Our inference and training framework to run on the Cosmos Models
☆451Aug 9, 2026Updated this week
Alternatives and similar repositories for cosmos-framework
Users that are interested in cosmos-framework are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomou…☆11,432Updated this week
- A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models☆770Jun 15, 2026Updated last month
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,529Apr 19, 2026Updated 3 months ago
- Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence☆912Updated this week
- Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.☆467Jul 31, 2026Updated last week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- NVIDIA Cosmos Evaluator is an automated evaluation & grading system for synthetic video output generated by Cosmos models☆42Jul 8, 2026Updated last month
- WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models☆253Jul 22, 2026Updated 2 weeks ago
- Cosmos Policy☆852Jan 23, 2026Updated 6 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆1,344Jun 8, 2026Updated 2 months ago
- [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactiv…☆915Jul 23, 2026Updated 2 weeks ago
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,275Apr 3, 2026Updated 4 months ago
- [RSS 2026] Causal video-action world model for generalist robot control☆1,741Jul 9, 2026Updated last month
- From Foundation to Application☆730Updated this week
- high-performance inference and serving library for interactive autoregressive video and world models☆451Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- NVIDIA Cosmos-Dreams (fka NVIDIA OmniDreams) is a world model that generates photorealistic video for autonomous-driving simulation in re…☆302Jul 24, 2026Updated 2 weeks ago
- Official code of Motus: A Unified Latent Action World Model☆1,220Jan 5, 2026Updated 7 months ago
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆715Jun 30, 2026Updated last month
- PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation☆117Jul 11, 2026Updated last month
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆489Apr 16, 2026Updated 3 months ago
- Self-supervised learning for spatial perception☆903Jul 8, 2026Updated last month
- ICLR 2026 Paper: Ctrl-World☆546Apr 8, 2026Updated 4 months ago
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆793Oct 29, 2025Updated 9 months ago
- ☆423Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Cosmos Curator is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dis…☆245Jul 31, 2026Updated last week
- Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos" (ICML 2026)☆1,032Mar 21, 2026Updated 4 months ago
- Advancing Open-source World Models☆4,349Jul 9, 2026Updated last month
- Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory☆131Jul 27, 2026Updated 2 weeks ago
- Native Multimodal Models are World Learners☆1,543Dec 30, 2025Updated 7 months ago
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing☆3,430Updated this week
- A Minimalist, Batteries-included Repository for Advancing World Model Science.☆705Jun 15, 2026Updated last month
- [ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time☆451Oct 31, 2025Updated 9 months ago
- [CVPR 2026 Highlight & Best Paper of VideoWorldModel Workshop] NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos☆648May 12, 2026Updated 2 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.☆1,311Jul 14, 2026Updated 3 weeks ago
- RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI☆4,500Updated this week
- ☆391Jul 30, 2026Updated last week
- Flow Map OPD for AnyStep Video Diffusion☆406May 23, 2026Updated 2 months ago
- [CVPR 2026] Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction☆368Mar 20, 2026Updated 4 months ago
- Infinite Worlds with Versatile Interactions☆1,496Jul 14, 2026Updated 3 weeks ago
- Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)☆3,476Sep 12, 2025Updated 10 months ago