Our inference and training framework to run on the Cosmos Models
☆588Oct 30, 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…☆12,213Updated this week
- NVIDIA Cosmos Evaluator is an automated evaluation & grading system for synthetic video output generated by Cosmos models☆54Oct 20, 2026Updated last week
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,741Apr 19, 2026Updated 6 months ago
- A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models☆867Sep 10, 2026Updated last month
- Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence☆978Sep 17, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [RSS 2026] Causal video-action world model for generalist robot control☆1,964Jul 9, 2026Updated 3 months ago
- Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.☆481Oct 22, 2026Updated last week
- Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".☆1,135Updated this week
- Cosmos Policy☆895Jan 23, 2026Updated 9 months ago
- NVIDIA OmniDreams is a world model that generates photorealistic video for autonomous-driving simulation in real time.☆355Oct 2, 2026Updated 3 weeks ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆1,390Jun 8, 2026Updated 4 months ago
- high-performance inference and serving library for interactive autoregressive video and world models☆530Updated this week
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,624Aug 20, 2026Updated 2 months ago
- The first MoE-based framework for unified and scalable world modeling.☆25Jul 16, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactiv…☆1,017Oct 24, 2026Updated last week
- A simulation benchmarking platform for evaluating generalist robot policies☆598Updated this week
- Official code of Motus: A Unified Latent Action World Model☆1,317Oct 9, 2026Updated 3 weeks ago
- From Foundation to Application☆1,085Sep 22, 2026Updated last month
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆504Apr 16, 2026Updated 6 months ago
- WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models☆271Jul 22, 2026Updated 3 months ago
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing☆3,888Oct 8, 2026Updated 3 weeks ago
- Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos" (ICML 2026)☆1,125Mar 21, 2026Updated 7 months ago
- Cosmos Curator is a toolkit for curating physical AI training data.☆298Oct 16, 2026Updated 2 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time☆463Oct 31, 2025Updated last year
- ICLR 2026 Paper: Ctrl-World☆575Apr 8, 2026Updated 6 months ago
- [NIPS 2026 Reviewed (6/5/4)] PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation☆135Sep 8, 2026Updated last month
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆792Oct 29, 2025Updated last year
- Long Video Gen / World Model / World Action Model (Embodied) Infrastructure☆2,849Updated this week
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆755Jun 30, 2026Updated 4 months ago
- RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI☆5,548Updated this week
- Advancing Open-source World Models☆4,561Jul 9, 2026Updated 3 months ago
- [ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process☆1,113Feb 10, 2026Updated 8 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- GPT as Policy☆653Sep 16, 2026Updated last month
- [IROS 26 ScaleInfra Workshop Best Tool Paper] Involving over 50 Advanced Manipulation Policies☆508Updated this week
- Self-supervised learning for spatial perception☆1,004Jul 8, 2026Updated 3 months ago
- FLUX 3 Action: open weights 7B world action model from Black Forest Labs. Train, fine-tune and run action prediction for robots (DROID, S…☆202Oct 16, 2026Updated 2 weeks ago
- Infinite Worlds with Versatile Interactions☆1,895Sep 10, 2026Updated last month
- DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆626Oct 24, 2025Updated last year
- [RSS 2026] Interactive World Simulator for Robot Policy Training and Evaluation☆302Jun 4, 2026Updated 4 months ago