Introducing Cosmos 3: Our latest frontier model for Physical AI
Cosmos 3 is the world’s first fully open omnimodel with native vision reasoning, world and action generation.
Today we’re releasing Super (32B) and Nano (8B) variants.
This is coming for all of us.
Mathematicians are having a hard time dealing with what AI is doing on their lifes, but they arejust one of the first waves...
Like translators in 2024, photographers, graphic designers, or customer service reps...
We better find soon what are we going to do when our intelligence has no value.
This #CVPR2026 paper from our research team is trending #1 on @HuggingFace 🤗
Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act.
Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection.
Project page: https://t.co/O7JMe8tzFM
🚀Generate a 30-second 1080p video in just 7 seconds!
We’re open-sourcing FastVideo Dreamverse: real-time vibe directing for video generation on a single NVIDIA B200 GPU with LTX-2 model @ltx_model
Repo: https://t.co/xTXsfCB6pF
Blog: https://t.co/kA19cQhOJo
The future has arrived!
After a long wait, we are finally ready to reveal our complete space humanoid HELIOS.
After two semesters of intense work, research and iteration, this is what we have to show.
4 arms. 4 hands. 1 vision. 1 dream.
open sourcing Marlin-2B 🐟
a tiny VLM to extract structured information from videos
Marlin is finetuned for two questions devs want to ask in their videos: what is happening, and when?
Best open model in its weight class, competitive with Gemini-2.5-flash at only 2B params 🧵
Xynova just launched Flex 2, its second-gen hybrid dexterous hand — and Xiaomi is already on the cap table. 🤖✋
The spec sheet is sharp: 23 DOF, 400g palm, ±0.1mm repeatability, 0.05N force control, 12kg single-hand grasp load, and multimodal sensing for adaptive grasping and slip detection.
Xynova is not only building a robotic hand.
It is building the manipulation stack around it: micro linear actuators, joint modules, sensing, control, and developer-facing integration.
The Xiaomi link is confirmed.
Xiaomi Strategic Investment joined Xynova’s angel round and continued adding in the Pre-A round.
What is not confirmed: whether Xiaomi’s own robot hand uses Xynova’s technology.
That detail still has no public proof.
But the direction is clear: Xiaomi is putting money into the component layer that decides whether humanoids can actually handle objects, tools, and daily tasks.
This is the part of robotics that rarely looks flashy on stage.
But it decides what a robot can really do with its hands.
After a long wait since our last announcement, OpenArm 2.0 is finally here.
We're expanding from a robotic arm into a standard evaluation environment for Physical AI research, anchored by OpenArm Cell.
- OpenArm Cell for reproducible eval
- New pinch-type end effector
- Standardized cameras
- Redesigned J5 wrist (natural teleop)
- VR teleop
- Long-term stable release
https://t.co/3UqDHm4qPE
Gossip Goblin is arguably the best AI filmmaker in the world.
His new film THE PATCHWRIGHT is a masterpiece (10M+ views).
But nobody knows how he actually makes these.
Until now.
He let me share every step of the workflow with you 🧵👇