New NVIDIA Cosmos 3 Open Models for Interactive World Simulation
We present a shared framework that adapts Cosmos world foundation models for real-time interactive world simulation in Physical AI.
Why am I seeing this Ranked on corroboration — 2 independent outlets
2 independent outlets carried this — Hugging Face and arXiv. Agreement across newsrooms that do not share an owner is the strongest thing we can measure, so it carries the most weight.
BreakingBreaking, because a first-party source announced it, at least two orgs have already carried it, and it is still fresh.
| Factor | Weight | Score | Contribution | Where it came from |
|---|---|---|---|---|
| Corroborationleads | 0.35 | 0.61 | +0.215 39% | 2 distinct tier-1/2 orgs, counted once each: Hugging Face and arXiv. Saturates at 5. |
| Source trust | 0.25 | 0.49 | +0.124 23% | Hugging Face is the highest-trust source on this story and is first-party — the organisation announcing its own news. Trust is taken from the best source, not averaged. |
| Pickup rate | 0.20 | 0.04 | +0.008 1% | The sources carry no usable publish times, so the rate could not be measured from them directly. |
| Freshness | 0.20 | 0.99 | +0.197 36% | Halves every 10 hours from the newest item on the story. This is the only factor that rewards a story for nothing more than being recent. |
Corroboration counts distinct organisations, once each, and only from tiers 1 and 2. Freshness halves every 10 hours, so this ranking is a snapshot and will differ at the next build.
What happened
We present a shared framework that adapts Cosmos world foundation models for real-time interactive world simulation in Physical AI. By streaming visual observations in response to actions and scene controls, the framework enables users and embodied agents to interact with evolving virtual environments. It supports both predicting the visual consequences of actions and generating observations from physical state maintained by an external simulator. We demonstrate this approach across camera navigation and robot manipulation, controllable video transfer, and multi-view autonomous vehicle (AV) simulation. These examples provide a shared foundation for developing interactive virtual environments for Physical AI training and evaluation.
How this story arrived
Ordered by when each source was first observed, which is what the velocity figure is computed from. Publishers backdate; observed order does not.
- 01 Arxivfirst-party first seen Interactive World Simulation with Cosmos for Physical AI
- 02 Huggingfacefirst-party +14.9h New NVIDIA Cosmos 3 Open Models for Interactive World Simulation
Overclock clusters coverage from independent sources and grades it automatically. The figures above are computed, not editorial. This page summarises and links to reporting by the outlets named — follow the links for the original work.