI model, Helix, control of the entire humanoid body (pixels in; motor torques out)? Core to our belief is shipping fully autonomous robots that”” https://x.com/adcock_brett/status/2016743751088263238
🎙️ @stepjamUK is the founder and CEO of @Neuracore_AI, and Assistant Professor of Robot Learning at Imperial College London: In this episode, Stephen shares his path from growing up in Wales to spending a decade at Imperial, a postdoc at Berkeley, and eventually founding”” https://x.com/IlirAliu_/status/2016875729775145087
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”” https://x.com/IlirAliu_/status/2017309072165425316
3D printed differential robot arm wrist. [👇 GitHub Link – Open Source ] High demand, so they open sourced it early. A differential mechanism released as a test fixture for future robots. Built around their Spectral micro BLDC driver. Parts, STL files, example code are”” https://x.com/IlirAliu_/status/2018609427117465775
A collection of Python robotics algorithms (localization, SLAM, path planning, motion planning). (📍GitHub ) Python sample codes and textbook for robotics algorithms. GitHub: https://t.co/4NRf4VCkZP —- Weekly robotics and AI insights. Subscribe free: https://x.com/IlirAliu_/status/2018404604556513504
A motorized Almond Coupling, or Bent-Arm Joint. No supports or hardware needed. (📍 Link to Makerworld) It was invented and patented around 1885 as a right angle transmission coupling for steam and gas engines. 📍 https://t.co/IEslL2rhyI — Weekly robotics and AI insights.”” https://x.com/IlirAliu_/status/2018247037649637711
A peek inside Physical Intelligence, the startup building Silicon Valley’s buzziest robot brains | TechCrunch https://techcrunch.com/2026/01/30/physical-intelligence-stripe-veteran-lachy-grooms-latest-bet-is-building-silicon-valleys-buzziest-robot-brains/
AI in robotics gets all the attention right now, but sometimes the most interesting work is very practical. Viet built a small vision system that counts potatoes on a conveyor belt. No giant dataset. No huge model. Just a clear problem and a smart setup. He used Ultralytics’”” https://x.com/IlirAliu_/status/2017522263210312184
Building artificial life forces a new appreciation for biology.”” https://x.com/TheHumanoidHub/status/2017804851422396426
Chris Paxton on X: “New blog post: how do we quantify progress in robotics? Benchmarks have made a huge difference in other areas of AI, but we don’t have an equivalent to imagenet or SWE-Bench for robotics. Why not and what are people doing about it? Simulations, distributed evaluation, and https://t.co/KujXPHN9YG” / X
https://x.com/chris_j_paxton/status/2016872870001963433
Engineers at XPENG developed an RL pipeline to achieve a natural walking gait for the IRON humanoid, tailoring both the data and the algorithm to adapt to the stiffness of its lattice skin.”” https://x.com/TheHumanoidHub/status/2018375680837443631
How do you teach a robot to handle complex, multi-step tasks, without training it for each one? [Github ⬇️] The team behind ReKep shows that robots can perform bimanual, in-the-wild tasks by reasoning over keypoint constraints: Generated on the fly using vision and language”” https://x.com/IlirAliu_/status/2018971869236310248
HumanX: a scalable framework that converts single monocular human videos into agile, generalizable interaction skills for humanoid robots without task-specific rewards. Core parts: – XGen: retargets human motion + synthesizes diverse physically plausible training data (via”” https://x.com/TheHumanoidHub/status/2018922472616391029
moltbook but real robots 😨”” https://x.com/TheHumanoidHub/status/2017721951595466845
Things didn’t go entirely according to plan, when XPENG’s latest generation IRON robot made a striking public appearance at a shopping mall.”” https://x.com/TheHumanoidHub/status/2017646098136141858
XPENG plans to enter mass production of IRON humanoids this year.”” https://x.com/TheHumanoidHub/status/2017700729876877313
AGI stuck in a box will always rely on humans to act in the physical world In the extreme, they will boss around humans Humanoid robots are the ultimate deployment vector for AGI”” https://x.com/adcock_brett/status/2018770644993978433
Reinforcement Learning for Active Perception in Autonomous Navigation. [📍GitHub & Paper ] Most robots navigate as if their cameras were nailed in place. But perception is not passive. Animals move their heads and eyes constantly to decide where to go next. Robots should do”” https://x.com/IlirAliu_/status/2018762226170016109
Robust humanoid perceptive locomotion is still underexplored. Especially when different cameras see different terrains, paths get narrow, and payloads disturb balance… Introduce RPL, tackling this with one unified policy: • Challenging terrains (slopes, stairs and stepping”” https://x.com/Yuanhang__Zhang/status/2019092752240181641
Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single”” https://x.com/IlirAliu_/status/2017884655869976975
Hard to know which X articles are valuable, but this is a good summary of the significance of world modeling by a distinguished scientist and robot expert NVIDIA”” https://x.com/emollick/status/2018774863734075878
Leave a Reply