Vision-Language Reasoning: Reason through the physical world. pic.twitter.com/VHxJEJZQrz
— NVIDIA AI (@NVIDIAAI) 2 juin 2026
Vision-Language Reasoning: Reason through the physical world.
ROBOTICS
-
Vision-Language Reasoning for Physical World Understanding
By
–
-
New edition of ‘Rise of the Robots’ on AI and jobless future
By
–
The new edition of "Rise of the Robots: Technology and the Threat of a Jobless Future" is now available! I have extensively updated the book to cover the latest advances in generative #AI and robotics and to examine the future economic and job market implications of the
-
NVIDIA unveils Alpamayo 2 Super, its most powerful open AI for robotaxis
By
–
🔥NVIDIA released its most powerful open AI model for robotaxis
— Amitav Bhattacharjee (@bamitav) 2 juin 2026
NVIDIA just unveiled its most advanced open-source driving AI yet: Alpamayo 2 Super. At 32 billion parameters, it’s three times larger than its predecessor and designed to handle the messy reality of real-world… pic.twitter.com/fuBDEymqu9NVIDIA released its most powerful open AI model for robotaxis NVIDIA just unveiled its most advanced open-source driving AI yet: Alpamayo 2 Super. At 32 billion parameters, it’s three times larger than its predecessor and designed to handle the messy reality of real-world
-
Synthetic Data as Key to Making Robots Truly Usable
By
–
synthetic data is the key to make robots really usable
-
NVIDIA Launches Cosmos Coalition for Open World Models
By
–
7/ NVIDIA also launched the Cosmos Coalition – with Black Forest Labs, Runway, Skild AI, Agile Robots, LTX and Generalist – to push open world models forward together. The bet: world models are becoming the intelligence layer for robots and AVs, and NVIDIA wants the open
-
Cosmos 3 Nano and Super models on Hugging Face with datasets
By
–
6/ Two sizes, both live on Hugging Face right now: Cosmos 3 Nano (8B) — runs on a single workstation GPU for real-time robotics
Cosmos 3 Super (32B) — datacenter-grade, max quality Plus six open datasets and full post-training scripts on GitHub. -
Cosmos 3 tops open leaderboards for text, video, physics, and robotics
By
–
5/ And it's not a demo. Cosmos 3 tops the open leaderboards: #1 open model on Artificial Analysis for text→image AND image→video
#1 on Physics-IQ for physics accuracy — ahead of Sora 2
Leads PAI-Bench overall, ahead of Veo 3.1
#1 robot policy on RoboArena
Open weights beating -
Cosmos 3: Synthetic data generation for robotics, 60x faster, including rare edge cases.
By
–
4/ The real unlock is data. Robotics has always been bottlenecked by how little real-world training data exists. Cosmos 3 generates physically-accurate synthetic data up to 60x faster – including the rare edge cases you can't safely film: collisions, near-misses, accidents.
Eval -
Cosmos 3: native action generation for VLM, world model, robot
By
–
3/ Inputs and outputs span text, image, video, audio AND action.
— Chubby♨️ (@kimmonismus) 1 juin 2026
That last one is the big deal. Cosmos 3 was trained natively to generate actions, so the same checkpoint can run as a vision-language model, a video world model, or a robot policy. No multi-model orchestration. pic.twitter.com/PoLsK33ytZ3/ Inputs and outputs span text, image, video, audio AND action. That last one is the big deal. Cosmos 3 was trained natively to generate actions, so the same checkpoint can run as a vision-language model, a video world model, or a robot policy. No multi-model orchestration.
-
NVIDIA open-sources Cosmos 3, first open omnimodel for physical AI
By
–
1/ NVIDIA just open-sourced Cosmos 3 at GTC Taipei!
— Chubby♨️ (@kimmonismus) 1 juin 2026
It's the first fully open "omnimodel" for physical AI – one model that understands the real world, predicts what happens next, and generates the actions a robot should take.
Weights, code, datasets. All open. And this is… https://t.co/5Y8BbXUWqJ pic.twitter.com/3bOMlwO0B21/ NVIDIA just open-sourced Cosmos 3 at GTC Taipei! It's the first fully open "omnimodel" for physical AI – one model that understands the real world, predicts what happens next, and generates the actions a robot should take. Weights, code, datasets. All open. And this is