---
type: "post"
id: "new-nvidias-cosmos-3-tools-simulation-specific-models-3af45b"
slug: "new-nvidias-cosmos-3-tools-simulation-specific-models-3af45b"
title: "New NVIDIAS Cosmos 3 Tools — Simulation-Specific Models, Multimodal and Multisensory Data Processing Pipelines and an Open Framework for Physical AI"
description: "NVIDIA announced an expansion of its Cosmos platform with training tools, simulation checkpoints, and Cosmos Data Factory blueprints for physical-AI development."
retrieval_nugget: "NVIDIA announced an expansion of its Cosmos platform with training tools, simulation checkpoints, and Cosmos Data Factory blueprints for physical-AI development."
published_at: "2026-10-24"
updated_at: "2026-10-24"
record_date: "2026-10-24"
date_kind: "published_at"
topics: ["models"]
entities: ["NVIDIA","Cosmos","Cosmos 3 Nano","Cosmos Data Factory","Cosmos Curator","vLLM","SGLang"]
related_patterns: []
novelty_label: "same_event"
what_changed: "Same event as NVIDIA Cosmos Opens New Tools to Train, Evaluate and Deploy World Models"
prior_refs: ["memory:82ec9a8b-76eb-88c1-af75-90c369f58b6f","memory:5c591ea4-45be-86a3-a114-b645f2f71119","memory:b2499934-ee63-8cd5-aca7-22bc7b781eb7"]
source_url: "https://forums.developer.nvidia.com/t/new-nvidias-cosmos-3-tools-simulation-specific-models-multimodal-and-multisensory-data-processing-pipelines-and-an-open-framework-for-physical-ai/386457"
source_urls: ["https://forums.developer.nvidia.com/t/new-nvidias-cosmos-3-tools-simulation-specific-models-multimodal-and-multisensory-data-processing-pipelines-and-an-open-framework-for-physical-ai/386457"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:new-nvidias-cosmos-3-tools-simulation-specific-models-3af45b"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/new-nvidias-cosmos-3-tools-simulation-specific-models-3af45b/","markdown":"https://newruntime.com/posts/new-nvidias-cosmos-3-tools-simulation-specific-models-3af45b.md","json":"https://newruntime.com/posts/new-nvidias-cosmos-3-tools-simulation-specific-models-3af45b.json"}
---

# New NVIDIAS Cosmos 3 Tools — Simulation-Specific Models, Multimodal and Multisensory Data Processing Pipelines and an Open Framework for Physical AI

## Retrieval answer

NVIDIA announced an expansion of its Cosmos platform with training tools, simulation checkpoints, and Cosmos Data Factory blueprints for physical-AI development.

NVIDIA announced an expansion of its Cosmos platform with training tools, simulation checkpoints, and Cosmos Data Factory blueprints for physical-AI development. The company describes the release as support for building world models used in robotics, autonomous vehicles, smart infrastructure, and related simulation work.

The release includes four Cosmos 3 Nano example checkpoints, each based on a 16B model, for multiview and multisensory data augmentation and simulation. NVIDIA says recipes and Cosmos Framework skills accompany the checkpoints. Cosmos Curator now accepts multimodal, multisensory inputs and adds processing blocks; the Data Factory blueprints cover autonomous-vehicle training, defect-image analysis, and video augmentation.

For post-training, NVIDIA lists LoRA, supervised fine-tuning, new reinforcement-learning algorithms, distillation, and quantization for compatible pretrained models. It also lists HD Diffusers, vLLM/vLLM-Omni, and SGLang as inference options. The announcement points to open code, recipes, datasets, and downloadable checkpoints, but it does not establish benchmark results, license terms for every component, pricing for hosted access, or production performance of the example models.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)