Skip to content

Add finetune guide to the landing doc #182

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Dinghow merged 1 commit into from
Jun 3, 2026
Merged

Add finetune guide to the landing doc #182

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
- [Choosing an Integration](#choosing-an-integration)
- [Examples](#examples)
- [Inference Benchmarks](#inference-benchmarks)
- [Finetune](#finetune)
- [Limitations](#limitations)
- [Ecosystem](#ecosystem)
- [News](#news)
Expand Down Expand Up @@ -641,6 +642,12 @@ Cosmos 3 latency and serving numbers live in [`inference_benchmarks.md`](inferen
| [Cosmos3-Super generator](inference_benchmarks.md#cosmos3-super-generator) | Generator | Cosmos3-Super | The same modalities and engines at the larger checkpoint scale |
| [Cosmos3-Nano reasoner](inference_benchmarks.md#cosmos3-nano-reasoner) | Reasoner | Cosmos3-Nano | vLLM serving metrics — TTFT, request latency, and throughput at concurrency 1/64/128/256 |

### Finetune

Finetune Cosmos 3 with the [Cosmos Framework](https://github.com/NVIDIA/cosmos-framework), NVIDIA's end-to-end Physical AI framework for training and serving world models. It provides runnable setup, inference, omni-model training, and evaluation workflows for the Generator and Reasoner surfaces, with reference recipes for vision, action, and reasoning post-training.

See the [Cosmos Framework training guide](https://github.com/NVIDIA/cosmos-framework/blob/main/docs/training.md) for the full post-training workflow, including data preparation, configuration, and launch commands.

### Limitations

Cosmos 3 can produce artifacts in long, high-resolution, or physically complex outputs. Common failure modes include temporal inconsistency, unstable camera or object motion, inaccurate sound-video alignment, imperfect action-state consistency, object morphing, inaccurate 3D structure, and implausible physical dynamics. Applications that require physically grounded simulation, safety-critical control, or complex multi-agent behavior need additional validation, guardrails, and system-level safety analysis before deployment.
Expand Down